点击阅读原文访问arxivdaily.com,涵盖CS|物理|数学|经济|统计|金融|生物|电气领域,更有搜索、收藏等功能!
cs.LG 方向,今日共计161篇
大模型相关(24篇)
【1】Aligning LLMs Toward Multi-Turn Conversational Outcomes Using Iterative PPO
标题:使用迭代PPO将LLM调整为多回合对话结果
链接:https://arxiv.org/abs/2511.21638
作者:Daniel R. Jiang,Jalaj Bhandari,Yukai Yang,Rémi Munos,Tyler Lu
备注:12 pages, 2 figures
【2】Beyond URLs: Metadata Diversity and Position for Efficient LLM Pretraining
标题:超越URL:元数据多样性和高效LLM预训练的地位
链接:https://arxiv.org/abs/2511.21613
作者:Dongyang Fan,Diba Hashemi,Sai Praneeth Karimireddy,Martin Jaggi
【3】Visualizing LLM Latent Space Geometry Through Dimensionality Reduction
标题:通过简化虚拟空间可视化LLM潜空间几何
链接:https://arxiv.org/abs/2511.21594
作者:Alex Ning,Vainateya Rangaraju
备注:24 pages, 16 figures
【4】A Systematic Study of Model Merging Techniques in Large Language Models
标题:大型语言模型中模型合并技术的系统研究
链接:https://arxiv.org/abs/2511.21437
作者:Oğuz Kağan Hitit,Leander Girrbach,Zeynep Akata
【5】Do Reasoning Vision-Language Models Inversely Scale in Test-Time Compute? A Distractor-centric Empirical Analysis
标题:推理视觉语言模型在测试时计算中是否具有巨大的规模?以干扰者为中心的实证分析
链接:https://arxiv.org/abs/2511.21397
作者:Jiyun Bae,Hyunjong Ok,Sangwoo Mo,Jaeho Lee
备注:preprint
【6】Masks Can Be Distracting: On Context Comprehension in Diffusion Language Models
标题:面具可以分散注意力:扩散语言模型中的上下文理解
链接:https://arxiv.org/abs/2511.21338
作者:Julianna Piskorz,Cristina Pinneri,Alvaro Correia,Motasem Alfarra,Risheek Garrepalli,Christos Louizos
【7】How to Correctly Report LLM-as-a-Judge Evaluations
标题:如何正确报告LLM作为评委的评估
链接:https://arxiv.org/abs/2511.21140
作者:Chungpa Lee,Thomas Zeng,Jongwon Jeong,Jy-yong Sohn,Kangwook Lee
【8】From Bits to Rounds: Parallel Decoding with Exploration for Diffusion Language Models
标题:从位到轮:并行解码与扩散语言模型探索
链接:https://arxiv.org/abs/2511.21103
作者:Hengyu Fu,Baihe Huang,Virginia Adams,Charles Wang,Venkat Srinivasan,Jiantao Jiao
备注:24 pages, 6 figures
【9】MLPMoE: Zero-Shot Architectural Metamorphosis of Dense LLM MLPs into Static Mixture-of-Experts
标题:MLPMoE:密集LLM MLP的Zero-Shot架构变形为静态专家混合体
链接:https://arxiv.org/abs/2511.21089
【10】Aligning LLMs with Biomedical Knowledge using Balanced Fine-Tuning
标题:使用平衡微调使LLM与生物医学知识保持一致
链接:https://arxiv.org/abs/2511.21075
作者:Zhenchao Tang,Fang Wang,Haohuai He,Jiale Zhou,Tianxu Lv,Jun Zhu,Shouzhi Chen,Minghao Yang,Yu Wang,Jiayang Wu,Yidong Song,Jianhua Yao
【11】A Unified Understanding of Offline Data Selection and Online Self-refining Generation for Post-training LLMs
标题:统一理解训练后LLM的离线数据选择和在线自精炼生成
链接:https://arxiv.org/abs/2511.21056
【12】Breaking the Safety-Capability Tradeoff: Reinforcement Learning with Verifiable Rewards Maintains Safety Guardrails in LLMs
标题:打破安全能力权衡:具有可验证奖励的强化学习维护LLC的安全护栏
链接:https://arxiv.org/abs/2511.21050
