机器学习学术速递[7.1]

AI 总结：提出分层全局注意力（HGA），作为预训练长上下文Transformer中密集因果注意力的即插即用替代方案，通过分层路由实现高效长上下文处理，在单GPU上支持64K token上下文，近似误差极小。

链接：https://arxiv.org/abs/2606.30709

机构：BMW Group（宝马集团）

作者：Woernle Frank, Fedosov Vladimir, Grinenko Artemiy

英文摘要：Hierarchical Global Attention (HGA) is a drop-in replacement for dense causal attention in pretrained long-context transformers. HGA preserves the original checkpoint parameters: the pretrained $W_Q$, $W_K$, $W_V$, and $W_O$ projections remain unchanged, no calibration parameters are introduced, and no retraining is required. Applied to Qwen3-30B-A3B-Instruct-2507-FP8 on a single RTX~5090 (32GB), the patched model runs out of the box at a 64K-token context, where token-level K/V storage is not feasible on this hardware. Unlike previous sparse-attention methods, HGA performs hierarchical two-level routing. It first retrieves relevant chunks using compact RoPE-aware summaries and then refines the selection by routing only the most relevant groups before performing exact token-level attention. This hierarchical retrieval significantly reduces the number of fetched tokens while preserving exact attention over the retrieved token set, making RAM- and NVMe-backed storage practical. The full historical token K/V resides in host RAM or NVMe storage, while only a small routed working set is transferred to GPU memory during attention. Consequently, GPU memory consumption depends primarily on model weights and the routed working set rather than on the total context length. Across all tested context lengths (4K - 64K tokens), routed attention remains within approximately $0.01$--$0.02$ nats of dense attention while the sparsity used is just about 3%. These results suggest that the approximation introduced by hierarchical routing is small, and that the remaining quality gap is likely dominated by long-context positional encoding rather than by the routing algorithm itself.

AI 总结：提出过程侧边栏方法，通过两系数编辑族修正安全训练后的记忆方向，实现记忆撤销，理论证明其二阶精度优于任务算术编辑。

链接：https://arxiv.org/abs/2606.30788

机构：Sideplane AI

作者：John Sweeney

英文摘要：Language models are often adapted in stages: a public skill phase, a private memory phase, and a later safety phase that learns to refuse outputs tied to the remembered entities. Revoking the memory after the safety phase is not the same problem as subtracting the memory update: the later safety optimizer has transported the memory direction. We introduce process sidecars, a two-coefficient edit family $\hat{\theta}(\lambda,\gamma)=\theta_{\mathrm{AMS}}-\lambda\Delta_{\mathrm{M}}-\gamma\hat{R}_{\mathrm{S}\leftarrow\mathrm{M}}$, with $\hat{R}_{\mathrm{S}\leftarrow\mathrm{M}}=\hat{J}_{\mathrm{S},\varepsilon}(\Delta_{\mathrm{M}})-\Delta_{\mathrm{M}}$, where $\hat{J}_{\mathrm{S},\varepsilon}$ is a centered secant through the realized future AdamW safety-training process. The implementation uses $\varepsilon=1$ at the natural memory-edit scale; it reuses $\theta_{\mathrm{AMS}}$ as the positive endpoint and computes one additional safety trace at $\theta_{\mathrm{A}}-\Delta_{\mathrm{M}}$. We prove two things. First, the exact sidecar, using the true transported direction $R_{\mathrm{S}\leftarrow\mathrm{M}}$ rather than the secant estimate, at $(\lambda,\gamma)=(1,1)$ recovers the counterfactual safety-only oracle $\theta_{\mathrm{AS}}$ up to second order; the proof treats AdamW as an augmented-state map over parameters, first moments, and second moments. Second, this process information is necessary: whenever future safety training bends the memory direction, every scalar task-arithmetic edit leaves first-order counterfactual error, while the process-sidecar edit is second-order accurate. Across three models, the validation-selected 2D edit improves held-out refusal closure over naive task arithmetic in all trials, and over the $\gamma=\lambda$ process-JVP subfamily, the diagonal slice of the cached 2D grid, in all paired trials.

AI 总结：提出多阶段延迟树，通过一系列稀疏决策树处理大部分样本，将少数样本延迟到后续树或黑盒模型，在保持高准确率的同时提升可解释性。

链接：https://arxiv.org/abs/2606.30995

机构：Duke University（杜克大学）； University of British Columbia（不列颠哥伦比亚大学）

作者：Zakk Heile, Hayden McTavish, Margo Seltzer, Cynthia Rudin

英文摘要： Recent work has shown that well-optimized individual decision trees can match complex black box models in some settings, primarily in noisy domains. For the remaining settings, however, complex ensembled compositions of trees often achieve higher accuracy at the cost of interpretability, leaving practitioners with difficult modeling decisions along an accuracy-interpretability tradeoff. Ideally, we would like to classify as much of the data as possible with one or a small number of trees, achieving interpretability for most samples while maintaining state-of-the-art accuracy. We introduce Multistage Defer Trees: a sequence of sparse decision trees that each make predictions for most samples, while deferring a small proportion to the next tree in the sequence or, ultimately, to a black box. We demonstrate that we can train this model class to match the performance of complex tree-based ensembles while routing most samples through only one or a small number of sparse decision trees. We discuss a range of techniques for training these models while maintaining simplicity. Our method expands the accuracy--interpretability frontier in settings where single-tree methods remain insufficient, demonstrating that even when complex models are necessary, they need not be fully opaque.

AI 总结：提出双通道神经网络DualNN，通过IQ通道参数共享高效处理复值信号，并基于Transformer实现Dualformer，在自动调制识别等任务上性能优于现有方法。

链接：https://arxiv.org/abs/2606.31352

机构：College of Electronic Science and Technology, National University of Defense Technology（国防科技大学电子科学学院）； Department of Electrical and Computer Engineering, The University of Hong Kong（香港大学电气与电子工程系）

作者：Yurui Zhao, Xiang Wang, Jingreng Lei, Wanlong Zhang, Yik-Chung Wu, Zhitao Huang

英文摘要：Designing effective feature extractors is critical for blind signal analysis tasks such as automatic modulation recognition (AMR), signal scheme recognition (SSR), and \color{black} signal structure parsing (SSP). In this work, we propose dual-channel neural network (DualNN) that efficiently exploits complex-valued signals through parameter sharing across IQ channels. Unlike traditional real-valued or complex-valued models, DualNN is a groundbreaking framework which shares the network parameters for processing the real and imaginary parts of the complex-valued signals, and is theoretically shown to reduce generalization error while preserving expressive capacity. Specifically, we propose a novel Transformer-based architecture to implement DualNN, called Dualformer. The Dualformer segments input signals into patch-level tokens and captures multi-granularity features, enabling robust performance across diverse signal analysis tasks. Furthermore, we conduct extensive experiments comparing Dualformer with three Transformer-based baselines and four conventional DL-based approaches. Results demonstrate consistent performance improvements on AMR, SSR, and SSP tasks. Besides, the modular design of DualNN allows it to generalize well to blind signal processing tasks such as blind source separation and low-SNR spectrum sensing. This work paves the way for a broader application of DualNN architectures in unsupervised and weakly supervised complex-valued signal analysis scenarios.

AI 总结：提出Mixture-of-Control（MoC）框架，通过稀疏混合专家机制自适应融合局部和全局控制信号，增强Transformer块间信息交换，实现高效微调。

链接：https://arxiv.org/abs/2606.31397

作者：Duc Anh Nguyen, Tien Ngoc Luu, Tung Pham, Toan Tran

英文摘要：State-based fine-tuning has emerged as a compelling alternative to weight-based adaptation for transformers, updating lightweight controls into states rather than model weights, offering substantial memory savings while retaining parameter efficiency. However, most existing state-based methods typically apply only per-block control updates, which limits inter-block information exchange and restricts representational adaptation. Meanwhile, prior mechanisms that enable cross-block communication often introduce considerable computational overhead, reducing their practicality for efficient fine-tuning. We introduce Mixture-of-Control (MoC), a lightweight fine-tuning framework that adaptively integrates local and global control signals to enhance representation learning. MoC treats block-wise control states as experts in a sparse mixture-of-experts process, enabling efficient communication across transformer blocks. Empirical results across diverse transformer-based benchmarks demonstrate that MoC outperforms state-based methods while maintaining a comparable memory and computational efficiency.

AI 总结：提出一种先决策后思考的并行推理方法，通过模型置信度识别分叉点并采样多条路径聚合，在保持或提升推理性能的同时，将token消耗降低30%，运行时间减少57%。

链接：https://arxiv.org/abs/2606.31484

作者：Zena Al-Khalili, Rafi Hakim, Dietrich Klakow, Ji-Ung Lee

英文摘要：Parallel thinking has enjoyed great success for boosting LLM performance on reasoning tasks without the need for any re-training. However, existing methods follow a think-first-then-decide paradigm, i.e., they first sample multiple reasoning paths, which inevitably leads to overgeneration, then prune or stop unnecessary paths to compensate. In contrast, decide-first-then-think, i.e., first identifying points that are likely to lead to desirable generations, has been underexplored so far. Following this paradigm, we propose Fork-think with confidence, that first identifies forking points using model confidence in a single seeding path, then triggers thinking, sampling multiple continuations and aggregating them for the final response. Our experiments across three models and three reasoning benchmarks show that Fork-think reduces the token consumption by up to 30% and run-time by up to 57%, while performing comparable to or better than parallel thinking. Our analysis reveals that Fork-think is able to identify forking points that are meaningful with respect to the downstream task and that sampling at later positions can lead to substantially better generations. Finally, we demonstrate how combining Fork-think with existing mechanisms such as early stopping and weighted voting can further boost the performance and perform comparably to existing state-of-the-art methods, without requiring any warm-up or offline training. Our results establish pre-determined forking as a promising research direction for efficient LLM reasoning.

AI 总结：本文通过动力学李代数框架揭示参数化量子电路的贫瘠高原源于其希尔伯特空间容量，并提出基于群论几何先验的结构正则化方法，在保持多项式级DLA增长的同时确保梯度丰富，实现可设计可训练性。

链接：https://arxiv.org/abs/2606.31536

机构：Tunghai University（东海大学）

作者：Kung-Ming Lan

英文摘要：As Quantum Machine Learning (QML) transitions toward practical implementation, the field faces a critical architectural bottleneck that challenges the fundamental assumptions of classical statistical learning theory. In classical deep learning, increasing model capacity typically risks overfitting. However, this study advances a counter-intuitive paradigm: unstructured contemporary QML architectures suffer from a profound state of quantum underfitting, driven by the "expressivity-trainability paradox." We demonstrate that the vast Hilbert space capacity of Parameterized Quantum Circuits (PQCs)-traditionally chased as the source of quantum advantage is the direct mathematical cause of Barren Plateaus (BPs), where gradient landscapes become exponentially flat. By synthesizing recent breakthroughs in Dynamical Lie Algebras (DLAs) and Geometric QML, we establish a comprehensive framework linking the algebraic dimension of circuit generators to their optimization dynamics. Furthermore, we empirically validate this framework on a non-linear binary classification task, illuminating a uniquely quantum manifestation of the bias-variance tradeoff: while unstructured architectures achieve near-perfect training accuracy via unscalable parameterization (quantum overfitting), embedding group-theoretic geometric priors acts as a structural regularizer. By restricting the DLA growth to a polynomial regime, our symmetry-preserving approach sacrifices raw memorization capacity to guarantee scalable, gradient-rich training landscapes, offering a robust roadmap for "Trainability-by-Design" in scalable quantum neural networks.

AI 总结：提出模误差路由扩展误差扩散法，在严格遵循戴尔原则的双流兴奋/抑制网络中，实现MNIST 96.7%和CIFAR-10 61.7%的分类性能，并集成PPO在强化学习任务中取得竞争性结果。

链接：https://arxiv.org/abs/2606.31700

机构：Sakana AI

作者：Yutaro Yamada, Luca Grillotti, Rujikorn Charakorn, Sebastian Risi, David Ha, Robert Tjarko Lange

英文摘要：Biological neural circuits obey Dale's principle: each neuron's synapses are uniformly excitatory or inhibitory. Artificial networks that respect this constraint must coordinate separate excitatory and inhibitory populations, fundamentally changing how credit is assigned during learning. Several biologically plausible learning rules avoid backpropagation's weight transport requirement, but it has been difficult to achieve strong performance under Dale's principle beyond MNIST. Error Diffusion (ED) was originally proposed in a dual-stream excitatory/inhibitory architecture, where learning is driven by routing global error signals to all layers without transporting transposed forward weights or relying on random feedback matrices. Whether such a rule can scale under Dale's principle across both supervised classification and reinforcement learning remains unknown. Here, we introduce modulo error routing to extend Error Diffusion beyond binary classification, and show that a dual-stream excitatory/inhibitory architecture trained with this method achieves 96.7% on MNIST and establishes a 61.7% baseline on CIFAR-10, demonstrating that representation learning is possible even when strictly enforcing Dale's principle. For the classification setting, we introduce three domain-specific innovations: layer-specific sigmoid widths, batch-centered class error signals, and asymmetric initialization, and ablation analysis reveals that their relative importance reverses between MNIST and CIFAR-10, exposing task-dependent credit-assignment bottlenecks invisible to single-benchmark evaluation. In reinforcement learning, we integrate ED with Proximal Policy Optimization (PPO) and evaluate it on continuous-control tasks in Google Brax and on Craftax, an open-ended exploration task. We show that ED-PPO achieves competitive performance relative to Direct Feedback Alignment, a backpropagation-free baseline.

AI 总结：提出LOTUS方法，利用循环Transformer在潜在空间进行多步推理，通过并行监督潜在块上的CoT令牌，首次在3B规模弥合与显式CoT的差距，并将推理延迟降低2.5-6.9倍。

链接：https://arxiv.org/abs/2606.31779

机构：UW-Madison（威斯康星大学麦迪逊分校）； Microsoft Research（微软研究院）； ETH Zürich（苏黎世联邦理工学院）； KRAFTON（魁匠团）； Ludo Robotics

作者：Ying Fan, Anej Svete, Kangwook Lee

英文摘要：Language models typically reason via explicit chain-of-thought (CoT), generating intermediate steps token-by-token. Latent CoT offers an alternative: it performs multi-step reasoning in the model's hidden states, replacing decoded tokens with continuous representations for greater efficiency. However, existing latent CoT methods underperform explicit CoT beyond 1B parameters, and the gap widens with scale. Looped, or recurrent-depth, Transformers, which reuse their weights to increase computation depth without adding parameters, are a natural fit for latent reasoning. We therefore ask whether looped Transformers can bridge this gap. We answer affirmatively with a simple recipe: a looped padded Transformer that processes K latent blocks in parallel for R iterations, with a cross-entropy loss on each latent position's gold CoT-step token, similar to explicit CoT supervision. We instantiate it as LOTUS (Looped Transformers with parallel supervision on latents). LOTUS is, to our knowledge, the first latent-CoT method to bridge the gap to explicit CoT at the 3B scale, while cutting thought-phase latency by 2.5x-6.9x from compact math expressions to natural language. Projecting LOTUS's post-loop latents through the base LM head recovers the gold reasoning steps and even surfaces alternative valid intermediate steps, evidence that its latent space is interpretable and CoT-aligned. Ablations confirm that both the looped backbone and the parallel supervision on gold CoT tokens are essential.

AI 总结：通过限制每层宽度为3，研究前馈网络、ResNet和Transformer如何改变低维拓扑不变量（如环绕数），揭示不同架构的表达能力差异。

链接：https://arxiv.org/abs/2606.31856

作者：Junyu Ren, Lek-Heng Lim

英文摘要： We study layered models, including feedforward networks, ResNets, and transformers, by limiting each layer to a width of $d = 3$, i.e., $\mathbb{R}^3$ as representation space. This allows us to track how a neural network changes low-dimensional topological invariants through its layers. Just about any topological structure may be simplified or even trivialized by simply increasing dimension; e.g., any knot is equivalent to an unknot in $\mathbb{R}^4$. By restricting to $\mathbb{R}^3$, we not only isolate the effects of activation and depth from that of width, we work in a space that lends itself to easy visualization. We focus on linking number here, deferring other invariants like link groups, Milnor's $\bar{\mu}$-invariants, knot types, ambient cobordisms, to a sequel. We provide full proofs and empirical experiments to justify the following insights: When measured by their power to effect changes in linking numbers, the layer-skipping feature in ResNets is as powerful as the attention mechanism in transformers; both ResNets and transformers are strictly more powerful than feedforward neural networks with monotonic activations, which are in turn more powerful than invertible and flow-based models; but replacing monotonic activation with a nonmonotonic one elevates a feedforward network into the same expressivity class as ResNets and transformers. These results suggest that low-dimensional topology can be a useful tool to guide designs of AI architectures. We also generalize our results from $d = 3$ to arbitrary $d > 3$.