作者:Dongkyu Derek Cho,Huan Song,Arijit Ghosh Chowdhury,Haotian An,Yawei Wang,Rohit Thekkanal,Negin Sokhandan,Sharlina Keshava,Hannah Marlowe
备注:AAAI-26 Workshop on Post-AI Formal Methods
【13】Semantic Anchors in In-Context Learning: Why Small LLMs Cannot Flip Their Labels
标题:上下文学习中的语义前提:为什么小型LLM无法翻转标签
链接:https://arxiv.org/abs/2511.21038
作者:Anantha Padmanaban Krishna Kumar
备注:13 pages total (7 pages main text, 3 pages references, 3 pages appendix), 2 figures, 14 tables. Code available at https://github.com/AnanthaPadmanaban-KrishnaKumar/semantic-anchors-icl
【14】Subgoal Graph-Augmented Planning for LLM-Guided Open-World Reinforcement Learning
标题:LLM引导的开放世界强化学习的子目标图形增强规划
链接:https://arxiv.org/abs/2511.20993
【15】BUSTR: Breast Ultrasound Text Reporting with a Descriptor-Aware Vision-Language Model
标题:BUSTR:使用描述符感知视觉语言模型的乳腺超声文本报告
链接:https://arxiv.org/abs/2511.20956
作者:Rawa Mohammed,Mina Attin,Bryar Shareef
备注:13 pages, 2 figures, 6 tables
【16】Length-MAX Tokenizer for Language Models
标题:语言模型的Longth-MAX令牌器
链接:https://arxiv.org/abs/2511.20849
【17】Structured Prompting Enables More Robust, Holistic Evaluation of Language Models
标题:结构化预算支持对语言模型进行更稳健、更全面的评估
链接:https://arxiv.org/abs/2511.20836
作者:Asad Aali,Muhammad Ahmed Mohsin,Vasiliki Bikia,Arnav Singhvi,Richard Gaus,Suhana Bedi,Hejie Cui,Miguel Fuentes,Alyssa Unell,Yifan Mai,Jordan Cahoon,Michael Pfeffer,Roxana Daneshjou,Sanmi Koyejo,Emily Alsentzer,Percy Liang,Christopher Potts,Nigam H. Shah,Akshay S. Chaudhari
【18】Training-Free Diffusion Priors for Text-to-Image Generation via Optimization-based Visual Inversion
标题:通过基于优化的视觉倒置实现文本到图像生成的免训练扩散先验
链接:https://arxiv.org/abs/2511.20821
作者:Samuele Dell'Erba,Andrew D. Bagdanov
备注
:11 pages, 7 figures, technical report (preprint)
【19】Memories Retrieved from Many Paths: A Multi-Prefix Framework for Robust Detection of Training Data Leakage in Large Language Models
标题:从多条路径检索的记忆:用于稳健检测大型语言模型中训练数据泄漏的多前置框架
链接:https://arxiv.org/abs/2511.20799
作者:Trung Cuong Dang,David Mohaisen
备注:11 pages, 2 tables, 8 figures
【20】Learning from Risk: LLM-Guided Generation of Safety-Critical Scenarios with Prior Knowledge
标题:从风险中学习:在法学硕士指导下生成具有先验知识的安全关键场景
链接:https://arxiv.org/abs/2511.20726
作者:Yuhang Wang,Heye Huang,Zhenhua Xu,Kailai Sun,Baoshen Guo,Jinhua Zhao
备注:24 pages, 6 figures
【21】Active Slice Discovery in Large Language Models
标题:大型语言模型中的活动切片发现
链接:https://arxiv.org/abs/2511.20713
作者:Minhui Zhang,Prahar Ijner,Yoav Wald,Elliot Creager
备注:Accepted for presentation at NeurIPS 2025 - Reliable ML Workshop
【22】PropensityBench: Evaluating Latent Safety Risks in Large Language Models via an Agentic Approach
标题:PropensityBench:通过统计方法评估大型语言模型中的潜在安全风险
链接:https://arxiv.org/abs/2511.20703
作者:Udari Madhushani Sehwag,Shayan Shabihi,Alex McAvoy,Vikash Sehwag,Yuancheng Xu,Dalton Towers,Furong Huang
【23】Minimizing Hyperbolic Embedding Distortion with LLM-Guided Hierarchy Restructuring
标题:利用LLM引导的分层重组最小化双曲嵌入失真
链接:https://arxiv.org/abs/2511.20679
作者:Melika Ayoughi,Pascal Mettes,Paul Groth
【24】Domain-Grounded Evaluation of LLMs in International Student Knowledge
标题:基于领域的法学硕士国际学生知识评估
链接:https://arxiv.org/abs/2511.20653
作者:Claudinei Daitx,Haitham Amar
Graph相关(图学习|图神经网络|图优化等)(4篇)
【1】Context-Specific Causal Graph Discovery with Unobserved Contexts: Non-Stationarity, Regimes and Spatio-Temporal Patterns
标题:未观察上下文的特定上下文因果图发现:非平稳性、状态和时空模式
链接:https://arxiv.org/abs/2511.21537
作者:Martin Rabel,Jakob Runge
【2】Representation Integrity in Temporal Graph Learning Methods
标题:时态图学习方法中的表示完整性
链接:https://arxiv.org/abs/2511.20873
作者:Elahe Kooshafar
备注:70 pages
【3】RefTr: Recurrent Refinement of Confluent Trajectories for 3D Vascular Tree Centerline Graphs
标题:RefTLR:3D血管树中心线图的汇合轨迹的循环细化
链接:https://arxiv.org/abs/2511.20823
作者:Roman Naeem,David Hagerman,Jennifer Alvén,Fredrik Kahl
【4】Pretraining Transformer-Based Models on Diffusion-Generated Synthetic Graphs for Alzheimer's Disease Prediction
标题:在扩散生成合成图上预训练基于变换器的模型用于阿尔茨海默病预测
链接:https://arxiv.org/abs/2511.20704
作者:Abolfazl Moslemi,Hossein Peyvandi
备注:14 pages. Preprint
Transformer(7篇)
【1】Mechanisms of Non-Monotonic Scaling in Vision Transformers
标题:视觉变形者的非单调缩放机制
链接:https://arxiv.org/abs/2511.21635
作者:Anantha Padmanaban Krishna Kumar
备注:16 pages total (11 pages main text, 1 pages references, 4 pages appendix), 5 figures, 11 tables. Code available at https://github.com/AnanthaPadmanaban-KrishnaKumar/Cliff-Plateau-Climb
【2】Mechanistic Interpretability for Transformer-based Time Series Classification
标题:基于变换器的时间序列分类的机制解释性
链接:https://arxiv.org/abs/2511.21514
作者:Matīss Kalnāre,Sofoklis Kitharidis,Thomas Bäck,Niki van Stein
【3】Subjective Depth and Timescale Transformers: Learning Where and When to Compute
标题:主观深度和时间尺度Transformer:学习何时何地计算
链接:https://arxiv.org/abs/2511.21408
作者:Frederico Wieser,Martin Benfeghoul,Haitham Bou Ammar,Jun Wang,Zafeirios Fountas
【4】BanglaMM-Disaster: A Multimodal Transformer-Based Deep Learning Framework for Multiclass Disaster Classification in Bangla
标题:BanglaMM-Disaster:一个基于多模态转换器的深度学习框架,用于孟加拉国的多类灾害分类
链接:https://arxiv.org/abs/2511.21364
作者:Ariful Islam,Md Rifat Hossen,Md. Mahmudul Arif,Abdullah Al Noman,Md Arifur Rahman
备注:Presented at the 2025 IEEE International Conference on Signal Processing, Information, Communication and Systems (SPICSCON), November 21-22, 2025, University of Rajshahi, Bangladesh. 6 pages, 9 disaster classes, multimodal dataset with 5,037 samples
【5】ASR Error Correction in Low-Resource Burmese with Alignment-Enhanced Transformers using Phonetic Features
标题:使用语音特征的对齐增强转换器在低资源缅甸语中进行ASR纠错
链接:https://arxiv.org/abs/2511.21088