AI 总结：提出Review Residuals，通过基于当前状态和提议更新的学习门控缩放残差更新，在大型Transformer中提升训练稳定性和性能，优势随模型规模增大而增强。

链接：https://arxiv.org/abs/2606.31859

作者：Kyle Kramer

英文摘要：Residual connections add every sublayer's proposed update with a fixed coefficient of one; the network never evaluates whether an update is reliable before committing it. Drawing on the human-factors principle of independent verification, we introduce Review Residuals, which scale each update by a learned, input-dependent gate conditioned on both the current state and the proposed update: h_l = h_{l-1} + r_l * u_l with r_l = sigmoid(W[RMSNorm(h_{l-1}), RMSNorm(u_l)]). Conditioning the gate on the update is the property that distinguishes it from prior gated and scaled residuals. We report two findings. First, a depth-stability result: a convex (Highway-style) form of the gate reintroduces vanishing gradients and fails to train beyond ~20 layers, whereas the additive, identity-preserving form trains stably at all depths we tested. Second, an emergence-with-scale result: trained from scratch across five sizes (60M-1B parameters, multi-seed), Review Residuals show no advantage at small scale but at 590M significantly outperform both a parameter-matched Highway gate and a parameter-matched standard residual (p<0.05), with a larger advantage at 1B. The benefit grows with model size rather than shrinking.

AI 总结：针对RMSNorm模型，提出有符号排列坐标传输方法，解决排列对齐不完整问题，在跨运行坐标恢复、工具迁移和训练状态保持上显著优于纯排列方法。

链接：https://arxiv.org/abs/2606.31963

机构：Sideplane AI

作者：John Sweeney

英文摘要：Modern LLM workflows move coordinate-indexed objects across checkpoints: steering vectors, sparse autoencoders, top-$k$ neuron sets, attribution lists, and merge alignments. This is only well posed after fixing the model's residual-stream gauge, which we show is architecture-dependent: LayerNorm residual charts have permutation gauge $S_d$ (up to a global sign flip), while RMSNorm charts with generic per-channel gain have signed-permutation gauge $B_d = S_d \ltimes \{\pm 1\}^d$. Permutation-only alignment is therefore symmetry-incomplete for RMSNorm models. We introduce sign-marginalized Hungarian matching and prove a sharp failure mode: with decorrelated coordinates, raw signed-correlation matching has a structural permutation-accuracy ceiling at the positive-sign fraction of the true gauge, which sign-marginalization removes. We then make coordinate-preserving transport, not function-level merging, the primary object: composing saved-checkpoint local $B_d$ gauges along same-base fine-tuning trajectories recovers 91.1% of cross-run coordinates at 1500 steps versus 60.3% for endpoint matching, and the gain is not explained by merely routing through the base. The recovered gauge transfers tools that permutation-only alignment breaks: TinyLlama SAE reconstruction has NMSE 0.004 under $B_d$ versus 1.08 under $S_d$; Qwen sentiment steering preserves 95.8% of its effect versus 17.2%; refusal steering reverses sign under $S_d$; coordinate-preserving merges behave the same way. The same covariance governs stateful training: signed transport of AdamW state preserves the resumed trajectory, while permutation-only state follows a different one from a functionally identical checkpoint. Finally, gauge-sweep audits show index-level interpretability claims are reproducible only relative to an explicit gauge.

AI 总结：提出语义参考框架(SemRF)，通过锚点固定实现残差流语义坐标的稳定测量，并利用Voronoi迹定义最小作用路径，揭示层间计算与参数效率的关系。

链接：https://arxiv.org/abs/2606.32022

机构：Monash University（莫纳什大学）； Technical University of Munich（慕尼黑工业大学）； Chongqing University（重庆大学）

作者：Jian Gu, Aldeida Aleti, Chunyang Chen, Hongyu Zhang

英文摘要：Residual-stream analysis asks how language-model computation evolves across depth, but intermediate decoding requires comparable readout coordinates across layers. If embedding anchors and unembedding readout disagree on the chosen span, apparent motion may reflect measurement drift rather than computation. We introduce \emph{Semantic Reference Frames} (SemRF), an anchor-based formalism separating semantic measurement from residual dynamics. A SemRF fixes anchors and measures states against them. Pseudo-inverse tying gives exact synchronization; under restricted bi-invertibility, SemRF yields stable semantic-basis coordinates, distortion bounds, and near-identity changes. With the frame fixed, residual computation becomes a depthwise semantic trajectory. The anchors induce a semantic Voronoi diagram: distance, or evidence such as logits, assigns each layer to a coarse cell, while coordinates retain within-cell motion and margins. We define layerwise steps, contribution profiles, and imbalance diagnostics, then use the Voronoi trace to define a margin-relaxed tube. The canonical trace is the minimum-action path inside this tube; when nonempty with positive quadratic weight, it is unique and obeys a discrete spline equation away from active constraints. Excess action controls step, curvature, and profile mismatch. Low curvature implies piecewise-linear compressibility and local knowledge density: lower trace complexity means fewer semantic knots. Through the parameter-to-trajectory map, this gives a conditional link to parameter efficiency: among admissible settings fitting data, lower-action and lower-complexity traces use fewer semantic degrees of freedom. The guarantees require controlled interface error and small projection residual under explicit tube constraints.

AI 总结：提出AdaJEPA，一种在模型预测控制闭环中进行测试时自适应的潜在世界模型，通过自监督信号持续校准模型，显著提升规划成功率。

链接：https://arxiv.org/abs/2606.32026

机构：New York University（纽约大学）； AMI Labs（AMI实验室）

作者：Ying Wang, Oumayma Bounou, Yann LeCun, Mengye Ren

英文摘要：Latent world models enable planning from high-dimensional observations by predicting future states in a compact latent space. However, these models are typically kept frozen at test time: when their predictions become inaccurate, planning can fail, especially under test-time distribution shift. To address this, we propose AdaJEPA, an adaptive latent world model that performs test-time adaptation within the closed loop of model predictive control (MPC). After training, AdaJEPA plans and executes the first action chunk, uses the observed next-state transition as a self-supervised adaptation signal, and replans with the updated model. This closed-loop update continuously recalibrates the world model without additional expert demonstrations. Across a range of goal-reaching tasks, AdaJEPA substantially improves planning success with as few as one gradient step per MPC replanning step.

AI 总结：利用稀疏自编码器解决高维生物数据中神经网络表示空间的叠加问题，恢复几何保真度，并通过Gromov-Wasserstein最优传输实现图像与单细胞RNA测序数据的跨模态对齐。

链接：https://arxiv.org/abs/2606.31394

机构：KAIST（韩国科学技术院）； Konyang University（建阳大学）； Chang Gung University（长庚大学）； UCL Queen Square Institute of Neurology & The Francis Crick Institute（伦敦大学学院皇后广场神经病学研究所与弗朗西斯·克里克研究所）

作者：Jisung Park, Seohyeon Kang, Daeun Yoo, Eunsu Lee, Seoin Cho, Wooyeop Choi, Ian Choi, James R. Evan, Daesoo Kim, Sonia Gandhi, Minee L. Choi

英文摘要：Artificial intelligence is transforming our capability to solve biological challenges. In dimensionality bottleneck regimes exacerbated by high-dimensional biological data, Neural networks force distinct concepts into the lower dimensions known as superposition. Although this superposition is widely known to hinder interpretability, its impact on corrupting the geometry of latent spaces remains critically overlooked. Here, we utilized sparse autoencoders (SAEs) trained on over 100,000 multiplexed images of patient-derived Parkinson's disease and healthy neurons to resolve superposition. This approach bypasses the mathematical non-uniqueness of feature attribution by shifting to interpretable latent representation analysis. We theoretically and empirically demonstrate that superposition contaminates representational metric spaces, and thereby SAEs successfully recover geometric fidelity. By treating these geometrically purified representations as single-cell state vectors, we adapted single-cell RNA sequencing (scRNA-seq) data analysis methodologies directly to the image domain. Finally, we introduce GW-map, utilizing Gromov-Wasserstein optimal transport to align these image representations with authentic scRNA-seq data \emph{de novo}. This coupling reconstructs hierarchical neuronal pathology pathways such as Calcium-AIS scaffold, without reference spatial transcriptomics, establishing a scalable foundation for spatial biology. Code is available at this https URL

AI 总结：针对噪声专家反馈场景，理论证明离线模仿学习样本复杂度指数增长，而在线策略蒸馏可实现多项式依赖，解释了为何在线方法优于离线方法。

链接：https://arxiv.org/abs/2606.30923

机构：Columbia University（哥伦比亚大学）

作者：Ved Sriraman, Peihan Liu, Daniel Hsu, Adam Block

英文摘要：Imitation Learning is a natural framework for learning in sequential decision-making systems and has emerged as the dominant paradigm through which we understand language model training. A central puzzle is that, while in theory offline IL can be horizon-free and optimal, in practice online methods such as on-policy distillation often outperform offline methods such as supervised fine-tuning. We propose a noisy expert model to explain this gap, in which the learner only has access to a noisy version of the expert's policy, but wishes to compete against the reward achieved by a clean expert, motivated by the fact that in many applications, e.g. training language models to perform long chains of thought, the expert is often imperfect. In this setting, we show a sharp separation between offline and online IL. Offline learning from noisy trajectories is fundamentally hard: to compete with the clean expert, the sample complexity must grow exponentially, in contradistinction to the clean expert setting where no explicit horizon dependence exists. In contrast, we prove that online interaction with the noisy expert via a novel variant of OPD enables polynomial dependence on the horizon in general. We further show that, under a natural condition on the expert noise distribution, which we show to be necessary for any horizon-free sample complexity, one can obtain such a guarantee, although our proposed algorithm sacrifices statistical efficiency in its dependence on the size of the policy class. Our analysis leads to an alternative loss function that is commonly considered empirically for LM training. We further provide algorithms and lower bounds, and extend our results to the more realistic setting of unknown corruption when the clean expert is deterministic, thereby providing a theoretical foundation for why OPD can outperform SFT when training language models from imperfect teachers.

AI 总结：提出一种离线强化学习框架，通过传感器位置条件架构和点注意力层实现多传感器布局下的策略提取，在K-S方程和Navier-Stokes方程控制问题中验证了灵活性和有效性。

链接：https://arxiv.org/abs/2606.31025

机构： University of Notre Dame（圣母大学）； Lawrence Livermore National Laboratory（劳伦斯利弗莫尔国家实验室）； Cornell University（康奈尔大学）

作者：Deepak Akhare, Luning Sun, Xin-Yang Liu, Xiantao Fan, Timo Bremer, Ben Zhu, Jian-Xun Wang

英文摘要：Active flow control is a fundamental application in engineering. Recent advances in deep reinforcement learning have made progress in this field. However, the classical online RL approaches require extensive real-time interactions with the high fidelity environment, while each sensor configuration change necessitates whole policy retraining. All these factors result in prohibitive computational costs for real-world applications. In this work, we propose a novel offline RL framework that addresses both challenges through data-driven policy extraction. We develop a sensor position-conditioned architecture that enables a single policy network to adapt seamlessly to multiple sensor arrangements. The position-conditioned approach incorporated spatial relationship modeling through Point Attention layers to ensure the generalizability to varying sensor placements. We demonstrate the framework on two representative problems, mitigating chaoticity in the Kuramoto-Sivashinsky equation and flow control over airfoils governed by the Navier-Stokes equation. The result demonstrates that the policy extraction from the dataset provides unprecedented flexibility for sensor placement optimization. This approach represents a significant step towards adaptive, intelligent flow control systems.

AI 总结：针对残差强化学习在动力学偏移下无法调整分布形状的问题，提出Warp RL方法，通过可逆状态条件变换重塑基础策略的动作分布，在ManiSkill3任务和真实机器人插销任务中优于残差校正。

链接：https://arxiv.org/abs/2606.31043

机构：University of Sydney（悉尼大学）； NVIDIA（英伟达）

作者：Ethan Hirschowitz, Fabio Ramos

英文摘要：Residual reinforcement learning adapts a pretrained robot policy by learning an additive correction to its actions. While effective when adaptation amounts to shifting the base policy's action distribution, additive corrections cannot change the distribution's shape, scale, or state-dependent geometry -- limitations we formalize as wrong variance, miscalibrated confidence, and non-uniform correction. We show that these matter under dynamics shift: when the base distribution is geometrically mismatched to the shifted system, residual correction can underperform even the unadapted policy. We propose \textbf{Warp RL}, a policy adaptation method that replaces additive residuals with an invertible, state-conditioned transformation of the base policy's action distribution. Instantiated with monotonic rational-quadratic spline flows [ arXiv:0706.1234v1 ], Warp RL preserves identity initialization, strictly generalizes additive residual correction, and exposes a structured adaptation space suitable for both policy-gradient and gradient-free optimization. Across a variety of ManiSkill3 manipulation tasks with controlled dynamics shifts, Warp RL matches residual correction when translation is sufficient and substantially outperforms it when adaptation requires distributional reshaping. We further demonstrate that warping can replace additive correction in an off-policy sim-to-real pipeline, achieving comparable success rate with 30% faster task completion on a real-robot peg-insertion task.

AI 总结：提出AET框架统一非线性MORL的SER和ESR范式，并基于此设计AETDICE离线算法，通过增广状态空间的密度比估计实现静态数据集优化。

链接：https://arxiv.org/abs/2606.31178

机构：Korea University（高丽大学）； Yonsei University（延世大学）； Gauss Labs Inc.（Gauss Labs公司）

作者：Woosung Kim, Youngjun Suh, Jinho Lee, Jongmin Lee, Byung-Jun Lee

英文摘要：Optimizing nonlinear preferences in multi-objective reinforcement learning (MORL) is essential for capturing complex trade-offs like risk aversion or fairness. However, such non-linearity has historically bifurcated nonlinear MORL objectives into two distinct paradigms: Scalarized Expected Return (SER) and Expected Scalarized Return (ESR). While SER requires global-level optimization and ESR requires non-Markovian policies, leading to fragmented optimization strategies, we bridge this divide through the Aggregation-Expectation-Transformation (AET) framework. By unifying both criteria through a tripartite decomposition of scalarization, AET provides a principled foundation for general nonlinear MORL. Building on this framework, we propose AETDICE, a tractable offline RL algorithm for AET objectives. By utilizing DICE-style density-ratio estimation in an augmented state space, AETDICE enables sample-based optimization from static datasets. Our framework resolves long-standing barriers and captures respective trade-offs induced by AET framework, which existing methods fail to address.

AI 总结：提出贝叶斯上下文实验者框架，利用Transformer模仿贝叶斯后验Neyman分配策略，通过注意力机制和投影梯度下降实现平滑自适应的平均处理效应高效估计。

链接：https://arxiv.org/abs/2606.31184

机构：Laboratory for Information and Decision Systems, MIT（麻省理工学院信息与决策系统实验室）

作者：Jiachun Li, David Simchi-Levi

英文摘要：Adaptive experiments for average treatment effects (ATE) require randomized allocations balancing valid inference with statistical efficiency. The oracle design is a covariate-dependent Neyman rule governed by unknown arm-conditional outcome variances. We investigate whether this sequential variance-estimation and allocation process can be amortized via in-context learning. We introduce Bayesian in-context experimenters: transformer policies trained to imitate a Bayesian posterior Neyman teacher. The teacher updates nonparametric beliefs over potential outcomes using experimental history to assign posterior Neyman treatment probabilities. This design converges to the oracle rule, supporting efficient ATE inference. Transformers constructively implement this mapping through attention-based sufficient statistics and projected gradient descent, imitating Bayesian updating for Gaussian-series priors. To address unknown outcome smoothness, we combine smoothness-indexed experimenters using a mixture-of-experts transformer. The gate acts as a hierarchical posterior over smoothness classes, concentrating on near-oracle experts. By bounding the complexity of the transformer class, we prove this amortized policy can be learned via empirical risk minimization using supervised pretraining. Experiments confirm accurate teacher imitation, adaptive allocation, and improved ATE precision over baselines.

AI 总结：本文探索深度强化学习在航天器再入姿态控制中的应用，通过动力学随机化提升泛化能力，混合控制器在操作包线内表现出优于传统控制的跟踪精度和鲁棒性。

链接：https://arxiv.org/abs/2606.31291

作者：Alexander Fabisch, Melvin Laux, Mariela De Lucas Álvarez, Edoardo Caroselli, Julian Theis

英文摘要：Deep reinforcement learning has the potential to solve attitude control problems more adaptively, precisely, and robustly by handling nonlinear dynamics, uncertainties, and failure cases more effectively than traditional attitude control approaches. We explore reinforcement learning (RL) for attitude control in spacecraft re-entry. An industry-standard proportional-integral-derivative controller with gain scheduling serves as a strong baseline for model-free RL and hybrid controllers that combine these two approaches. We formalize the application in the RL framework to apply continuous, off-policy RL. State-of-the-art RL achieves comparable performance to traditional control approaches in this domain. However, its out-of-distribution generalization is not sufficient. Hence, we use dynamics randomization to introduce challenging task variations during training and enforce generalization in a predefined operational envelope. Finally, we assess the best obtained RL-based controllers with application-specific metrics to show superior performance in comparison to traditional controllers in the operational envelope, that is, hybrid controllers are able to track the angle of attack better and are more robust under variations of mass, inertia tensor, and flap actuator bandwidth.