作者:Ye Bhone Lin,Thura Aung,Ye Kyaw Thu,Thazin Myint Oo
备注:7 pages, 2 figures, 7 tables, Accepted to iSAI-NLP 2025
【6】Prediction of Herd Life in Dairy Cows Using Multi-Head Attention Transformers
标题:使用多头注意力转换器预测奶牛的牛群寿命
链接:https://arxiv.org/abs/2511.21034
作者:Mahdi Saki,Justin Lipman
【7】On the Role of Hidden States of Modern Hopfield Network in Transformer
标题:现代Hopfield网络隐藏状态在Transformer中的作用
链接:https://arxiv.org/abs/2511.20698
作者:Tsubasa Masumura,Masato Taki
备注:NeurIPS 2025 accepted
GAN|对抗|攻击|生成相关(5篇)
【1】Matrix: Peer-to-Peer Multi-Agent Synthetic Data Generation Framework
标题:Matrix:点对点多代理合成数据生成框架
链接:https://arxiv.org/abs/2511.21686
作者:Dong Wang,Yang Li,Ansong Ni,Ching-Feng Yeh,Youssef Emad,Xinjie Lei,Liam Robbins,Karthik Padthe,Hu Xu,Xian Li,Asli Celikyilmaz,Ramya Raghavendra,Lifei Huang,Carole-Jean Wu,Shang-Wen Li
【2】TSGM: Regular and Irregular Time-series Generation using Score-based Generative Models
标题:TSGM:使用基于分数的生成模型生成规则和不规则时间序列
链接:https://arxiv.org/abs/2511.21335
作者:Haksoo Lim,Jaehoon Lee,Sewon Park,Minjung Kim,Noseong Park
【3】From Diffusion to One-Step Generation: A Comparative Study of Flow-Based Models with Application to Image Inpainting
标题:从扩散到一步生成:基于流的模型及其在图像修复中的应用的比较研究
链接:https://arxiv.org/abs/2511.21215
作者:Umang Agarwal,Rudraksh Sangore,Sumit Laddha
【4】Probabilistic Wildfire Spread Prediction Using an Autoregressive Conditional Generative Adversarial Network
标题:使用自回归条件生成对抗网络的概率野火蔓延预测
链接:https://arxiv.org/abs/2511.21019
作者:Taehoon Kang,Taeyong Kim
备注:22 pages, 15 figures, Submitted to Journal of Environmental Management
【5】Dataset Poisoning Attacks on Behavioral Cloning Policies
标题:对行为克隆政策的数据集中毒攻击
链接:https://arxiv.org/abs/2511.20992
作者:Akansha Kalra,Soumil Datta,Ethan Gilmore,Duc La,Guanhong Tao,Daniel S. Brown
备注:Accepted at EAI SmartSP 2025
半/弱/无/有监督|不确定性|主动学习(3篇)
【1】Beyond Accuracy: An Empirical Study of Uncertainty Estimation in Imputation
标题:超越准确性:归责中不确定性估计的实证研究
链接:https://arxiv.org/abs/2511.21607
作者:Zarin Tahia Hossain,Mostafa Milani
备注:To appear in conference proceedings
【2】Hybrid-AIRL: Enhancing Inverse Reinforcement Learning with Supervised Expert Guidance
标题:Hybrid-AIRL:用监督专家指导增强逆强化学习
链接:https://arxiv.org/abs/2511.21356
作者:Bram Silue,Santiago Amaya-Corredor,Patrick Mannion,Lander Willem,Pieter Libin
备注:Comments: 13 pages, 5 figures, 1 table. Code: https://github.com/silue-dev/hairl. Submitted to ESANN 2026
【3】Geometric Calibration and Neutral Zones for Uncertainty-Aware Multi-Class Classification
标题:不确定性多类分类的几何校准和中性区
链接:https://arxiv.org/abs/2511.20960
作者:Soumojit Das,Nairanjana Dasgupta,Prashanta Dutta
迁移|Zero/Few/One-Shot|自适应(9篇)
【1】An AI-Enabled Hybrid Cyber-Physical Framework for Adaptive Control in Smart Grids
标题:用于智能电网自适应控制的人工智能混合网络物理框架
链接:https://arxiv.org/abs/2511.21590
作者:Muhammad Siddique,Sohaib Zafar
备注:16 pages, 11 figures, IEEEaccess journal
【2】Learning When to Stop: Adaptive Latent Reasoning via Reinforcement Learning
标题:学习何时停止:通过强化学习进行自适应潜在推理
链接:https://arxiv.org/abs/2511.21581
作者:Alex Ning,Yen-Ling Kuo,Gabe Gomes
备注:13 pages, 6 figures
【3】Anomaly Detection with Adaptive and Aggressive Rejection for Contaminated Training Data
标题:对受污染的训练数据进行自适应和攻击性拒绝的异常检测
链接:https://arxiv.org/abs/2511.21378
作者:Jungi Lee,Jungkwon Kim,Chi Zhang,Kwangsun Yoo,Seok-Joo Byun
【4】MortgageLLM: Domain-Adaptive Pretraining with Residual Instruction Transfer, Alignment Tuning, and Task-Specific Routing
标题:MortgageLLM:具有剩余指令传输、对齐调整和任务特定路由的域自适应预训练
链接:https://arxiv.org/abs/2511.21101
作者:Manish Jain,Satheesh Kumar Ponnambalam,Salman Faroz,Chandrakanth Lns,Vinay Sharma
【5】FedAPA: Federated Learning with Adaptive Prototype Aggregation Toward Heterogeneous Wi-Fi CSI-based Crowd Counting
标题:FedAPA:采用自适应原型聚合的联邦学习,实现基于异类Wi-Fi CSC的人群计数
链接:https://arxiv.org/abs/2511.21048
作者:Jingtao Guo,Yuyi Mao,Ivan Wang-Hei Ho
备注:17 pages, 11 figures, this article was submitted to IEEE for possible publication
【6】RAVQ-HoloNet: Rate-Adaptive Vector-Quantized Hologram Compression
标题:RAVQ-HoloNet:速率自适应的载体量化全息压缩
链接:https://arxiv.org/abs/2511.21035
作者:Shima Rafiei,Zahra Nabizadeh Shahr Babak,Shadrokh Samavi,Shahram Shirani
【7】FANoise: Singular Value-Adaptive Noise Modulation for Robust Multimodal Representation Learning
标题:FANoise:用于鲁棒多模式表示学习的奇异值自适应噪音调制
链接:https://arxiv.org/abs/2511.20997
作者:Jiaoyang Li,Jun Fang,Tianhao Gao,Xiaohui Zhang,Zhiyuan Liu,Chao Liu,Pengzhang Liu,Qixia Jiang
备注:13 pages, 5 figures, accept to AAAI2026
【8】$Δ$-NeRF: Incremental Refinement of Neural Radiance Fields through Residual Control and Knowledge Transfer
标题:$Δ$-NeRF:通过剩余控制和知识转移对神经辐射场进行增量细化
链接:https://arxiv.org/abs/2511.20804
作者:Kriti Ghosh,Devjyoti Chakraborty,Lakshmish Ramaswamy,Suchendra M. Bhandarkar,In Kee Kim,Nancy O'Hare,Deepak Mishra
【9】RosettaSpeech: Zero-Shot Speech-to-Speech Translation from Monolingual Data
标题:RosettaSpeech:从单语数据进行Zero-Shot语音翻译
链接:https://arxiv.org/abs/2511.20974
作者:Zhisheng Zheng,Xiaohang Sun,Tuan Dinh,Abhishek Yanamandra,Abhinav Jain,Zhu Liu,Sunil Hadap,Vimal Bhat,Manoj Aggarwal,Gerard Medioni,David Harwath
备注:Work in progress
强化学习(5篇)
【1】Predictive Safety Shield for Dyna-Q Reinforcement Learning
标题:Dyna-Q强化学习的预测安全盾
链接:https://arxiv.org/abs/2511.21531
作者:Jin Pin,Krasowski Hanna,Vanneaux Elena
【2】Staggered Environment Resets Improve Massively Parallel On-Policy Reinforcement Learning
标题:交错环境重置改善大规模并行的政策强化学习
链接:https://arxiv.org/abs/2511.21011
作者:Sid Bharthulwar,Stone Tao,Hao Su
【3】Independent policy gradient-based reinforcement learning for economic and reliable energy management of multi-microgrid systems