AI 总结：提出AutoSafe架构，通过将结构化安全监控与干预直接集成到动作生成中，实现性能与安全行为之间的平滑风险依赖转换，在连续控制基准和实物倒立摆系统上验证了强安全性与学习平滑性。

链接：https://arxiv.org/abs/2606.31320

机构：Technical University of Munich（慕尼黑工业大学）； University of Oxford（牛津大学）； University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）

作者：Hongpeng Cao, Liqun Zhao, Yuliang Gu, Naira Hovakimyan, Lui Sha, Marco Caccamo

英文摘要：Safe online reinforcement learning requires policies to respect safety constraints while maintaining smooth optimization dynamics. Existing approaches typically rely on either strict safety enforcement via action interventions, which introduce discontinuities in system interaction and learning, or soft safety constraint formulations, which preserve smooth learning but provide limited safety assurance. We propose AutoSafe, a safety-aware policy architecture that integrates structured safety monitoring and intervention directly into the action generation process. This design enables smooth, risk-dependent transitions between performance-driven and safety-preserving behaviors, resulting in continuous online interaction and learning dynamics. Empirical results across a suite of continuous-control benchmarks demonstrate strong safety enforcement without sacrificing learning smoothness. We further validate AutoSafe on a physical cart-pole system, highlighting its practical effectiveness for safe online learning in the real world.

AI 总结：针对有限自适应性的上下文式板赌博机问题，提出两种算法B-SlateGLinCB和RS-SlateGLinCB，分别适用于批处理和少切换设置，在多样性假设下实现与非线性参数无关的遗憾界，并具有计算效率。

链接：https://arxiv.org/abs/2606.31449

机构：Microsoft Research India（微软研究院印度）

作者：Tanmay Goyal, Sukruta Prakash Midigeshi, Gaurav Sinha

英文摘要：We investigate the contextual slate bandit problem with generalized linear rewards under limited adaptivity. At each round, the learner is presented with $N$ sets of items, where each item is represented by a $d$-dimensional feature vector. The learner then constructs a slate by selecting one item per set; the resulting slate yields a scalar reward sampled from a Generalized Linear Model (GLM). We propose algorithms under two limited-adaptivity settings: (a) Batched and (b) Rarely-Switching. For the batched setting, we introduce B-SlateGLinCB, which partitions the time horizon into $\mathcal{O}(\log\log T)$ batches such that each batch's policy relies only on data from previous batches. For the rarely-switching setting, we propose RS-SlateGLinCB, which adaptively performs only $\mathcal{O}(Nd\log T)$ parameter updates. Under a diversity assumption on the item sequences, we prove that B-SlateGLinCB and RS-SlateGLinCB achieve regret bounds of $\mathcal{O}(Nd^{3/2}\sqrt{T})$ and $\mathcal{O}(Nd\sqrt{T})$, respectively. Notably, both bounds are independent of the non-linearity parameter $\kappa$ that is typically found to scale the regret of GLM bandit algorithms. Our algorithms are computationally efficient, requiring only $\text{poly}(N)$ time per round despite $2^{\Omega(N)}$ possible slates. Simulations show our algorithms outperform existing baselines with limited adaptivity and remain competitive with Slate-GLM-OFU, a fully adaptive state-of-the-art algorithm. Notably, a slightly modified B-SlateGLinCB empirically matches this baseline. Finally, we demonstrate strong performance in a practical in-context example selection task for language models.

AI 总结：提出ECHO框架，通过选择性回合记忆和源索引重建解决长程智能体强化学习中的历史崩溃与可追踪学习问题，在BrowseComp-Plus上达到43.4%准确率，优于GRPO和SUPO。

链接：https://arxiv.org/abs/2606.31650

机构：School of Mathematical Sciences, Peking University（北京大学数学科学学院）； Baidu Inc.（百度公司）； University of Science and Technology of China（中国科学技术大学）

作者：Zijun Xie, Binbin Zheng, Enlei Gong, Jihua Liu, Yuyang You, Lingfeng Liu, Jiayao Tang, Guanqun Zhao, Aoqi Hu, Zeyu Chen

英文摘要： Long-horizon language agents must repeatedly interact with tools, accumulate evidence, and make decisions under bounded context windows. Existing context-management methods make such rollouts feasible by truncating distant history, folding past turns into summaries, or selecting compact memory states. However, these breakthroughs introduce two coupled limitations. First, as the number of turns grows, historical observations are progressively removed or collapsed into compressed states, making it harder for the policy to reuse fine-grained evidence. Second, once the original turns are no longer source-addressable, outcome-based RL loses an explicit path for aligning policy updates with the evidence that supported a successful final answer. To this end, we propose ECHO, a selective turn-memory framework that jointly addresses history collapse and traceable learning through source-indexed reconstruction. Specifically, ECHO compresses each completed environment turn into a compact memory record, reconstructs bounded policy contexts by selecting from these records, and reuses the selected source indices to route positive outcome credit to the evidence and selection actions that support successful answers. On BrowseComp-Plus, ECHO reaches 43.4% held-out accuracy, outperforming GRPO (28.9%) and the rolling-summary baseline SUPO (36.1%), while using fewer turns and lower trajectory volume than SUPO (Figure 1). Additionally, the trained policy improves zero-shot generalization across multi-objective QA, code generation, and deep information-seeking benchmarks on both dense and MoE backbones.

AI 总结：针对在线表格马尔可夫决策过程，提出基于乐观跟随正则化领导者的算法，通过设计乐观Q函数估计器和数据依赖转移奖励，在未知转移下实现一阶、二阶和路径长度遗憾界，并达到随机情形下的间隙相关polylog(T)遗憾。

链接：https://arxiv.org/abs/2606.31769

作者：Mingyi Li, Taira Tsuchiya, Kenji Yamanishi

英文摘要：We study policy optimization for online episodic tabular Markov decision processes with unknown transition kernels, aiming for best-of-both-worlds guarantees together with data-dependent regret bounds. Recent work (Dann et al., 2023; Li et al., 2026) has shown that policy optimization can adapt to both adversarial and stochastic losses with first-order, second-order, and path-length bounds, but only under known transitions, leaving open whether such data-dependent guarantees are achievable by policy optimization when the transition kernel is unknown. We resolve this by developing a new algorithm based on optimistic follow-the-regularized-leader that attains these guarantees under unknown transitions. The key ingredient is a new design of optimistic $Q$-function estimators together with a data-dependent transition bonus that controls estimator bias through the loss-prediction error. Our analysis further identifies an unavoidable transition-dependent complexity term that captures the intrinsic cost of estimating the transition kernel. As a result, we obtain first-order, second-order, and path-length bounds with the transition-dependent complexity term while simultaneously achieving gap-dependent $\mathrm{polylog}(T)$ regret in the stochastic regime.

AI 总结：提出TRIAGE框架，通过角色类型化信用分配修正GRPO仅依赖结果信用的盲点，在ALFWorld等任务中提升成功率并减少交互步数。

链接：https://arxiv.org/abs/2606.32017

机构：LinkedIn Corporation（领英公司）； Harvard University（哈佛大学）； Johns Hopkins University（约翰霍普金斯大学）

作者：Yuanda Xu, Zhengze Zhou, Hejian Sang, Xiaomin Li, Jiaxin Zhang, Xinchen Du, Zhipeng Wang, Alborz Geramifard

英文摘要：Agentic reinforcement learning requires assigning credit to environment-facing actions such as searches, clicks, edits, navigation commands, and object interactions. Standard GRPO uses the final verifier outcome as a uniform advantage over all action tokens. This outcome signal is useful but structurally incomplete: it punishes useful exploration in failed rollouts and reinforces redundant or regressive actions in successful rollouts. We propose TRIAGE, a role-typed credit assignment framework that adds a semantic role axis to outcome credit. A structured judge classifies each segment as decisive progress, useful exploration, no-progress infrastructure, or regression, and a fixed role-conditioned rule maps these labels to bounded segment-level process rewards. This keeps verifier outcomes as the source of optimization direction while correcting the two main blind spots of outcome-only credit. We further show that role-conditioned credit is the optimal segment-level correction expressible from role labels alone -- a projection of the per-segment advantage residual onto the role variable -- so that the fixed role constants reduce advantage estimation error whenever the judge is reliable, and we connect this to lower-variance policy gradients. Across ALFWorld, Search-QA, and WebShop, TRIAGE improves success rates over GRPO for two policy models and outperforms both a scalar judge-derived process reward and an outcome-supervised shared-backbone value baseline. Ablations show that the gain comes from role typing rather than merely adding dense rewards: reliable detection of regression inside successful trajectories is the dominant contributor, while exploration credit provides a consistent secondary gain; on completed ALFWorld and WebShop rollouts, TRIAGE also reduces environment-facing turns by an additional $10.4\%$ and $14.8\%$ relative to GRPO.

AI 总结：本文发现确定性少步生成在连续图像潜在变量上成功，但在连续文本潜在变量上崩溃为不连贯文本，原因是几何因素而非训练或缩放缺陷：平滑的确定性映射无法在尖锐分类读出前解决离散分支选择，失败由解码器尖锐度而非传输精度主导。

链接：https://arxiv.org/abs/2606.30705

机构：Fudan University（复旦大学）； Shanghai Innovation Institute（上海创新研究院）

作者：Zhongyao Wang

英文摘要： Deterministic few-step generation succeeds on continuous image latents but collapses to incoherent text on continuous text latents, and we show the cause is geometric rather than a training or scaling deficiency: a smooth, regularity-limited deterministic map cannot resolve a discrete branch choice before a sharp categorical readout, so few-step failure is governed by decoder sharpness, not transport accuracy. In the overlapping regime of real text autoencoders, we prove (Theorem 3) that the posterior-mean terminal step flips tokens at the rate of the latent mass in an $O(s(t))$ tube around decision boundaries. Two diagnostics, DABI (readout sharpness) and CCI (categorical commitment), measured on published checkpoints show that four independently built continuous-text decoders amplify a boundary-aligned perturbation far beyond a norm-matched isotropic one (DABI from $5\times10^{2}$ to $>10^{5}$), while image decoders have DABI $\approx 1$. Two mechanisms escape the continuous bound: categorical commitment (autoregressive decoders succeed despite sharper readouts) and stochastic re-injection (deterministic ODE at $K=4$ gives PPL 294 versus SDE 50 on the same model). In the idealized separated regime we prove matching sharp transport laws, including a dimension phase diagram: the deterministic stiffness needed to separate $M$ modes grows as $\Theta(\sqrt{\log M})$ once the latent dimension is $\Omega(\log M)$ (and as $M^{1/n}$ in fixed dimension), with a depth-$B$ hierarchy giving a $\sqrt{B}$-smaller per-step peak (Theorems 5-7); a coarea identity links these to the overlapping tube (Theorem 17). The result is an accuracy-depth-stiffness tradeoff: within the deterministic-continuous class the cost is irreducible, and both escapes step outside it.

AI 总结：提出质量表示模块（QRM），通过轻量级变压器学习质量感知向量，调整DiT中的自适应层归一化调制，提升生成图像质量，无需改变采样流程。

链接：https://arxiv.org/abs/2606.30934

机构：Carleton University（卡尔顿大学）

作者：Luke Budny, Yuhong Guo, Kevin Cheung

英文摘要：Modern text-to-image diffusion models, such as diffusion transformers (DiT), rely on timestep or prompt embeddings to modulate the strength of the denoising process in each timestep. While this modulation communicates the current noise level, it does not provide any quality-aware information, which can lead to generated images that are unaligned, visually inconsistent, and lacking in fidelity. In this paper, we propose the Quality Representation Module (QRM), a lightweight transformer module that learns a quality-aware representation based on existing model inputs, and produces a set of vectors $M_{qrm}$. These vectors adjust the adaptive LayerNorm modulation within the DiT transformer blocks, thereby injecting a quality-sensitive signal into the denoising parameters. The QRM introduces no significant changes to the sampling schedule or diffusion backbone. Experiments include ablations on QRM training losses and architectures, as well as empirical results demonstrating consistent image quality improvements over baseline DiT-based models.

AI 总结：提出OTCache，一种无需训练的扩散采样加速框架，通过最优传输预测缓存调度，在低NFE区域优于图方法，实现4.5倍以上加速并保持生成质量。

链接：https://arxiv.org/abs/2606.31026

机构：Data Science & Artificial Intelligence Research Institute, China Unicom（中国联通数据科学与人工智能研究院）； Unicom Data Intelligence, China Unicom（中国联通联通数据智能）； National Key Laboratory for Novel Software Technology, Nanjing University（南京大学计算机软件新技术国家重点实验室）

作者：Huanlin Gao, Fang Zhao, Qiang Hui, Fuyuan Shi, Shaoan Zhao, Yantao Li, Chao Tan, Ting Lu, Yuren You, Kai Wang, Shiguo Lian

英文摘要：We propose OTCache, a training-free framework for accelerating diffusion sampling via caching schedule prediction. Existing graph-based caching methods reduce redundant computation by optimizing shortest-path objectives, but rely on an additive independence assumption, which often breaks down in the low NFE regime. To address this issue, OTCache models caching schedules across inference budgets as a smooth evolution in policy space, inspired by Optimal Transport (OT). The framework consists of three stages: (1) obtaining a high-fidelity \textbf{reference schedule} using a graph-based caching method under a conservative budget; (2) performing a lightweight anchor search under an extreme low-budget setting via Optuna optimization with an end-to-end perceptual objective; and (3) predicting schedules for target budgets via quantile interpolation between the reference and anchor policies using continuous warping representations. Experiments on FLUX.1 [dev], Qwen-Image, and HunyuanVideo show that OTCache achieves 4.5x, 4.7x, and 3.66x acceleration, respectively, while consistently improving generation fidelity over state-of-the-art caching baselines. This work provides a new perspective on accelerating diffusion models through Optimal-Transport-inspired schedule modeling. Code: this https URL

AI 总结：提出一种稀疏高斯过程框架，通过拉普拉斯近似进行后验推断，并利用预测不确定性分解驱动诱导点填充和数据获取的序贯算法，以高效实现贝叶斯分位数回归。

链接：https://arxiv.org/abs/2606.31284

机构：Inria（法国国家信息与自动化研究所）； Center for Applied Mathematics, École polytechnique, Institut Polytechnique de Paris（巴黎综合理工学院应用数学中心）； CNRS（法国国家科学研究中心）

作者：Hugo Nicolas (PLATON, CMAP), Olivier Le Maître (PLATON, CMAP)

英文摘要：Quantile regression aims to estimate the conditional quantiles of a response variable from observed data. In a Bayesian setting, Gaussian process quantile regression provides uncertainty quantification but faces significant computational challenges due to the nonconjugacy of the asymmetric Laplace likelihood and the cost of posterior inference. We develop a sparse Gaussian process framework in which the quantile function is represented through a reduced set of inducing variables and posterior inference is performed using a Laplace approximation. A decomposition of the predictive uncertainty into conditional-prior and posterior-induced variance components is then exploited to drive two complementary adaptive mechanisms: inducing-input infilling and data acquisition. These mechanisms are combined within a sequential algorithm that allocates computational effort toward the dominant source of predictive uncertainty and adaptively controls model complexity. Numerical experiments on benchmark problems demonstrate the accuracy of the Laplace approximation, the benefits of variance-based inducing-input placement, and the effectiveness of the proposed sequential enrichment strategy compared with predefined data-acquisition strategies.

AI 总结：将生成式AI中的流匹配方法应用于地球物理概率反演，通过两个案例验证其在简单和复杂速度模型中的有效性。

链接：https://arxiv.org/abs/2606.31288

机构：Institute of Geophysics and Geoinformatics, TU Bergakademie Freiberg（弗莱贝格工业大学地球物理与地理信息研究所）

作者：Baldur Paulwitz, Stefan Buske

英文摘要：We demonstrate the application of Flow Matching, a technique originating from generative Artificial Intelligence, to probabilistic inversion in geophysical settings, such as seismic Full-Waveform inversion. We adapt the well-established mathematical theory of Flow Matching from generative Artificial Intelligence to the context of probabilistic inversion. We evaluate the approach with two case studies: a simple 2D velocity model to illustrate the general features of the method, and the OpenFWI dataset to show its capabilities for probabilistic inversion of more complex seismic velocity models.

AI 总结：提出Patch-PODiff-ViT框架，使用分块本征正交分解（POD）定义固定线性正交基的潜在空间，结合Vision Transformer实现高效扩散，并通过线性解码器解析传播不确定性，在多个领域实现参数少、内存低且校准良好的超分辨率重建。

链接：https://arxiv.org/abs/2606.31290

作者：Onkar Jadhav, Tim French, Matthew Rayson, Nicole L. Jones

英文摘要：Diffusion models enable probabilistic super-resolution and conditional generation, but pixel-space methods are computationally expensive and learned latent spaces often lack interpretable uncertainty quantification. We introduce Patch-PODiff-ViT, a structured latent diffusion framework in which the latent space is defined by patchwise Proper Orthogonal Decomposition (POD), a fixed linear orthonormal basis over local patches, rather than learned by a nonlinear autoencoder. This yields low-dimensional, variance-ordered tokens that preserve spatial structure and enable efficient diffusion in a structured low-dimensional latent space with a Vision Transformer. Because the decoder is fixed, linear, and orthonormal, latent coefficient uncertainty can be propagated directly to physical-space predictive variance, enabling analytic propagation of predictive variance through the linear decoder without Monte Carlo estimation in pixel space. Across sea surface temperature, medical imaging, and natural images, the method achieves strong reconstruction with fewer parameters and lower memory, while producing well-calibrated spatial uncertainty that closely matches empirical ensembles.