标题:基于独立政策梯度的强化学习,实现多微电网系统经济可靠的能源管理
链接:https://arxiv.org/abs/2511.20977
【4】Exploring Time-Step Size in Reinforcement Learning for Sepsis Treatment
标题:探索脓毒症治疗的强化学习中的时间步大小
链接:https://arxiv.org/abs/2511.20913
作者:Yingchuan Sun,Shengpu Tang
【5】Cryptocurrency Portfolio Management with Reinforcement Learning: Soft Actor--Critic and Deep Deterministic Policy Gradient Algorithms
标题:采用强化学习的加密货币投资组合管理:软参与者--批判性和深度确定性政策梯度算法
链接:https://arxiv.org/abs/2511.20678
元学习(2篇)
【1】Lost in Time? A Meta-Learning Framework for Time-Shift-Tolerant Physiological Signal Transformation
标题:迷失在时间中?耐时移生理信号转换的元学习框架
链接:https://arxiv.org/abs/2511.21500
作者:Qian Hong,Cheng Bian,Xiao Zhou,Xiaoyu Li,Yelei Li,Zijing Zeng
备注:The 40th Annual AAAI Conference on Artificial Intelligence (AAAI 26)
【2】MNM : Multi-level Neuroimaging Meta-analysis with Hyperbolic Brain-Text Representations
标题:MNU:具有双曲脑文本表示的多水平神经影像荟萃分析
链接:https://arxiv.org/abs/2511.21092
作者:Seunghun Baek,Jaejin Lee,Jaeyoon Sim,Minjae Jeong,Won Hwa Kim
备注:MICCAI 2025 (Provisional Accept; top ~9%)
分层学习(1篇)
【1】Learning Cell-Aware Hierarchical Multi-Modal Representations for Robust Molecular Modeling
标题:学习细胞感知的分层多模式表示以实现稳健的分子建模
链接:https://arxiv.org/abs/2511.21120
作者:Mengran Li,Zelin Zang,Wenbin Xing,Junzhou Chen,Ronghui Zhang,Jiebo Luo,Stan Z. Li
备注:Accepted to AAAI 2026 (Oral)
医学相关(1篇)
【1】Machine Learning Approaches to Clinical Risk Prediction: Multi-Scale Temporal Alignment in Electronic Health Records
标题:临床风险预测的机器学习方法:电子健康记录中的多尺度时间对齐
链接:https://arxiv.org/abs/2511.21561
作者:Wei-Chen Chang,Lu Dai,Ting Xu
备注:5 pages, 3 figures
蒸馏|知识提取(3篇)
【1】BanglaASTE: A Novel Framework for Aspect-Sentiment-Opinion Extraction in Bangla E-commerce Reviews Using Ensemble Deep Learning
标题:BanglaASTE:一个使用Ensemble深度学习的孟加拉电子商务评论中的情感-情绪-意见提取的新框架
链接:https://arxiv.org/abs/2511.21381
作者:Ariful Islam,Md Rifat Hossen,Abir Ahmed,B M Taslimul Haque
备注:Presented at the 2025 IEEE International Conference on Signal Processing, Information, Communication and Systems (SPICSCON), November 21-22, 2025, University of Rajshahi, Bangladesh. 6 pages, ensemble deep learning, 3,345 annotated Bangla product reviews
【2】Foundry: Distilling 3D Foundation Models for the Edge
标题:Foundry:为Edge提取3D基础模型
链接:https://arxiv.org/abs/2511.20721
作者:Guillaume Letellier,Siddharth Srivastava,Frédéric Jurie,Gaurav Sharma
【3】Post-Pruning Accuracy Recovery via Data-Free Knowledge Distillation
标题:基于无数据知识蒸馏的剪枝后精度恢复
链接:https://arxiv.org/abs/2511.20702
作者:Chinmay Tripurwar,Utkarsh Maurya,Dishant
推荐(1篇)
【1】A Probabilistic Framework for Temporal Distribution Generalization in Industry-Scale Recommender Systems
标题:行业规模推荐系统中时间分布概括的概率框架
链接:https://arxiv.org/abs/2511.21032
作者:Yuxuan Zhu,Cong Fu,Yabo Ni,Anxiang Zeng,Yuan Fang
聚类(1篇)
【1】Interpretable Fair Clustering
标题:可解释的公平集群
链接:https://arxiv.org/abs/2511.21109
作者:Mudi Jiang,Jiahui Zhou,Xinying Liu,Zengyou He,Zhikui Chen
超分辨率|去噪|去模糊|去雾(1篇)
【1】Sawtooth Sampling for Time Series Denoising Diffusion Implicit Models
标题:时间序列去噪扩散隐式模型的锯齿抽样
链接:https://arxiv.org/abs/2511.21320
作者:Heiko Oppel,Andreas Spilz,Michael Munz
自动驾驶|车辆|车道检测等(1篇)
【1】DeeAD: Dynamic Early Exit of Vision-Language Action for Efficient Autonomous Driving
标题:DeeAD:动态提前退出视觉语言动作以实现高效自动驾驶
链接:https://arxiv.org/abs/2511.20720
作者:Haibo HU,Lianming Huang,Nan Guan,Chun Jason Xue
点云|SLAM|雷达|激光|深度RGBD相关(2篇)
【1】MODEST: Multi-Optics Depth-of-Field Stereo Dataset
标题:MODEST:多光学景深立体数据集
链接:https://arxiv.org/abs/2511.20853
作者:Nisarg K. Trivedi,Vinayak A. Belludi,Li-Yun Wang,Pardis Taghavi,Dante Lok
【2】Accelerating Sparse Convolutions in Voxel-Based Point Cloud Networks
标题:加速基于体素的点云网络中的稀疏卷积
链接:https://arxiv.org/abs/2511.20834
作者:Dionysios Adamopoulos,Anastasia Poulopoulou,Georgios Goumas,Christina Giannoula
联邦学习|隐私保护|加密(2篇)
【1】Privacy in Federated Learning with Spiking Neural Networks
标题:使用尖峰神经网络的联邦学习中的隐私
链接:https://arxiv.org/abs/2511.21181
作者:Dogukan Aksu,Jesus Martinez del Rincon,Ihsen Alouani
【2】Trustless Federated Learning at Edge-Scale: A Compositional Architecture for Decentralized, Verifiable, and Incentive-Aligned Coordination
标题:边缘规模的无可信联邦学习:一种用于去中心化、可验证和激励一致协调的组合架构
链接:https://arxiv.org/abs/2511.21118
作者
:Pius Onobhayedo,Paul Osemudiame Oamen
推理|分析|理解|解释(9篇)
【1】IntAttention: A Fully Integer Attention Pipeline for Efficient Edge Inference
标题:IntAttention:一个完全可调的注意力管道,用于高效的边缘推理
链接:https://arxiv.org/abs/2511.21513
作者:Wanli Zhong,Haibo Feng,Zirui Zhou,Hanyang Peng,Shiqi Yu
【2】Semantic Superiority vs. Forensic Efficiency: A Comparative Analysis of Deep Learning and Psycholinguistics for Business Email Compromise Detection
标题:语义优势与取证效率:用于商业电子邮件妥协检测的深度学习和心理语言学的比较分析
链接:https://arxiv.org/abs/2511.20944
作者:Yaw Osei Adjei
备注:8 pages, 12 figures, 7 tables
【3】Guaranteed Optimal Compositional Explanations for Neurons
标题:保证神经元的最佳组成修复
链接:https://arxiv.org/abs/2511.20934
作者:Biagio La Rosa,Leilani H. Gilpin
备注:41 pages, 10 figures
【4】Open Vocabulary Compositional Explanations for Neuron Alignment
标题:神经元对齐的开放词汇组成解释
链接:https://arxiv.org/abs/2511.20931
作者:Biagio La Rosa,Leilani H. Gilpin
备注:47 pages, 11 figures
【5】SPHINX: A Synthetic Environment for Visual Perception and Reasoning
标题:SPHINX:视觉感知和推理的合成环境
链接:https://arxiv.org/abs/2511.20814
作者:Md Tanvirul Alam,Saksham Aggarwal,Justin Yang Chae,Nidhi Rastogi
【6】Cross Domain Evaluation of Multimodal Chain-of-Thought Reasoning of different datasets into the Amazon CoT Framework
标题:多模态思维链推理的跨域评估将不同数据集整合到Amazon CoT框架中