AI 总结：本文从变分视角出发，介绍常微分和随机微分方程在生成式机器学习中的应用，推导ELBO，并统一讨论扩散模型、分数匹配和流匹配。

链接：https://arxiv.org/abs/2606.31576

机构：Department of Biology, University of Copenhagen（哥本哈根大学生物系）； Department of Applied Mathematics and Computer Science, Technical University of Denmark（丹麦技术大学应用数学与计算机科学系）； Google DeepMind（谷歌深度思维）； Technical University of Berlin (TU Berlin)（柏林工业大学）； Technical University of Munich（慕尼黑工业大学）

作者：Ole Winther, Paul Jeha, Sander Dieleman, Andriy Mnih, Manfred Opper, Andrea Dittadi

英文摘要：The use of ordinary and stochastic differential equations has led to substantial progress in generative machine learning with applications to, for example, image, video and biomolecule generation. This paper provides a self-contained and informal introduction to the differential equations, the probabilistic framework for using them in generative modeling and the Fokker--Planck equation that governs the temporal evolution of the marginal distribution of the stochastic variables of the differential equations. The variational lower bound on the log-likelihood (the evidence lower bound, ELBO) is derived and used as a general starting point for a discussion of diffusion models, score matching, and flow matching. All of these approaches may be viewed as specific parameterizations of the most general variational approach. A one-dimensional density modeling problem is used as a simple example to compare different parameterizations.

AI 总结：提出Seq. RC-TGAN框架，结合谱包络损失函数和变分高斯混合模型，有效生成含周期性和季节性的分类与连续时间序列，并引入两种新评估指标。

链接：https://arxiv.org/abs/2606.31904

机构：Mitacs

作者：Mohamed Gueye, Yazid Attabi, Manuel Morales, Maxime Dumas

英文摘要：The generation of synthetic relational databases often involves modeling complex temporal dynamics, such as transaction logs or event sequences. A significant challenge in this domain is the handling of categorical time series (e.g., status codes), where standard encoding methods like one-hot encoding fail to capture intrinsic frequency-domain features such as seasonality and cyclicity. In this paper, we introduce Sequential RC-TGAN (Seq. RC-TGAN), a temporal extension of the RC-TGAN framework, equipped with a novel integrated loss function based on the \textit{Spectral Envelope Theory}. This differentiable loss allows the generator to directly optimize the preservation of latent periodic structures via backpropagation. While spectral envelope theory is inherently designed for categorical sequences, we extend this frequency-domain regularization to continuous time series by employing a Variational Gaussian Mixture Model (VGM) discretization strategy. To establish a mathematically rigorous evaluation standard, we simulate categorical time series governed by a parameter $\alpha$, with exactly known theoretical spectral envelopes. Integrating these dynamic sequences into the child tables of a relational database yields a robust ground-truth benchmark for evaluating the frequency-domain fidelity of our generative framework. Furthermore, we address the lack of robust evaluation standards for relational time series by proposing two new metrics: Spectral Density Divergence and Spectral Envelope Divergence. Experimental results on real-world datasets, as well as our simulated benchmarks, demonstrate that our end-to-end approach significantly outperforms state-of-the-art systems in reproducing cyclic patterns and long-term seasonality across both categorical and continuous features.

AI 总结：提出GRPO训练动力学的第一性原理降阶模型，揭示其指数饱和律的物理含义，预测群大小不变性、稳定性阈值和过阻尼-振荡转变，并在多个模型和基准上验证。

链接：https://arxiv.org/abs/2606.30789

机构：Nutanix； Unsloth

作者：Rajat Ghosh, Datta Nimmaturi, Aryan Singhal, Vaishnavi Bhargava, Henry Wong, Johnu George, Debojyoti Dutta

英文摘要： Group Relative Policy Optimization (GRPO) has become a standard tool for improving the reasoning ability of large language models, yet its training dynamics are still described empirically: reward trajectories are fit with low-parameter functional forms whose constants carry no mechanistic meaning, and hyperparameter choices remain a matter of trial and error. We develop a first-principles reduced-order model of these dynamics. The reduction has three consequences. First, it subsumes the empirical single-exponential saturation law as its overdamped limit, recasting the fitted plateau, timescale, and size exponent as the fixed point, inverse stiffness, and curvature-scaling exponent of the underlying potential, and adding, through the retained inertial term, the slow-start phase the single exponential cannot represent. Second, it yields predictions tied to independently measurable quantities rather than fitted ones: group-size invariance of the deterministic trajectory with a $1/G$ stationary fluctuation, a sharp stability threshold in the refresh interval, and an overdamped-to-oscillatory transition. Third, it furnishes diagnostics that separate failure modes a reward curve alone conflates -- reward hacking, advantage degeneracy, policy concentration, and dynamical instability. Across three models and two group sizes, the closed-form trajectory fits training reward to $R^2 \geq 0.91$ and the predicted group-size invariance holds on both the reward curve and out-of-distribution transfer to eight math benchmarks. The stability and oscillatory predictions are exercised in a controlled exact-reduction setting where the mean-field assumption holds exactly: a softmax-bandit reduction reproduces the predicted overdamped-to-oscillatory transition and locates the refresh-interval stability threshold at the independently measured stiffness, with a deep-network demonstration left to future work.

AI 总结：提出深度梯度增强框架，通过窗口平滑算子沿深度方向变换优化器更新，在不改变模型架构或训练目标下提升多种架构和任务的优化与泛化性能。

链接：https://arxiv.org/abs/2606.30813

作者：Haoming Meng, Anton Sugolov, Vardan Papyan

英文摘要：Deep neural networks with repeated architectural blocks, such as transformers, often exhibit structured relationships across layers that emerge during training. Motivated by this observation, we introduce \emph{Depth-wise Gradient Augmentation}, a general optimization paradigm in which the update applied to each layer is obtained by transforming the collection of block-wise optimizer updates along the depth dimension. Within this framework, we study \emph{Gradient Smoothing}, a family of depth-wise smoothing methods, and instantiate it with a simple local \emph{Window Smoothing} operator. The resulting method operates directly on block-wise updates produced by arbitrary base optimizers (e.g., SGD, Adam, Muon), incurs minimal computational overhead, and is compatible with existing optimization pipelines. We evaluate Gradient Smoothing across a diverse set of architectures and training regimes, including language model pretraining, RL post-training of LLMs for reasoning, diffusion modeling, and image classification with Vision Transformers. Across these settings, Gradient Smoothing consistently improves optimization and generalization performance without modifying model architectures or training objectives. We further show that it promotes more structured representation evolution across depth, consistent with its interpretation as a structured depth-wise preconditioning method. Together, these results establish Depth-wise Gradient Augmentation as a promising framework for exploiting cross-depth structure in optimization and demonstrate Gradient Smoothing as a simple and broadly applicable instantiation.

AI 总结：提出分区引导的距离显著性（PGDS）框架，通过代理模型学习决策空间几何距离到目标空间近邻的映射，自动分区并识别局部支配点，量化决策变量对解位置的敏感性，将特征分类为驱动者或阻碍者，以增强多目标优化的可解释性。

链接：https://arxiv.org/abs/2606.30836

机构：A3Data； CEFET-MG - Centro Federal de Educação Tecnológica de Minas Gerais（米纳斯吉拉斯联邦技术教育中心）； Aston University（阿斯顿大学）

作者：Cláudio Lúcio do Val Lopes, Flávio Vinícius Cruzeiro Martins, Elizabeth Fialho Wanner

英文摘要：Explainability in Many-Objective Optimization (MaO) is currently hindered by the escalating complexity of the Pareto front, which renders the relationship between high-dimensional decision variables and objective outcomes increasingly opaque. As the number of objectives exceeds the limits of traditional visualization, decision-makers encounter a ``cognitive drought'' in identifying relevant trade-offs or specifying target regions without a priori knowledge. To bridge this interpretability gap, we introduce the {Partition-Guided Distance Saliency (PGDS)} framework, a novel XAI approach designed for continuous optimization landscapes. Our framework automates the explanation process through a three-stage pipeline that prioritizes geometric intuition over abstract rules. First, we employ a surrogate model that learns how geometric distances in the decision space map to proximity in the objective space. Second, to address the difficulty of manual target selection in high dimensions, the framework automatically partitions the objective landscape into distinct regions and identifies local ``Dominating Points'' to serve as automated targets for improvement. Third, we quantify how sensitive a solution's position is to each decision variable by measuring the distance shifts induced by perturbations to each variable. This allows PGDS to categorize features as either ``Drivers'' which facilitate convergence toward preferred regions, or ``Blockers'' which represent geometric constraints hindering further progress. Validation on 10-objective benchmarks and a physics-informed engineering problem (Welded Beam) demonstrates that PGDS provides differentiated, actionable insights that traditional visualization and rule-based XAI methods fail to provide.

AI 总结：将随机森林中基于三元组的高原搜索建模为生灭马尔可夫链，推导其平稳分布，并给出中心集成大小和波动的渐近阶。

链接：https://arxiv.org/abs/2606.30837

机构：Sberbank（俄罗斯联邦储蓄银行）； Skolkovo Institute of Science and Technology (Skoltech)（斯科尔科沃科学技术学院）； Federal Research Center “Computer Science and Control” of Russian Academy of Sciences (FRC CSC RAS)（俄罗斯科学院联邦研究中心“计算机科学与控制”）

作者：Andrey A. Dukhovny, Andrey M. Lange

英文摘要： The number of trees is a central computational parameter in Random Forests: increasing it reduces finite-ensemble variability but increases training and prediction cost. Plateau-based tuning adapts this parameter through local comparisons of out-of-bag scores at a geometric triplet of tree counts. After the remaining hyperparameters have stabilized, however, the central triplet point need not converge to a deterministic value; instead, it fluctuates around a stationary regime. This paper develops a stationary-distribution theory for this process. The central ensemble size $B_t$ is modeled as a birth-death Markov chain on a geometric grid, and its stationary distribution is derived through local balance. Under a leading centered folded-normal approximation, equilibrium equations are obtained for the original update rule and a symmetric modified variant, implying that the stationary center $B_*=O(\varepsilon^{-2})$ as $\varepsilon\downarrow 0$. The stationary spread is also characterized. A local Gaussian approximation and a Fokker-Planck interpretation give grid-level variance constants. After conversion to the ensemble-size scale, $\sigma_{B,*}=O(\varepsilon^{-2})$, while the variance is $O(\varepsilon^{-4})$. The leading relative spread is independent of $\varepsilon$ and controlled by the scale factor and update rule. These results interpret plateau-based Random Forest tuning as a stochastic process rather than a deterministic stopping rule.

AI 总结：利用统计力学工具研究神经网络和机器学习，重点分析对抗攻击和隐式低维学习，通过密集联想记忆和受限玻尔兹曼机两类模型探讨学习与记忆化的平衡。

链接：https://arxiv.org/abs/2606.31110

作者：Robin Theriault

英文摘要：Artificial neural networks (NNs) and machine learning (ML) algorithms are poorly understood from a theoretical perspective, which makes it difficult to fully realize their potential and overcome their weaknesses. For instance, ML algorithms train NN weights by moving them along a low-dimensional subspace of their allowed values, but this implicitly low-dimensional learning structure is not properly exploited to improve training because its nature is not well understood. Moreover, trained NNs are easily confused by pervasive adversarial attacks whose theoretical underpinnings are still unclear. This thesis aims to improve our theoretical understanding of NNs and ML, with a particular focus on adversarial attacks and implicitly low-dimensional learning. For this purpose, we use mathematical tools from statistical mechanics to study different types of NNs and ways in which they can fit the data. In particular, we study two classes of models that fit the data with various degrees of learning and memorization: dense associative memory (DAM) and restricted Boltzmann machines (RBM). In the process, we investigate connections between different versions of these models that are useful to make analytical investigations more efficient.

AI 总结：针对单条格劳伯动力学轨迹，提出一种多项式时间算法，通过条件方差估计、局部边测试和鲁棒中值聚合，在轨迹长度不依赖混合时间的前提下恢复条件独立图。

链接：https://arxiv.org/abs/2606.31230

机构：MIT（麻省理工学院）

作者：Eric Shen, Tony Wu, Mahbod Majid, Ankur Moitra

英文摘要：We study the task of learning the structure of a $d$-sparse Gaussian graphical model on $n$ variables from a single trajectory of Glauber dynamics. Beyond algorithmic considerations, many applications present temporally correlated observations rather than i.i.d.\ samples. In the classical i.i.d.\ setting, under comparably general sparsity and minimum edge-strength assumptions, sublinear-in-$n$ sample guarantees are known, but achieving them in polynomial-time remains open. Motivated in part by this gap, we give a polynomial-time algorithm that recovers the conditional-independence graph from a single Glauber trajectory, with a trajectory-length guarantee that does not depend on the mixing time. Technically, our algorithm has three components. First, we estimate the conditional variances and rescale the trajectory to reduce to the unit-diagonal case, without changing the underlying graph. Second, we design a local edge test that extracts adjacency information from short update windows by isolating pairwise influence. Third, we aggregate these local statistics using a robust median-based estimator, and prove accuracy despite temporal dependence arising from a single trajectory.

AI 总结：通过复制交换Wang-Landau算法估计二元网络中的联合态密度，研究梯度学习与随机采样在泛化性能上的差异如何随训练数据量变化，发现数据量增大时梯度学习的优势减弱，从而解释了关于体积假说的矛盾实验结果。

链接：https://arxiv.org/abs/2606.31282

作者：Ari Pakman, Lior Kreimer, Yakir Berchenko

英文摘要：Modern deep neural networks often contain far more parameters than needed to fit their training data, yet they achieve impressive generalization. A common explanation for this success is the implicit bias of stochastic gradient descent (SGD). An alternative volume hypothesis posits that, within low training-loss regions, loss-landscape basins leading to strong generalization occupy much larger regions of weight space than basins that generalize poorly, and therefore SGD is simply more likely to land in the former. Recent experimental explorations of this idea present seemingly contradictory results. While in one set of experiments randomly sampling the network weights until achieving zero training error yielded poor generalization, molecular dynamics density estimates supported the volume hypothesis. We observe that these experiments were performed at different dataset size regimes, and explore an intermediate regime using the Replica Exchange Wang-Landau algorithm to estimate the joint density of states over training and test accuracies in binary networks. Across several architectures and datasets, we show that the generalization advantage of gradient learning over random sampling training generally diminishes as the training data size grows, suggesting a resolution of the paradox.

AI 总结：提出一种自适应正则化的原始-对偶框架，无需Slater条件即可实现随机约束下$O(\sqrt{T})$遗憾和$O(\sqrt{T}\log T)$约束违反，并扩展到对抗约束。

链接：https://arxiv.org/abs/2606.31480

机构：KAIST（韩国科学技术院）； Seoul National University（首尔国立大学）

作者：Kihyun Yu, Junehee Lee, Dabeen Lee

英文摘要： We study constrained online convex optimization with adversarial losses and stochastic or adversarial constraints. For stochastic constraints, existing algorithms that achieve nearly optimal regret and constraint violation bounds typically rely on regularity assumptions such as Slater's condition, while adversarial-constraint algorithms avoid these assumptions by using a rather restrictive round-wise feasible comparator. We bridge this gap with an anytime primal-dual framework that incorporates an adaptive regularizer into the dual update. The regularizer stabilizes the dual process without relying on the negative drift induced by Slater's condition. For stochastic constraints and convex losses, our algorithm achieves $O(\sqrt{T})$ expected regret and $O(\sqrt{T}\log T)$ expected cumulative constraint violation. Furthermore, we show that our algorithm also admits high-probability bounds of the same order on regret and constraint violation. For strongly convex losses, the regret bound improves to $O(\log T)$ with a violation bound of the same order. With a minor modification, the framework also applies to adversarial constraints and provides guarantees for hard constraint violation.

AI 总结：针对SAIL算法收敛性分析缺失的问题，提出SAIL-RevKL正则化目标，证明其满足PL条件并实现近线性样本复杂度，在MuJoCo和LLM对齐任务上优于原始SAIL。

链接：https://arxiv.org/abs/2606.31524

机构：The University of Hong Kong（香港大学）； Yale University（耶鲁大学）； Purdue University（普渡大学）

作者：Xudong Wu, Pangpang Liu, Vaneet Aggarwal, Jiayu Chen

英文摘要：The Self-Improving Alignment (SAIL) algorithm addresses distribution shift by reducing a bilevel formulation of the problem to an efficient, single-level method. Empirically, SAIL has demonstrated strong performance on this task. However, a formal analysis of its convergence properties has been lacking. We identify a key theoretical challenge: the standard SAIL objective function is not guaranteed to be strongly concave due to unfavorable properties of its Hessian. To address this limitation, we propose a regularized objective, SAIL-RevKL, which incorporates a reverse Kullback-Leibler (KL) divergence penalty to improve the optimization landscape. Our central theoretical contribution is to prove that this regularized objective satisfies the Polyak-Lojasiewicz (PL) condition within a bounded parameter space. We establish global convergence guarantees, achieving a near-linear sample complexity. We further validate the effectiveness and stability of SAIL-RevKL through empirical evaluations, demonstrating that it outperforms the vanilla SAIL on both MuJoCo benchmarks and LLM alignment tasks.

AI 总结：通过几何分析揭示交叉熵优化下隐藏表示的径向膨胀导致记忆-泛化延迟，提出径向惩罚加速泛化，在模算术和加法任务上实现最高6倍加速。

链接：https://arxiv.org/abs/2606.32000

机构：Indian Institute of Technology Roorkee（印度理工学院罗尔基分校）

作者：Srijan Tiwari, Aditya Chauhan, Manjot Singh

英文摘要：Why do neural networks memorize algorithmic training data long before they generalize? We present a geometric case study demonstrating that, on tasks where generalization requires discovering structured low-dimensional circuits, the memorization-generalization delay is driven by radial inflation of hidden representations under cross-entropy optimization. We formalize a radial-angular decomposition of activation-space dynamics and derive three testable propositions: (i) that penalizing radial inflation induces anisotropic, data-dependent weight regularization; (ii) that it suppresses radial gradient energy below the isotropic random baseline, forcing predominantly angular updates; and (iii) that it biases convergence toward flatter minima. To empirically validate these propositions, we study a single-hyperparameter norm penalty that softly constrains activations to a sqrt(d)-radius hypersphere. On modular arithmetic, this penalty accelerates grokking up to 6x across MLPs and Transformers, and halves training steps for a 10M-parameter nanoGPT on 3-digit addition.

AI 总结：本文研究从大型推理模型DeepSeek-R1向紧凑学生模型Qwen2.5-7B的知识蒸馏，通过构建思维链训练语料库微调，使学生在竞赛数据集上准确率提升4.76个百分点，并发现响应长度对数学推理质量至关重要。

链接：https://arxiv.org/abs/2606.31048

机构：Northern Kentucky University（北肯塔基大学）

作者：Gaurab Baral, Aaditya Khanal, Yangyang Tao, Junxiu Zhou

英文摘要：This paper investigates knowledge distillation from a large reasoning model (DeepSeek-R1) to a compact student model (Qwen2.5-7B). Using historical problems from the John O'Bryan Mathematics Competition at Northern Kentucky University (2011-2025), we build a Chain-of-Thought (CoT) training corpus through a dual-agent framework. The dataset is used to fine-tune the student model with Low-Rank Adaptation (LoRA) on Apple Silicon hardware using the MLX framework. The base Qwen2.5-7B model achieves 64.67% accuracy on competition problems, while the DeepSeek-R1 teacher achieves 91.40%. An initial 1,000-iteration training run revealed severe overfitting, with validation loss reaching a minimum at iteration 200 before rising steadily. Based on this finding, we ran five independent training runs each limited to 200 iterations with varied random seeds to assess result stability. Across these five runs, the fine-tuned student model achieves a mean accuracy of 69.43% (std dev 0.17%) on the competition dataset, a 4.76 percentage-point improvement over the base model, and generalizes to 73.1% (std dev 0.18%) on the MATH-500 benchmark. We further study how response length affects answer quality across six reasoning levels (R1-R6): accuracy declines consistently from 69.43% at R1 (mean 220 words) to 41.9% at R6 (mean 31.2 words), with the two-person speed section most sensitive to token reduction. These results demonstrate that CoT distillation improves compact student models and that response length is a critical factor in mathematical reasoning quality.

AI 总结：提出GoodQ框架，利用现成生成模型构建训练集，通过信息密集提示、内在分布感知选择和教师引导自适应降噪，解决零样本量化目标检测中的多实例、类别不平衡和伪标签噪声问题，在低比特（W4A4）达到最优性能。

链接：https://arxiv.org/abs/2606.31456

机构：Seoul National University（首尔大学）； LG Electronics（LG电子）

作者：Hyunho Lee, Kyomin Hwang, Hyeonjin Kim, Suyoung Kim, Sunghyun Wee, Nojun Kwak

英文摘要：With an increasing number of Object Detection (OD) models being deployed on edge devices, Zero-Shot Quantization for OD (ZSQ-OD) aims to quantize these models when access to the original training data is prohibited. Existing research on Zero-Shot Quantization-Aware Training (QAT) for OD synthesizes training sets through noise optimization. However, this approach struggles to maintain performance in low-bit regions. In this paper, we introduce GoodQ (Generative off-the-shelf models for object detector Quantization), a QAT pipeline that utilizes off-the-shelf generative models to construct a training set. We first identify three challenges that arise when introducing a generative model to the ZSQ-OD task: 1) each image contains dense information with multiple instances, 2) the class-wise distribution in the original dataset is imbalanced, and 3) the pseudo-labels assigned to the generated images can potentially act as noisy signals during QAT. GoodQ addresses these challenges by 1) introducing an Information-Dense Prompting strategy to generate multi-instance images, 2) applying Intrinsic Distribution-Aware Selection to match the pretrained class distribution, and 3) employing Teacher-guided Adaptive Noise Reduction to mitigate noise arising from the QAT process. Our framework achieves state-of-the-art performance in low-bit ZSQ (W4A4) and extends quantization to extreme bit-widths (W3A3). Furthermore, we conduct an extensive analysis to uncover the underlying factors contributing to the efficacy of GoodQ.

AI 总结：针对长上下文大语言模型推理中KV缓存导致的瓶颈，提出RaBitQCache框架，利用随机旋转二值量化和高效二进制-INT4算术无偏估计注意力权重，实现自适应Top-p检索，加速推理并减少内存I/O。

链接：https://arxiv.org/abs/2606.31519

作者：Wenhao Li, Jinhao Dong, Hailin Zhang, Wenhang Shi, Wei Lu, Xiaoyong Du

英文摘要：Long-context Large Language Model inference is severely bottlenecked by the massive Key-Value (KV) cache, yet existing sparse attention methods often suffer from static fixed-budget (Top-k) retrieval or rely on proxy scores that are computationally expensive and biased. To address these limitations, we propose RaBitQCache, a novel sparse attention framework that utilizes randomized rotated binary quantization and high-throughput binary-INT4 arithmetic to efficiently estimate attention weights. Our proxy score serves as an unbiased estimator with a proven error bound, enabling adaptive Top-p retrieval that dynamically adjusts the token budget based on actual attention sparsity. We further implement a hardware-aware system with asynchronous pipelining and lazy updates to mask overhead. Evaluations demonstrate that RaBitQCache significantly accelerates inference and reduces memory I/O while preserving generation quality compared to state-of-the-art baselines. Code is available at this https URL.

AI 总结：针对门控FFN中低秩更新导致的选择偏差问题，提出NA-LoRA，通过导数时序重要性掩码和激活特定步长缩放规则，提升参数高效微调性能。

链接：https://arxiv.org/abs/2606.31717

机构：Beijing Institute of Technology, Zhuhai（北京理工大学珠海学院）； The Hong Kong Polytechnic University（香港理工大学）； The University of Osaka（大阪大学）； Shenzhen University（深圳大学）

作者：Shuai Yuan, Sudong Cai, Bingzhi Chen, Shuyuan Zheng, Chuan Xiao, Makoto Onizuka, Rui Mao

英文摘要：Low-rank adaptation (LoRA) is commonly viewed as an update-space approximation to full fine-tuning, yet this view is incomplete for self-gated Transformer feed-forward networks. In gated FFNs, a low-rank residual can change not only projected features but also the nonlinear selection weights that determine which channels contribute to the output. We formalize this effect as selection misalignment and connect it to the local effective homogeneity of self-gated activations. This motivates a nonlinearity-aware principle for parameter-efficient fine-tuning: low-rank updates should allocate capacity to gate channels whose nonlinear states remain responsive and should shape the temporal evolution of selection. We propose NA-LoRA, a training-only method with two lightweight mechanisms: a derivative-based temporal-importance mask for gate-related LoRA updates and an activation-specific step-scaling rule when a meaningful coarse effective-homogeneity partition is available. NA-LoRA adds no auxiliary loss and incurs no inference-time overhead. Experiments on language-model fine-tuning and vision-language transfer benchmarks show that NA-LoRA consistently improves over vanilla LoRA and is competitive with or better than strong PEFT variants.

AI 总结：针对RLVR中LoRA初始化问题，提出保持几何的正交初始化方法（RLPO和RLMO），理论证明其最小化与全微调差距，实验表明稳定训练且优于标准LoRA。

链接：https://arxiv.org/abs/2606.31813

机构：Johns Hopkins University（约翰霍普金斯大学）； Meta Superintelligence Labs（Meta超级智能实验室）； The University of Texas at Austin（德克萨斯大学奥斯汀分校）

作者：Ruijia Zhang, Jiacheng Zhu, Hanqing Zhu, Laixi Shi

英文摘要：Low-rank adaptation (LoRA) and its variants enable parameter-efficient fine-tuning of large language models under the supervised fine-tuning (SFT) paradigm. However, their efficacy and behavior under Reinforcement learning with verifiable rewards (RLVR) are less well understood. In particular, two structurally initialized LoRA variants, PiSSA and MiLoRA, which outperform standard LoRA under SFT, can underperform standard LoRA under RLVR and may even exhibit training instability. These observations suggest that how to initialize the low-rank matrices in RLVR remains unclear. In this work, we develop a theoretical analysis of LoRA in RLVR, showing that orthonormal initialization achieves the minimal gap between LoRA outcome and that of full fine-tuning. Guided by this insight, we propose geometry-preserving orthonormal initialization for low-rank adaptation in RLVR, leading to two new variants, RLPO and RLMO. Experiments on mathematical reasoning benchmarks show that the proposed orthonormal initialization stabilizes RLVR training and outperforms standard LoRA, contrasting with PiSSA and MiLoRA. Finally, our unified analysis for LoRA initialization also explains why PiSSA and MiLoRA can underperform in RLVR, which may be of independent interest. Code and checkpoints are publicly available at this https URL.

AI 总结：提出分类器门控路由架构，在推理前评估查询复杂度和数据敏感性，将含PII的查询路由到本地端点，简单查询路由到小型模型，实现合规与成本效率。

链接：https://arxiv.org/abs/2606.31163

作者：Abhishek Dey

英文摘要：Large language models deployed in regulated industries operate under two constraints: compliance enforcement and cost efficiency. Personally identifiable information (PII) in user queries can reach model endpoints before the system determines whether that data should leave its jurisdictional boundary. Serving all queries through a single large model consumes full GPU capacity regardless of query complexity while offering no mechanism for geographic routing. Mixture-of-Experts architectures do not address this routing occurs between expert layers within the model after data has already arrived at the endpoint, with all experts loaded in memory regardless of query complexity. We propose a classifier-gated routing architecture that enforces compliance by design. A trained encoder classifier sits before any decoder inference, evaluating each query for complexity and data sensitivity, then routing it to an appropriately sized dense model in the appropriate geographic location. PII-containing queries route to local endpoints before any LLM computation begins, making data residency violations structurally impossible. Simple queries reach small, fast models at a fraction of the cost. Our evaluation on 600 queries demonstrates 39% median latency reduction, 33-52% cost savings depending on query distribution, and generation throughput of 122-200 tokens/second versus 50-64 for the baseline. The encoder classifier achieves 99.2% accuracy with near-perfect PII recall at 7ms inference overhead, establishing pre-inference classification as a practical path to compliance-by-design LLM deployment.

AI 总结：提出一种基于预期增益评分的两轮VFL推理协议，仅在预期能提升决策时调用高成本融合轮次，无需单独训练路由网络，在通信-准确率权衡上优于基线方法。

链接：https://arxiv.org/abs/2606.31331

作者：Mohamad Mestoukirdi, Vincent Corlay

英文摘要：Collaborative inference can improve predictive performance by integrating complementary information across agents, but applying collaborative fusion to every sample can incur unnecessary communication and computational overhead. This trade-off is particularly relevant in vertical federated learning (VFL), where clients observe different views of the same sample and fusion typically requires transmitting intermediate representations to a server. We study selective escalation in a two-round VFL inference protocol, in which a low-cost first round produces a prediction from client posteriors and a second embedding-fusion round is invoked only when it is expected to improve the final decision. We formulate routing as expected-gain score estimation: a sample is escalated when a predicted improvement in correctness justifies the additional communication. The proposed analytical score combines a calibrated pooled posterior with classwise reliability estimates of the VFL model, both obtained from held-out calibration data, yielding an interpretable router that requires no separately trained routing network. Experiments on multi-view classification benchmarks, including controlled test--time view degradation settings, show that the proposed router improves the communication-accuracy trade-off over confidence-, learned-gain-, and deferral-based baselines.

AI 总结：提出TabPATE，一种无需公开数据的差分隐私PATE风格防御方法，通过教师模型分区和私有聚合生成学生上下文，在表格基准上保持可用性并将成员推断降至随机水平。

链接：https://arxiv.org/abs/2606.31474

作者：Dariush Wahdany, Matthew Jagielski, Jesse C. Cresswell, Adam Dziedzic, Franziska Boenisch

英文摘要：Tabular foundation models enable accurate in-context learning (ICL) from small labeled datasets, but the private records placed in context can leak through model predictions. We first show that even basic membership inference attacks succeed against tabular ICL, motivating formal privacy protection. We then introduce TabPATE, a differentially private PATE-style defense for tabular ICL that does not require public in-distribution data. TabPATE partitions the private context across teacher models, privately aggregates their labels on synthetic tabular queries, and releases the resulting labeled queries as a student context. Because tabular features are bounded and relatively low-dimensional, useful queries can be generated from feature ranges alone or from lightly privatized marginals. Across tabular benchmarks, TabPATE preserves competitive utility while reducing membership inference to near-random success, providing a practical path to private tabular ICL without public data.

AI 总结：提出FedXDS方法，首次利用XAI的特征归因技术识别需共享的数据元素，通过选择性数据共享和度量隐私保护，在异质性联邦学习中提升精度和收敛速度。

链接：https://arxiv.org/abs/2606.31742

机构：Fraunhofer Heinrich Hertz Institute（弗劳恩霍夫海因里希·赫兹研究所）； Technical University of Berlin（柏林工业大学）； Berlin Institute for the Foundations of Learning and Data (BIFOLD)（柏林学习与数据基础研究所）

作者：Maximilian Andreas Hoefler, Karsten Mueller, Wojciech Samek

英文摘要： Explainable AI (XAI) methods have demonstrated significant success in recent years at identifying relevant features in input data that drive deep learning model decisions, enhancing interpretability for users. However, the potential of XAI beyond providing model transparency has remained largely unexplored in adjacent machine learning domains. In this paper, we show for the first time how XAI can be utilized in the context of federated learning. Specifically, while federated learning enables collaborative model training without raw data sharing, it suffers from performance degradation when client data distributions exhibit statistical heterogeneity. We introduce FedXDS (Federated Learning via XAI-guided Data Sharing), the first approach to utilize feature attribution techniques to identify precisely which data elements should be selectively shared between clients to mitigate heterogeneity. By employing propagation-based attribution, our method identifies task-relevant features through a single backward pass, enabling selective data sharing that aligns client contributions. To protect sensitive information, we incorporate metric privacy techniques that provide formal privacy guarantees while preserving utility. Experimental results demonstrate that our approach consistently achieves higher accuracy and faster convergence compared to existing methods across varying client numbers and heterogeneity settings. We provide theoretical privacy guarantees and empirically demonstrate robustness against both membership inference and feature inversion attacks. Code is available at this https URL.

AI 总结：提出FedLAB框架，通过类型化分层码本组织模态证据、节点语义和拓扑上下文，实现联邦多模态图学习中的可追踪语义，在10个基准和6个下游任务上提升达7.53%。

链接：https://arxiv.org/abs/2606.32016

机构：Beijing Institute of Technology（北京理工大学）

作者：Zekai Chen, Kairui Yang, Xuaner Chen, Xunkai Li, Xun Wu, Rong-Hua Li, Guoren Wang

英文摘要：Multimodal graph foundation models aim to learn reusable knowledge from graphs enriched with text, images, attributes, and relational topology, thereby supporting diverse graph-centric and modality-centric tasks. In practice, however, such multimodal graphs are often distributed across decentralized clients, where raw contents and local structures cannot be centrally shared due to privacy constraints. This motivates federated multimodal graph foundation learning, which requires not only transferable representation learning but also intrinsic semantic traceability under strict data isolation. Existing methods usually exchange or store knowledge through parameters, prototypes, embeddings, or compact codebooks, which support optimization and transfer but do not explicitly expose how modality evidence, node semantics, and topology context jointly support predictions. To bridge this gap, we propose FedLAB, a traceable semantic codebook framework that organizes multimodal graph knowledge into typed hierarchical codebooks for modality evidence, node semantics, and topology context. FedLAB further refines these trace units through federated semantic barycenter pre-training while keeping raw multimodal contents and graph structures local. Extensive experiments on 10 benchmarks and 6 downstream tasks show that FedLAB improves over state-of-the-art baselines by up to 7.53\%, while preserving a native semantic trace interface.

AI 总结：研究通过概率校准评估器的成对判断来缓解LLM智能体反馈回路中的偏好耦合，实验表明校准将耦合系数降低20-49%，JS散度降低45-67%。

链接：https://arxiv.org/abs/2606.31371

机构：Qilu Institute of Technology, School of Software Engineering（齐鲁理工学院软件工程学院）

作者：Zewen Liu

英文摘要：When large language model (LLM) agents adapt their behavior through evaluator feedback, systematic evaluator biases propagate into the agent's learned strategy distribution - a phenomenon termed evaluator preference coupling. Prior work has documented this coupling and established a diagnostic framework (EPC) to measure it, but has not investigated whether calibration techniques can mitigate the effect. We present the first study of evaluator calibration as mitigation: applying probability calibration to the evaluator's pairwise judgments to reduce spurious preference propagation. In a controlled within-subjects experiment (N=5) comparing standard binary TTRL (win/loss) with confidence-calibrated TTRL (probability-weighted updates) using DeepSeek-V4-Pro as executor and GLM5.2 as evaluator, we find that calibration reduces the coupling coefficient gamma by 20-49% and Jensen-Shannon divergence by 45-67%. A symmetric-LR control confirms the effect is not due to reduced update asymmetry. We release the calibrated TTRL protocol and recommend it as a lightweight mitigation for LLM-as-judge deployment pipelines.

AI 总结：研究训练后神经网络对输入扰动的鲁棒性，提出一种高效的黑盒鲁棒性度量方法，并引入鲁棒性曲线进行深入分析。

链接：https://arxiv.org/abs/2606.31581

作者：Mark Levene, Martyn Harris

英文摘要：We investigate the problem of the robustness of a trained neural network to the perturbation of its input values. More specifically, we examine the interplay between the accuracy of the network, as measured by the mean squared error, and robustness. Accordingly, we present a robustness measure, which, with high probability, suggests an upper bound on the mean squared error of the network, with respect to an input data set, for a given perturbation of the input values of the network. The measure we propose is both simple and efficient to compute, treating the neural network as a black box. We provide experimental results on several real-world data sets showing the efficacy of the proposed method. We also introduce the concept of robustness curves, which allows us to further analyse robustness within and between data sets.

AI 总结：研究优化器选择对LLM涌现性失调的影响，发现优化器导致7倍失调率差异，Muon通过隐式正则化奇异值分布保持对齐，谱正则化可缓解失调。

链接：https://arxiv.org/abs/2606.31591

作者：Jason R. Brown, Patrick Leask, Lev McKinney

英文摘要： Emergent misalignment (EM) is a recently discovered phenomenon in LLMs where fine-tuning on a narrow misaligned task, such as writing insecure code, leads to broadly misaligned behaviour on unrelated prompts. Previous work has noted that the severity of EM is highly sensitive to training choices; however, we still lack a systematic characterisation of this sensitivity. We perform a sweep over several Qwen3 models, optimisers, datasets, and batch sizes, and find that the choice of optimiser has the largest effect, producing a 7x spread in misalignment rate. Surprisingly, model size has a negligible effect within the Qwen3 family. An additional sweep over 12 models from three families using Adam confirms that model scale (1B-235B) and family have negligible effects for that optimiser. Analysing the loss-alignment relationship on Qwen3-8B, we find that final log training loss is a strong predictor of alignment, and that stratifying by optimiser captures nearly all the residual variance. Training dynamics reveal that each optimiser follows a different trajectory through loss-alignment space, and that after significant training, the optimiser becomes more important than training loss as a predictor of alignment. Muon, the adaptive optimiser that preserves alignment the best, implicitly regularises for a more uniform distribution of singular values of the LoRA adapter. We evaluate this insight by training with an additional loss term that incentivises a flatter singular value spectrum, and find that this substantially recovers alignment for the more EM-prone adaptive optimisers (Adam and Lion), with negligible cost to training loss. These results identify optimiser choice as a key factor in EM severity, but show that spectral regularisation can substantially mitigate the effects of EM-prone optimisers.

AI 总结：本文提出用贝叶斯工作流（后验预测检查、模拟校准等）作为验证器，检测和修复LLM编写的概率程序中的统计错误，在检测（AUC 0.97）和修复（显著优于单元测试反馈）上表现优异。

链接：https://arxiv.org/abs/2606.31630

作者：Jian Xu, Delu Zeng, John Paisley, Qibin Zhao

英文摘要：Language models increasingly write probabilistic programs (in NumPyro, Stan, or Pyro), but a program that compiles, runs, and passes every unit test can still be \emph{statistically} wrong -- a Gaussian likelihood for heavy-tailed data, a Poisson for over-dispersed counts, an invalid prior support, or a pathological parameterization. The right verifier is therefore not a test suite but the Bayesian workflow itself: posterior predictive checks, simulation-based calibration, sampler diagnostics ($\hat R$, divergences, ESS), and held-out predictive density. We study this calibration oracle along three axes. \textbf{Detection:} on a benchmark of $14$ misspecification types across $10$ model families ($200$ instances), it flags the bug with AUC $0.97$ ($88\%$ at $2\%$ FPR \emph{when handed the correct reference program, an upper bound}) -- and a fully \emph{reference-free} version that uses no correct program reaches $62$--$78\%$ (the upper figure from a small automated model search), versus $0\%$ for a unit-test oracle. \textbf{Repair:} used as feedback in an LLM repair loop across fifteen models, calibration significantly outperforms unit-test feedback -- which is itself \emph{significantly worse than no feedback at all}, a passing test inducing false confidence that suppresses repair -- and improves over no feedback on strong-but-unsaturated models (GPT-5.1 $33{\to}92\%$, Claude $75{\to}100\%$; paired McNemar, $n{=}228$). \textbf{Reality:} on programs LLMs write from scratch for neutral briefs, $15$--$47\%$ of runnable ones are statistically misspecified (unit tests catch none), and calibration-guided repair significantly beats LLM-as-judge review, a Bayesian-workflow checklist, and data-summary self-debug. Across all three, the lesson is the same: for probabilistic programs, correctness is calibration, not compilation.

AI 总结：提出AD-CERT方法，结合对抗蒸馏与区间传播上界进行认证训练，在多个鲁棒性基准上取得最优认证性能，并证明logit级蒸馏优于特征空间蒸馏。

链接：https://arxiv.org/abs/2606.31653

机构：School of EEECS Queen’s University Belfast（贝尔法斯特女王大学电子、电气工程与计算机科学学院）

作者：Matteo Melis, Jesus Martinez Del Rincon, Vishal Sharma

英文摘要：Certified training aims to produce models whose predictions can be formally verified against adversarial perturbations, typically by optimising upper bounds on the worst-case loss over an allowed perturbation set. For neural networks, certified training methods based purely on tight relaxation bounds produce networks that are amenable to certification, but sacrifice standard accuracy. Conversely, adversarial training often yields stronger empirical robustness and standard accuracy, but the resulting models are generally difficult to certify with neural network verifiers. Recently, the literature has shown that better standard-certified accuracy trade-offs can be achieved by combining adversarial training objectives with loose over-approximations based on Interval Bound Propagation (IBP), effectively interpolating between lower and upper bounds of the worst-case loss. Building on this, we introduce AD-CERT, a certified training objective that combines adversarial distillation with an IBP upper bound. We show that distilling adversarial information over the logit space from an empirically robust teacher provides an effective lower bound surrogate for certified training, with AD-CERT achieving state-of-the-art certified performance on several robustness benchmarks. Furthermore, in a unified setup, distilling adversarial information at the logit-level is shown to improve certified accuracy over a robust feature-space distillation objective by up to 5.40 percentage points.

AI 总结：提出SEAR方法，通过对抗优化和过程奖励，让模型在推理中探索有害思路但最终输出安全答案，从而缓解安全训练导致的过度拒绝问题。

链接：https://arxiv.org/abs/2606.31748

机构：Carnegie Mellon University（卡内基梅隆大学）； SynthLabs

作者：Taeyoun Kim, Aviral Kumar

英文摘要： Safety training on language models often induces over-refusal: improved safety on harmful prompts at the cost of increased refusal on harmless ones. Though this trade-off can be mitigated by training models with reinforcement learning (RL) to reason before answering, it does not remove the underlying problem that reasoning can often be a "rubber stamp" for a predetermined response. In this paper, we address the safety-refusal trade-off by rethinking how models are trained to reason about safety. Our key insight is that unsafe reasoning can itself serve as a useful exploratory signal. Rather than preemptively blocking harmful thoughts, we encourage the model to sufficiently explore unsafe reasoning but produce a safe response. The harmful exploration improves the model's ability to distinguish harmful from harmless prompts by resolving ambiguity, allowing it to remain safe while complying only when appropriate. We cast this as an adversarial optimization problem in which a reasoning player explores strategies for producing an unsafe response and an answer player ensures that the final output is safe. We train a single model with dense rewards to play both roles within one chain-of-thought, across different segments. To achieve this, we find that process rewards are crucial for stable optimization of competing objectives. Our resulting model SEAR deliberately engages in harmful reasoning as exploration while reliably flipping back to a safe answer. We demonstrate that this behavior helps mitigate over-refusal and defend against attacks that directly manipulate the reasoning to be harmful.

AI 总结：提出MADreMIA框架，利用链式再生迭代轨迹增强生成模型的成员推断和数据集推理攻击，在低误报率下提升信号强度。

链接：https://arxiv.org/abs/2606.31991

机构：Warsaw University of Technology（华沙理工大学）

作者：Wojciech Łapacz, Stanisław Pawlak

英文摘要：The tendency of large generative models to memorize training data makes sample verification critical for privacy auditing and copyright enforcement. Current membership (MIA) and dataset inference (DI) attacks often rely on one-shot generations, which yield weak signals and limited sensitivity across modalities. Inspired by Model Autophagy Disorder (MAD), we introduce MADreMIA, a model-agnostic framework that enhances white-, gray-, and black-box MIA and DI. Rather than relying on shadow model training -- often infeasible for large generative models -- our framework facilitates scalable inference by leveraging inherent signals through iterative trajectories. This process utilizes chained generations across diverse modalities, where each output serves as the subsequent input, to improve membership evidence at low FPR. We demonstrate that memorized training samples exhibit significantly higher coherence and slower degradation during iterative regeneration than non-member generations. Our results show that MADreMIA provides richer signals across diverse model families and modalities; we present comprehensive evaluations for IARs, diffusion, and language models, alongside preliminary results demonstrating its potential for audio models.

AI 总结：提出在高维空间中嵌入图，并通过可微分的边交叉代理搜索优化美学和可读性指标的二维视角，优于标准布局，并引入交互系统DataFly。

链接：https://arxiv.org/abs/2606.31119

机构：Khoury College of Computer Sciences, Northeastern University（东北大学库里计算机科学学院）； School of Computation, Information and Technology, Technical University of Munich（慕尼黑工业大学计算、信息与技术学院）

作者：Ya Ji (1), Xuefeng Li (1), Timo Brand (2), Jacob Miller (2), Peng Zhang (1), Stephen Kobourov (2), Yifan Hu (1) ((1) Khoury College of Computer Sciences, Northeastern University, Seattle, (2) School of Computation, Information and Technology, Technical University of Munich, Heilbronn, Germany)

英文摘要：Graphs are commonly visualized in 2D, where humans readily interpret spatial relationships, yet such layouts often distort higher-dimensional structure. We propose to embed graphs in high-dimensional space and search for informative 2D viewpoints that optimize aesthetic and readability metrics (e.g., edge crossings and angular resolution), enabled by a novel differentiable surrogate for edge crossings. Numerical experiments show that these viewpoints consistently outperform standard 2D layouts, and can even surpass methods explicitly designed to optimize these metrics. We further introduce DataFly, an interactive system for exploring multiple candidate viewpoints through seamless navigation. A usability study demonstrates that our approach reveals structural patterns that remain hidden in conventional 2D visualizations.

AI 总结：提出MetaFlow，将工作流生成视为元学习问题，通过两阶段训练（监督微调+强化学习）使模型能生成可泛化的任务级工作流，在问答、代码生成和数学推理任务上实现零样本泛化。

链接：https://arxiv.org/abs/2606.30704

机构：School of Mathematics Science, Peking University（北京大学数学科学学院）

作者：Gan Luo, Zihan Qin, Bin Dong, Wotao Yin

英文摘要：Large language models (LLMs) excel across a wide range of tasks, yet their instance-specific solutions often lack the structural consistency needed for reliable deployment. Workflows that encode recurring algorithmic patterns at the task level provide a principled framework, offering robustness across instance variations, interpretable traces for debugging, and reusability across problem instances. However, manually designing such workflows requires significant expertise and effort, limiting their broader application. While automatic workflow generation could address this bottleneck, existing methods either produce instance-specific solutions without learning task-level patterns, or cannot generalize beyond their training configurations. We present MetaFlow, which casts workflow generation as a meta-learning problem: given a task and an operator set, the model learns to compose solution strategies. MetaFlow trains in two stages: supervised fine-tuning on synthetic workflow data, followed by reinforcement learning with verifiable rewards (RLVR) that uses execution feedback across problem instances in the task to improve end-to-end success. The resulting model produces effective workflows for trained tasks and exhibits strong generalization to untrained tasks and novel operator sets. Across benchmarks in question answering, code generation, and mathematical reasoning, MetaFlow achieves performance comparable to state-of-the-art baselines on in-domain tasks with single inference, while demonstrating remarkable zero-shot generalization capabilities on out-of-domain tasks and operator sets.

AI 总结：提出函数空间保护方法FORA，通过输入激活协方差的主方向投影，在微调中保留模型原有能力，实验表明优于权重空间投影。

链接：https://arxiv.org/abs/2606.31092

机构：Dalian University of Technology（大连理工大学）； Zhejiang University（浙江大学）

作者：Rui Zhou, Tianci Xie

英文摘要：Full fine-tuning adapts large language models to new tasks but can erode capabilities they already possess. Existing remedies protect through proxies such as parameter distances, importance penalties, output matching, or dominant singular directions of the weights, but none directly asks which activation directions the preserved capability relies on. We argue that a capability is characterized more faithfully by the activation subspace it induces than by the singular geometry of the weight matrix, and develop function-space protection, instantiated as FORA (Function-space Orthogonal Residual Adaptation). From label-free calibration inputs, FORA estimates, per layer, the principal directions $Q$ of the input-activation covariance and forms a right projector $P_Q = I - QQ^T$. Paired with a left projector $P_U$ from the weight SVD, the update is $\Delta W = P_U M P_Q + U_2 D_{\delta} V_2^T$: a high-capacity branch structurally barred from reading capability-relevant function directions, plus a narrow spectral channel for controlled plasticity. The construction extends to parameter-efficient adaptation via $M \to (\alpha/r) BA$. Across three settings on Qwen3-1.7B, including COGS and GSM8K learned while preserving translation and translation learned while preserving math, FORA consistently improves preservation over weight-space projection and standard regularization, with only a small new-task trade-off in the math-preservation setting. A controlled ablation isolating the projection source shows that the advantage comes not from projection itself, but from projecting onto capability-derived rather than weight-derived directions. Code is available at this https URL.

AI 总结：提出智能模式记忆（ISM），一种自我演进的记忆增强系统，通过从成功和失败案例中学习并维护策略模式库，在不更新模型参数的情况下提升冻结LLM在持续学习中的数学推理能力。

链接：https://arxiv.org/abs/2606.31191

作者：Prakhar Dixit, Tim Oates

英文摘要：We propose Intelligent Schema Memory (ISM), a self-evolving memory-augmented system that improves mathematical reasoning for a frozen LLM under continual learning with hard episodic resets. ISM maintains a compact, self-refined bank of strategy schemas learned from both successful and failed episodes, with symbolic tools that check intermediate steps and certify this http URL updating model parameters, ISM outperforms passive, retrieval, and reflection baselines on MATH-Hard and OlympiadBench, using 64% and 86% fewer schemas respectively than the strongest passive baseline. These results show that small, actively maintained, and verified strategy memories can support reliable continual mathematical reasoning under strict episodic isolation.

AI 总结：基于NHANES 2003-2006数据构建加速度计心血管代谢基准，评估三种表格学习方法预测HbA1c、甘油三酯和CRP的性能，并应用分裂共形预测进行不确定性量化与公平性分析。

链接：https://arxiv.org/abs/2606.30702

作者：Federico Felizzi

英文摘要：Structured tabular data dominates clinical medicine, yet existing benchmarks fail to reflect real-world properties like complex survey sampling, demographic oversampling, and subgroup fairness. We introduce the NHANES Accelerometry Cardiometabolic Benchmark, derived from NHANES 2003-2006, comprising 1,381 adults with hip-worn accelerometry, fasting laboratory biomarkers, dietary intake, and anthropometrics. We evaluate three tabular learning methods -- ridge regression, XGBoost, and the foundation model TabPFN v2 -- to predict glycated haemoglobin (HbA1c), fasting triglycerides, and C-reactive protein (CRP) from activity phenotypes and lifestyle covariates. TabPFN v2 achieves the best overall performance (HbA1c R^2=0.156, CRP R^2=0.383), while triglycerides remain largely unpredictable (R^2 < 0.05), consistent with known genetic dominance. We apply split conformal prediction to generate distribution-free 90% prediction intervals and evaluate demographic coverage equity across sex and race/ethnicity subgroups. Marginal coverage aligns with the 90% target for CRP and HbA1c but falls below for triglycerides. At the subgroup level, we observe localized undercoverage (e.g., HbA1c for Mexican American participants), illustrating the gap between marginal guarantees and the conditional coverage required for clinical fairness. Code and data are at this https URL.

AI 总结：本文研究表格基础模型（如TabPFN3和TabICL）在生物分子性质预测中的泛化能力，发现其性能取决于所使用的序列或分子表示。

链接：https://arxiv.org/abs/2606.31126

机构：CSIRO（澳大利亚联邦科学与工业研究组织）

作者：Davy Guan, Lu Zhang, Asiri Wijesinghe, Allen Zhu, He Zhao, Helen Power, F. Hafna Ahmed, Andrew Warden, Cheng Soon Ong, Daniel M. Steinberg

英文摘要：Predicting biomolecular properties from limited labeled data is a central bottleneck in protein engineering and small-molecule design. As strong pretrained encoders now supply rich fixed-length representations, the difficulty has shifted from representation learning to building a data-efficient predictor for the few-shot regime. Tabular foundation models such as TabPFN3 and TabICL are unlikely candidates for this role: they are in-context learners pretrained on synthetic tables drawn from random causal graphs, a generative prior with no obvious correspondence to the processes that produce protein sequences or molecular graphs. That this tabular, causal inductive bias should transfer to biomolecular data at all is unintuitive, yet we find it does. Treating each method as a predictor-representation pair, we evaluate across two domains. Over a fixed ESMC representation, tabular in-context learning is consistently competitive for protein fitness regression on ProteinGym and a diverse esterase dataset. For small-molecule classification with ECFP/RDKit descriptors, no single pairing dominates across TDC ADMET, MoleculeNet, FS-Mol, and DrugOOD; representation choice becomes a primary determinant, as expected when the predictor's own prior is indifferent to molecular structure. We conclude that tabular foundation models are strong performers on biomolecular prediction tasks, but that their performance depends strongly on the sequence or molecular representation used.

AI 总结：提出PPT-Eval基准，包含120个PowerPoint任务，并设计基于评分标准的评估框架，通过部分评分和自然语言反馈衡量智能体表现，发现现有最强模型仅达45%成功率。

链接：https://arxiv.org/abs/2606.31154

作者：Apurva Gandhi, Vishwas Suryanarayanan, Raja Hasnain Anwar, Firoz Shaik, Shubhang Desai, Thong Q. Nguyen, Muhammad Taqi Raza, Vishal Chowdhary, Graham Neubig

英文摘要：Creating and editing slides is a rich, multimodal activity that is ubiquitous in professional and educational settings, making it an ideal testbed for real-world computer-use agents. Microsoft PowerPoint is among the most widely adopted and feature-rich environments for presentation creation. We introduce PPT-Eval, a benchmark of 120 PowerPoint tasks across 12 files that cover both content creation and presentation editing scenarios, organized by difficulty. A central challenge in this domain is evaluation: tasks are complex, multimodal, and often admit many valid solutions. Moreover, today's agents frequently make only partial progress, which binary success metrics fail to capture. To address this, we design a robust evaluation framework to help create task-specific rubrics for PowerPoint tasks, taking inspiration from and building on past works for rubric-based evaluation. These rubrics award partial credit for intermediate steps, penalize unnecessary changes and poor aesthetics, and provide natural language feedback. This nuanced approach proves highly effective, achieving a Kendall's {\tau}-b correlation of 0.77 with human judgments. We find that existing frontier agents still struggle with solving PowerPoint tasks, with strong models like Claude-4.5-Opus achieving only a 45% success rate and an average partial score of 57%. The benchmark is located at: this https URL.

AI 总结：提出ICLMEM框架探测表格基础模型在上下文学习中的参数记忆化，发现低基数任务中存在中等记忆信号，但实际训练条件下信号消失。

链接：https://arxiv.org/abs/2606.31208

作者：Francesco Capano, Jonas Böhler

英文摘要：Large tabular models (LTMs), i.e., tabular foundation models leveraging in-context learning (ICL), achieve state-of-the-art performance on tabular tasks. While LLMs are known to unintentionally memorize training data, the memorization dynamics of LTMs remain largely unexplored. We investigate the potential for parametric memorization in tabular ICL. We introduce ICLMEM, a probing framework designed to separate context-based predictions from parametric memorization. Our zero-information multiple-choice context strips away valid contextual patterns to force the model to fall back on its parametric memory. Our controlled fine-tuning setup establishes membership ground truth and accounts for common pitfalls, e.g., distribution shift, feature contamination, base-rate fallacy, and the pre-trained base model acts as reference to calibrate for sample difficulty. Our controlled evaluation on a leading real-world-trained LTM detects moderate memorization signals in 8 out of 10 tasks ($\text{AUC}$ up to $0.67$ and TPR at $1\%$ FPR $>0.1$). Notably, memorization signals are strongest for low-cardinality and binary tasks. However, they largely vanish under realistic training conditions. Our findings show LTM memorization signals under specific circumstances (single-task fine-tuning with fixed samples across many epochs and small query size). To protect sensitive data, appropriate measures must be taken, which we discuss.

AI 总结：提出TDGT工具包，集成自适应贝叶斯混合合成器（ABMS）及其变体VAE-ABMS，支持GPU加速，通过11项统计保真度指标评估，在医疗、社会经济和网络安全数据集上验证了生成质量。

链接：https://arxiv.org/abs/2606.31268

作者：Vasileios C. Pezoulas, Nikolaos S. Tachos, Eleni Georga, Kostas Marias, Manolis Tsiknakis, Dimitrios I. Fotiadis

英文摘要：The growing demand for privacy-preserving data sharing has positioned synthetic data generation as a critical component of responsible AI workflows. Despite notable advances in generative modeling, existing solutions often lack integration of adaptive generation strategies, multi-metric evaluation, and accessible end-to-end generators within a unified web-based toolkit. In this work, we introduce TDGT (Tabular Data Generation Toolkit), a web-based toolkit for synthetic tabular data generation and fidelity assessment. TDGT introduces the Adaptive Bayesian Mixture Synthesizer (ABMS), a novel algorithm that autonomously determines the optimal number of mixture components through iterative cluster quality optimization, eliminating the need for manual hyperparameter configuration. Building upon ABMS, we further propose VAE-ABMS, a hybrid architecture that couples Variational Autoencoder-based latent space learning with adaptive Bayesian mixture synthesis, enabling high-fidelity generation of complex, nonlinear tabular distributions. For large-scale scenarios, TDGT provides a GPU-accelerated variant of ABMS leveraging CUDA-based k-means clustering and Gaussian mixture fitting. Synthetic data fidelity is assessed through eleven statistical fidelity metrics spanning distributional divergence, structural correlation, and sample-level similarity, complemented by privacy risk indicators including k-anonymity scoring and disclosure rate estimation. The web-based toolkit supports a real-time streaming interface with interactive Plotly-based visualizations. TDGT is assessed across datasets from healthcare, socioeconomic modeling, and cybersecurity domains, demonstrating consistent generation fidelity and statistical coherence across heterogeneous feature types and data scales.

AI 总结：提出一种基于残差重叠的停止规则，通过Bhattacharyya系数衡量类别分离，自动确定特征排序的截断点，在保持预测性能的同时大幅减少特征数量。

链接：https://arxiv.org/abs/2606.31686

机构：School of Engineering Pablo de Olavide University（巴勃罗·德·奥拉维德大学工程学院）

作者：Jesus S. Aguilar-Ruiz

英文摘要： Feature rankings are widely used in supervised feature selection because they are simple, scalable and easy to interpret. Variables are first ranked by a relevance score, and a subset is then obtained by retaining the top-ranked variables. Although the first stage has been extensively studied, the second is often governed by an arbitrary cardinality, an empirical threshold or cross-validation, without a direct interpretation. This raises a basic question: given a feature ranking, when is there enough accumulated class-separation evidence to stop selecting features? This paper develops a distributional framework for transforming supervised feature rankings into class-independent subsets through an explicit risk-calibrated stopping rule. For each variable and each pair of classes, marginal separation is measured by the Bhattacharyya coefficient between the corresponding class-conditional distributions. The proposed method selects a single global subset shared by all classes by retaining the shortest prefix of a ranking whose residual product overlap falls below a prescribed threshold for every relevant class contrast. We derive binary and multiclass Bayes-risk bounds for the labelled product marginal problem, and obtain prior-dependent and prior-free calibrations of the residual-overlap threshold from a target all-pairs risk level. An empirical comparison on high-dimensional genomic datasets illustrates that the rule can reduce tens of thousands of variables to a few dozen while maintaining predictive performance statistically comparable to the all-features baseline. As the stopping rule only requires one-dimensional marginal overlap estimates and scans a precomputed ranking, it is well suited to very high-dimensional settings where exhaustive subset search is infeasible and interpretable truncation of feature rankings is essential.

AI 总结：提出婴儿中心触觉事件编码系统，构建264k两秒触觉片段数据集，用于预训练发展基础模型，揭示触觉对婴儿视觉学习的重要性。

链接：https://arxiv.org/abs/2606.31943

机构：Boston University（波士顿大学）； University of Texas, Austin（德克萨斯大学奥斯汀分校）

作者：Max Whitton, Zecheng Wang, Puchen Liu, Quang Tuan Truong, Shengao Wang, Manaswi Yadamreddy, Oktay Ozel, Visista Jayanti, Saniya Sekhon, Hanna Samuel Tadesse, Lawrence Miao, Junjie Wang, Jiasen Lu, Chen Yu, Boqing Gong

英文摘要：Is the sense of touch a mechanism for human babies' learning of visual concepts? If so, can we quantify its importance, and to what extent do babies rely on their sense of touch for visual learning? To approach these questions in a principled way, we propose a structured coding system for baby-centric touch events, yielding a dataset of 264k two-second clips of touch events coded according to this system. Using this dataset, we pretrain developmentally grounded models that reveal promising insights into the nature of baby learning from touch.

AI 总结：提出QVal，一种无需训练的基准测试，通过Q值对齐直接评估密集监督信号质量，避免下游训练开销。在21种方法、4个环境上的实验表明，简单提示基线优于现有方法。

链接：https://arxiv.org/abs/2606.32034

机构：Tübingen AI Center, University of Tübingen（图宾根大学图宾根人工智能中心）； Fondazione Bruno Kessler（布鲁诺·凯斯勒基金会）

作者：Sergio Hernández-Gutiérrez, Matteo Merler, Ilze Amanda Auzina, Joschka Strüber, Ameya Prabhu, Matthias Bethge

英文摘要：LLM agents increasingly act over long horizons, where a single trajectory can contain hundreds or thousands of actions. In these settings, outcome-only rewards provide too sparse guidance, failing to inform the model about the goodness of intermediate actions. Dense supervision methods aim to solve this problem by scoring intermediate steps, from intrinsic confidence to self-distillation and embedding similarities. However, it is common practice to evaluate them by measuring the downstream performance of a training pipeline that integrates them. This is expensive, conflates supervision quality with training engineering confounders, and renders different methodological families requiring distinct training setups incomparable. As a result, dense supervision methods are rarely benchmarked on common ground. We introduce QVal, a training-free testbed for directly evaluating dense supervision signals. Given a state-action pair, QVal measures how well a method's score is Q-aligned: whether it orders actions according to the Q-values of a strong reference-policy. This lets us compare signals before any training run and separate signal quality from other engineering choices. We instantiate QVal as QVal-v1.0, benchmarking 21 dense supervision methods across four diverse environments and seven methodological families, with over 1.2K evaluation experiments across six open-weight model backbones. We find that simple prompting baselines consistently outperform recent dense supervision methods from the literature, and that performance clusters strongly by family. These findings hold across model sizes, environments, and observation modalities. QVal is designed to be easily extensible to new environments and methods, enabling researchers to iterate on dense supervision methods before any training run.

AI 总结：提出MCO-PDE框架，通过软竞争权重机制融合多源数据集，联合发现共享偏微分方程的结构和参数，在稀疏观测下高精度恢复经典方程。

链接：https://arxiv.org/abs/2606.30699

作者：Hao Xu, Siyu Lou, Yuntian Chen, Dongxiao Zhang

英文摘要： Discovering governing equations directly from observational data is a key step towards interpretable scientific machine learning. Current data-driven approaches typically operate on a single dataset, inherently limiting their performance when faced with restricted observations. In practice, multiple datasets are often available for the same physical system, distinguished only by distinct initial conditions or boundary configurations. Here, we present a competitive optimization framework designed to discover shared partial differential equations (PDEs) from multi-source datasets, termed MCO-PDE. The framework first trains independent neural surrogates for each data source, and then employs a soft-competitive weighting mechanism to dynamically assess dataset credibility and aggregate a consensus global coefficient. Integrated with a genetic algorithm for structural search, this approach simultaneously identifies the functional forms and parameters of the governing laws. We demonstrate that fusing as few as 50 observations per dataset across seven cases recovers canonical equations with high accuracy. The framework inherently handles two- and three-dimensional domains characterized by irregular boundaries and heterogeneous coefficients, and successfully extracts physically meaningful laws from real-world wave-tank experiments. Overall, this work establishes a promising route for automated scientific discovery via heterogeneous data fusion.

AI 总结：提出ReactionAtlas框架，利用机器学习生成模型和DFT训练的力场，从少量种子分子自动构建化学反应网络，以甲酸循环为例展示了在生命起源化学中的大规模应用。

链接：https://arxiv.org/abs/2606.30778

机构：BIFOLD – Berlin Institute for the Foundations of Learning and Data（BIFOLD – 柏林学习与数据基础研究所）； TU Berlin（柏林工业大学）； Department of Artificial Intelligence, Korea University（高丽大学人工智能系）； MPI for Informatics（马克斯·普朗克信息学研究所）

作者：Stefan Gugler, Max Eissler, Khaled Kahouli, Klaus-Robert Müller

英文摘要：Mapping a chemical reaction network, the graph of minima and transition states (TS) and the elementary reactions connecting them, is the natural language of chemistry, from catalysis to combustion to the origin of life. Constructing such a reaction network for a given chemistry has been impractical: it requires finding and characterizing tens of thousands of TS, a task for which traditional methods such as density functional theory (DFT) are typically prohibitively slow and require reactant and product as input. We introduce ReactionAtlas, which builds a reaction network $\textit{ab origine}$ from a handful of seed molecules and without hand-crafted rules. Specifically, our machine-learned generative model proposes reactions from kinetically sampled candidate compounds and a DFT-trained machine learned force field (MLFF) filters them to valid TS, the resulting products of which enter the search as new seeds. Starting from eight pre-biotic seeds (CH$_2$O, H$_2$O, OH$^-$, H$_3$O$^+$, CO$_2$, H$_2$CO$_3$, HCO$_3^-$, H), ReactionAtlas discovers $\sim$47,000 reactions among $\sim$12,000 compounds. The MLFF TSs match the PBE0 references within 0.5 Å RMSD in 85% of the cases and can be easily brought to the PBE0 level. Thus, ReactionAtlas maps small carbohydrate chemistry up to C$_4$H$_8$O$_4$ at unprecedented scale and accuracy, including charge and stereo information. It enables novel insights into many well-studied reaction paths, including the formose cycle, which we highlight for its centrality to the chemical origins of life. Notably, our framework also allows establishing alternative reaction pathways for formose chemistry.

AI 总结：针对现实应用中均值-残差降尺度方法产生的偏差和欠分散问题，提出ReMatch方法，通过PCA空间中的最优传输对齐训练与测试残差分布，减少欠分散并改善校准。

链接：https://arxiv.org/abs/2606.30821

机构：Cornell University（康奈尔大学）

作者：Yujin Kim, Nidhi Soma, Sarah Dean

英文摘要：Probabilistic downscaling is the task of modeling the conditional distribution of high-resolution fields given coarse inputs, and is a central challenge to atmospheric science, climate modeling, and other multiscale physical systems. A widely used paradigm decomposes the problem into a deterministic mean predictor followed by a stochastic residual generator. While effective in idealized settings, this mean--residual approach frequently produces biased and under-dispersive ensembles in real-world applications. Is this merely generic predictive uncertainty miscalibration? We show that the root cause is more fundamental: residual target misspecification, the residual distribution induced during training differs systematically from the one required at test time due to downscaling bias. To close this gap, we introduce ReMatch (Residual Distribution Matching). ReMatch aligns the training residual distribution toward the test-time regime via optimal transport in a low-dimensional PCA space. This preserves the statistical benefits of the mean--residual framework while reducing the train--test mismatch in the residual targets seen by the stochastic generator. On a controlled synthetic benchmark with varying bias levels and a real-world HRRR--ERA5 wind field downscaling task, ReMatch substantially reduces under-dispersion, improves calibration (SSR and CRPS), and outperforms strong baselines, including the standard mean--residual model and its variants, as well as state-of-the-art super-resolution models. Our code is available at this https URL.

AI 总结：提出一种跨疾病家族训练的logistic回归时序先验，无需重新拟合即可应用于新疫情传播重建，在ANDV基准上显著优于基线，并揭示传播标签不确定性影响干预优先级。

链接：https://arxiv.org/abs/2606.30842

机构：National Institute of Textile Engineering and Research (NITER)（国家纺织工程与研究学院）

作者：Md Ahsan Karim

英文摘要：Outbreak transmission reconstruction treats epidemiological timing and transmission labels as deterministic ground truth; neither has been systematically evaluated. We trained a logistic regression temporal prior on eleven disease families, locked all parameters before accessing any target outbreak data, and applied it without refitting to a strict Andes virus (ANDV) parent-ranking benchmark of 29 tasks. The locked prior achieved mean reciprocal rank (MRR) 0.571 versus 0.274 and Top-1 accuracy 37.9% versus 13.8% against the best source-trained parametric baseline (permutation p <= 0.0002; 7-8 reversals to lose MRR significance). A phylogenetic concordance audit of 75 NYC mpox inter-host pairs - independent label-reliability evidence rather than a prior validation - found that 54.67% (exact 95% CI: 42.75-66.21%) were genomically unresolved or unsupported. Retaining uncertain edges in ANDV and Guangdong Delta graphs shifted top-5 source-priority sets (Jaccard 0.429-0.667). Transmission-label uncertainty was measurable in the outbreak evidence modules examined, and retaining uncertain links changed which source cases were prioritized for intervention.

AI 总结：针对双边市场政策个性化中跨方外部性和市场干扰问题，提出集成框架，通过混合排名模型和目标外推方法，在满足约束条件下提升目标指标。

链接：https://arxiv.org/abs/2606.30932

机构：LinkedIn Corporation（领英公司）

作者：Yufei Wu, Zhen Yan

英文摘要：Two-sided marketplaces connect distinct user groups whose interests often conflict -- improving outcomes on one side could degrade the other side's experience. To address this challenge, we deploy an integrated framework for personalizing free-value thresholds -- a policy governing the scope of complimentary services for job listings -- across a two-sided job marketplace connecting millions of employers and job seekers. Our personalized policy delivers statistically significant and economically sizable lift in the target metric while respecting engagement guardrail constraints. Direct application of standard uplift methods proves insufficient here for two reasons. First, cross-side externalities demand multi-objective optimization: maximizing employer-side metrics risks harming job seeker engagement, with effects varying substantially across job segments. Second, marketplace interference necessitates cluster-level randomization, limiting us to few discrete treatment levels -- effectively a form of positivity violation that rules out methods designed for continuous treatments. We contribute an integrated framework with three components. Our ensemble-based hybrid ranking models target and guardrail metrics separately, cutting guardrail risk by over 10% for equivalent target gains compared to single-objective approaches. A treatment effect extrapolation method extends our estimates from limited experimental variation to untested policy levels, relying on monotonicity assumptions that we validate empirically. Finally, we present production deployment, where post-launch data confirms both extrapolation accuracy and guardrail compliance. Our deployed system demonstrates that principled methodology can enable meaningful personalization even when experiments are severely constrained and different objectives compete -- common conditions that characterize many real-world marketplaces.

AI 总结：提出使用条件归一化流从短弧角度测量中推断地月空间初始状态的后验分布，结合物理信息采样并通过非线性最小二乘优化提供经典算法的热启动。

链接：https://arxiv.org/abs/2606.30936

机构：University of Strathclyde（斯特拉斯克莱德大学）

作者：Walther Litteri, Massimiliano Vasile

英文摘要：Generative Astrodynamics is advanced in this work by extending generative modelling to an orbit determination problem in the cislunar environment. The task is formulated as conditional density estimation, aiming to infer the probability distribution of the initial state from angles-only measurements over short observation arcs. A normalising flow is trained on perturbed topocentric observations from Near Rectilinear Halo Orbits, enabling a flexible and potentially multimodal posterior representation. Given new measurements, the learned density is sampled to generate statistically consistent and physics-informed state hypotheses. These estimates are refined via nonlinear least-squares minimisation, providing a competitive warm start for classical algorithms.

AI 总结：本文提出一种结合双重/去偏机器学习与层次贝叶斯框架的因果方法，利用地理空间相似性度量估计双边市场中新增供给对交易量的影响，并在Airbnb数据上验证了其合理性和强样本外性能。

链接：https://arxiv.org/abs/2606.30999

机构：Airbnb, Inc.（爱彼迎公司）

作者：Yufei Wu, Daniel Schmierer, Dan Zylberglejd

英文摘要：In two-sided marketplaces with heterogeneous products, it is important to understand the causal relationship between additional supply and marketplace outcomes, such as the total quantity transacted or transaction value in the marketplace. This paper studies a causal machine learning approach to estimating this relationship across product segments. We use the Airbnb marketplace as an example, focusing on the impact of additional listing supply on total bookings, but the methodology applies to other two-sided marketplaces. Our approach combines double/debiased machine learning with a hierarchical Bayesian framework that leverages pre-existing knowledge as priors. We construct tractable and informative features for the model by leveraging measures of product segment similarity from the geospatial literature. We find that such a model provides plausible estimates of the marketplace returns to additional supply and strong out of sample performance.

AI 总结：针对资源匮乏环境下专科癫痫专家稀缺的问题，提出MANANA框架，通过非参数提示学习从少量患者数据中学习本地处方指南，结合贝叶斯提示平均实现不确定性驱动的选择性预测，在乌干达儿科癫痫队列中提升处方准确率并支持转诊。

链接：https://arxiv.org/abs/2606.31036

机构：University of California, Los Angeles（加州大学洛杉矶分校）； Makerere University（马凯雷雷大学）； St. Francis Hospital Nsambya（圣弗朗西斯医院恩桑比亚分院）

作者：Shreyas Rajesh, Kartik Sharma, Tonmoy Monsoor, Mehmet Yigit Turali, Richard Idro, Juliana Kayaga, Robert Sebunya, Tracy Tushabe Namata, Jessica Nichole Pasqua, Vwani Roychowdhury, Rajarshi Mazumder

英文摘要：Specialist epilepsy expertise is scarce in resource-constrained settings, making LLM-based decision support attractive for frontline clinicians managing longitudinal treatment. Such systems must adapt to local prescribing practice and know when to defer. We study this problem in Ugandan pediatric epilepsy care, predicting anti-seizure medication regimens from longitudinal unstructured clinic notes. Standard prompting achieves non-trivial agreement with physician prescriptions, but neurologist review shows that many errors reflect distribution-miscalibrated prescribing defaults rather than failures to parse the local record. We introduce MANANA, a non-parametric prompt-learning framework that learns local prescribing guidance from a small patient-level training set. MANANA converts observed prescription errors into auditable prompt memories, instantiated in single-agent and multi-agent variants, and improves over classical ML models, direct LLM prompting, and prompt-optimization baselines across two independently collected Ugandan cohorts. We further propose Bayesian prompt averaging, which converts the learned prompt trajectory into prescription likelihoods and an uncertainty-based deferral signal. On the independently collected held-out cohort, this improves visit-level top-3 prescription accuracy by 4-8 percentage points over prompt-optimization baselines and enables selective prediction: the system can auto-handle the most confident half of cases at 95% precision, or the most confident quarter at 99% precision, while deferring lower-confidence cases for specialist review.

AI 总结：提出一种基于贝叶斯滤波的方法，从部分含噪测量中学习物理系统动力学，通过拉格朗日力学建模并用神经网络参数化能量，联合学习参数和状态。

链接：https://arxiv.org/abs/2606.31137

机构：School of Engineering and Applied Science, Ahmedabad University（艾哈迈达巴德大学工程与应用科学学院）； Department of Electrical Engineering, Indian Institute of Technology (BHU) Varanasi（印度理工学院（BHU）瓦拉纳西分校电气工程系）； ELLIS Institute Finland（芬兰ELLIS研究所）； Department of Electrical Engineering and Automation, Aalto University（阿尔托大学电气工程与自动化系）

作者：Kundan Kumar, Shreya Das, Simo Särkkä

英文摘要：This paper proposes a Bayesian filtering-based approach for learning the dynamics of a physical system from partial, noisy measurements. We model the system dynamics using a Lagrangian mechanics formulation. As in Lagrangian neural networks (LNNs), we parameterize the kinetic and potential energies with neural networks. The unknown external forces in the Lagrangian formulation are modeled as white Gaussian noise. The corresponding Euler--Lagrange equations then yield a continuous-time stochastic state-space model (SSM) that describes the system dynamics. The neural network parameters and system states are then jointly learned via a maximum-likelihood method using Gaussian-approximation-based Bayesian filters. The effectiveness of the proposed method is demonstrated on pendulum and Duffing oscillator examples, and its performance is compared with conventional LNNs and with approximate Bayesian filters using known system models.

AI 总结：提出STOIC框架，结合图神经网络与表格基础模型，通过零样本校准实现图结构能源时间序列的共形预测，提供可靠的不确定性估计。

链接：https://arxiv.org/abs/2606.31804

作者：Keivan Faghih Niresi, Alice Cicirello, Olga Fink

英文摘要：Accurate energy demand forecasting is essential for the reliable operation and planning of modern sustainable energy systems. Spatial-temporal graph neural networks (STGNNs) have recently achieved strong performance in point forecasting by jointly modeling temporal dynamics and relational dependencies across interconnected energy nodes. However, in real-world energy systems, accurate point forecasts alone are insufficient, as operators also require reliable uncertainty estimates to support risk-aware decision-making, grid stability, and operational planning under uncertainty. Conformal prediction provides a principled and model-agnostic framework for uncertainty quantification with statistical coverage guarantees, making it particularly attractive for safety-critical energy applications. However, existing conformal prediction approaches often fail to fully capture the complex spatial-temporal structure of energy systems. To address these limitations, we propose STOIC (Spatial-Temporal Graph Conformal Prediction with In-Context Learning), a novel framework that integrates graph-based forecasting with the zero-shot calibration capabilities of tabular foundation models. STOIC first generates point forecasts using an STGNN and subsequently reformulates spatial-temporal residuals into a tabular representation suitable for in-context learning. Leveraging a tabular foundation model, STOIC calibrates prediction intervals without task-specific retraining, effectively capturing both sequential and relational dependencies. We evaluate STOIC on five diverse benchmarks, including synthetic simulations as well as real-world electricity and district heating networks. Across all datasets, STOIC consistently outperforms existing conformal prediction baselines, delivering more reliable and robust uncertainty estimates for complex graph-structured energy time series.

AI 总结：提出界面感知神经牛顿预条件器(IA-NNP)，通过学习状态依赖的界面修正解决内聚力模型隐式有限元分析中的收敛困难，保持原始牵引-分离律，在多个基准测试中提升困难增量收敛性并减少失败。

链接：https://arxiv.org/abs/2606.31921

机构：National Center for Applied Mathematics, Tianjin University（天津大学国家应用数学中心）； School of Mechanical and Aerospace Engineering, Jilin University（吉林大学机械与航空航天工程学院）

作者：Zhangyong Liang, Huanhuan Gao

英文摘要：Cohesive Zone Models (CZMs) are widely used to simulate interface fracture, delamination, adhesive failure, and fiber--matrix debonding in aerospace composite structures. In implicit quasi-static finite element analyses, cohesive softening may introduce negative interface tangents, solution jumps, and Newton-basin mismatch, so the previous converged state can become a poor initial guess for the next increment. This may lead to stagnation, wrong-branch convergence, or repeated step cuts. Existing remedies, including viscous regularization, path following, dynamic relaxation, and manual Newton--Raphson (NR) modification, either alter the effective response, increase cost, or rely on hand-crafted interface rules. This work proposes an Interface-Aware Neural Newton Preconditioner (IA-NNP) for difficult CZM increments. IA-NNP recasts manual NR modification as rule-based interface lifting and generalizes it into a learned, state-dependent interface correction. The method acts only on active interface variables and preserves the original traction--separation law, residual assembly, tangent evaluation, history update, and dissipation checks. Two realizations are developed: IA-NNP-Init for learned initial-guess lifting and IA-NNP-NL for iteration-level nonlinear right preconditioning. Interface graph features encode opening, traction, tangent, damage/history variables, mode mixity, residuals, and neighboring states. The correction is bounded, confidence-gated, and accepted only through the original CZM Newton solve. A root-equivalence property shows that IA-NNP changes the path to convergence but not the discrete CZM solution set. Tests on horizontal, circular, two-interface, and active-front benchmarks show improved difficult-increment convergence, better branch recovery, and fewer failures than standard NR and manual NR modification, while preserving the force--displacement response.

AI 总结：提出CoMet方法，将多模态大模型的不确定性分解为上下文项和多样性项，通过轻量级后验模块高效估计，无需自回归生成或重复采样，在多个基准上优于现有方法。

链接：https://arxiv.org/abs/2606.32012

机构：Princeton University（普林斯顿大学）

作者：Sanghyuk Chun, William Yang, Amaya Dharmasiri, Olga Russakovsky

英文摘要： Uncertainty estimation has been a long-standing challenge in AI models; it amounts to "knowing what you don't know," and metacognition is notoriously difficult even for humans (cf. the Dunning-Kruger effect). Although it is still far from solved even in simpler classification systems, tackling it in multimodal large language models (MLLMs) is becoming increasingly important. Within MLLMs, uncertainty can stem from any of the diverse sources as well as from their relationships, and further can stem from the unbounded answers in the open-ended setting. To tackle the issues, we propose CoMet, an MLLM uncertainty estimation method by decomposing uncertainty into a context-specific term and a multiplicity-specific term. The former captures ambiguity induced by the given context (e.g., task or prompt), while the latter captures how many plausible answers determined by the context remain compatible with the given input. We train a lightweight post-hoc uncertainty module to estimate these quantities, which enables efficient uncertainty estimation without autoregressive answer generation or repeated sampling. Experiments on various open-ended multimodal benchmarks, hallucination detection, and multiple-choice visual question answering benchmarks show that CoMet consistently improves uncertainty estimation over existing baselines while remaining efficient in practice. Code is available at this https URL

AI 总结：提出AI辅助研究中证据许可主张的概念与方法论框架，通过五个算子描述研究过程，强调校准作为管理科学断言权的机制，并区分不同语义类型。

链接：https://arxiv.org/abs/2606.31273

机构：School of Life Science and Technology, Institute of Science Tokyo（东京科学大学生命科学与技术学院）； Department of Computational Biology and Medical Sciences, Graduate School of Frontier Sciences, The University of Tokyo（东京大学前沿科学研究生院计算生物学与医学科学系）

作者：Hongmin Li

英文摘要：AI-assisted research has entered a stage in which the central question is not only whether systems can generate hypotheses, run experiments, or produce manuscripts, but whether their scientific claims are calibrated to the evidence that supports them. This Perspective-style paper develops a conceptual and methodological framework for evidence-licensed claims in AI-assisted research. Motivated by representative routes including specialized scientific foundation models, LLM research assistants, multi-agent co-scientists, AI Scientist pipelines, mathematical discovery agents, and self-driving laboratories, it represents AI-assisted research as five operators: hypothesis generation, model-mediated consequence derivation, external validation, belief update, and claim calibration. The central claim is that calibration is not merely cautious wording but a mechanism for managing scientific assertion rights: evidence licenses some forms of speech and withholds others. The paper distinguishes linguistic, consequence-based, interventional, and evidence-licensed semantics; defines the claim-evidence gap and epistemic debt; and treats minimal structural reconstruction across heterogeneous outputs as an upward form of claim calibration. AISim-Cal is included as an illustrative synthetic dynamics exercise, not as an empirical forecast or benchmark. The resulting principles are: no claim without license, validation does not determine claim level, and automation amplifies the need for calibration. Reliable AI-assisted research is therefore evaluated as a loop that generates hypotheses, derives testable consequences, accepts independent adjudication, updates beliefs, and outputs only evidence-licensed claims.

AI 总结：研究开放模型能否替代解释封闭模型，发现预测保真度显著高估归因保真度，模型虽答案一致但理由不同，机械解释不能自动迁移。

链接：https://arxiv.org/abs/2606.32008

作者：Philippe Chlenski, Zachariah Carmichael, Ayush Warikoo, Chia-Tse Shao, Yingxiao Ye, Aobo Yang, Vivek Miglani, Nehal Bandi

英文摘要：Mechanistic interpretability (MI) requires full access to model internals, yet the APIs for most widely deployed language models at best expose log-probabilities over output tokens. This creates a surrogate problem: when do measurements made on open models allow us to make claims about a closed model? We evaluate surrogate fidelity at the prediction, attribution, and representation levels. For binary classification tasks, log-odds provide an API-compatible scalar readout of the model's representation space, and leave-one-out attributions provide insight into model behavior. Across eleven models spanning four families (Llama, Qwen, GPT, and Gemini), we find that prediction fidelity substantially overstates attribution fidelity: models that agree on what the answer is often disagree on why. We document an access-validity inversion: white-box signals like attention patterns and perturbation magnitudes are highly stable across models but only weakly predictive of causal attributions, which black-box input ablations capture by design. Mechanistic insight does not automatically transfer to closed targets, and prediction-level agreement is insufficient to warrant such transfer. Code and results are available at this https URL.