链接:https://arxiv.org/abs/2511.20701
作者:Nitya Tiwari,Parv Maheshwari,Vidisha Agarwal
【7】Reasoning With a Star: A Heliophysics Dataset and Benchmark for Agentic Scientific Reasoning
标题:与恒星推理:太阳物理学数据集和统计科学推理基准
链接:https://arxiv.org/abs/2511.20694
作者:Kevin Lee,Russell Spiewak,James Walsh
备注:Accepted at NeurIPS 2025 Machine Learning and the Physical Sciences (ML4PS) Workshop. Dataset: https://huggingface.co/datasets/SpaceML/ReasoningWithAStar
【8】Maxitive Donsker-Varadhan Formulation for Possibilistic Variational Inference
标题:可能性变分推理的最大Donsker-Varadhan公式
链接:https://arxiv.org/abs/2511.21223
作者:Jasraj Singh,Shelvia Wongso,Jeremie Houssineau,Badr-Eddine Chérief-Abdellatif
【9】Nonconvex Penalized LAD Estimation in Partial Linear Models with DNNs: Asymptotic Analysis and Proximal Algorithms
标题:含DNN的部分线性模型中的非凸罚LDA估计:渐进分析和逼近算法
链接:https://arxiv.org/abs/2511.21115
作者:Lechen Feng,Haoran Li,Lucky Li,Xingqiu Zhao
检测相关(2篇)
【1】ChatGpt Content detection: A new approach using xlm-roberta alignment
标题:ChatGpt内容检测:使用xlm-roberta对齐的新方法
链接:https://arxiv.org/abs/2511.21009
作者:Md Tasnin Tanvir,Dr Santanu Kumar Dash,Ishan Shahnan,Nafis Fuad,Tanvir Rahman,Abdullah Al Faisal,Asadullah Al Mamun
【2】Wavefront-Constrained Passive Obscured Object Detection
标题:波阵面约束的被动隐形物体检测
链接:https://arxiv.org/abs/2511.20991
作者:Zhiwen Zheng,Yiwei Ouyang,Zhao Huang,Tao Zhang,Xiaoshuai Zhang,Huiyu Zhou,Wenwen Tang,Shaowei Jiang,Jin Liu,Xingru Huang
分类|识别(6篇)
【1】Computing Strategic Responses to Non-Linear Classifiers
标题:计算对非线性分类器的战略响应
链接:https://arxiv.org/abs/2511.21560
作者:Jack Geary,Boyan Gao,Henry Gouk
【2】MMA: A Momentum Mamba Architecture for Human Activity Recognition with Inertial Sensors
标题:MMA:用于使用惯性传感器识别人类活动的动量曼巴架构
链接:https://arxiv.org/abs/2511.21550
作者:Thai-Khanh Nguyen,Uyen Vo,Tan M. Nguyen,Thieu N. Vo,Trung-Hieu Le,Cuong Pham
备注:14 pages, 5 pages
【3】Ensemble Performance Through the Lens of Linear Independence of Classifier Votes in Data Streams
标题:从数据流中分类器投票的线性独立性的角度提高性能
链接:https://arxiv.org/abs/2511.21465
作者:Enes Bektas,Fazli Can
备注:14 pages, 3 figures, 5 tables
【4】Enhancing Burmese News Classification with Kolmogorov-Arnold Network Head Fine-tuning
标题:基于Kolmogorov-Arnold网络头微调的缅甸新闻分类
链接:https://arxiv.org/abs/2511.21081
作者:Thura Aung,Eaint Kay Khaing Kyaw,Ye Kyaw Thu,Thazin Myint Oo,Thepchai Supnithi
备注:6 pages, 2 figures, 4 tables, Accepted to iSAI-NLP 2025
【5】CNN-LSTM Hybrid Architecture for Over-the-Air Automatic Modulation Classification Using SDR
标题:使用SDR进行空中自动调制分类的CNN-LSTM混合架构
链接:https://arxiv.org/abs/2511.21040
作者:Dinanath Padhya,Krishna Acharya,Bipul Kumar Dahal,Dinesh Baniya Kshatri
备注:8 Pages, 10 figures, 2 Tables, Accepted in Journal (Journal of Innovations in Engineering Education), Issue is not Published Yet
【6】CHiQPM: Calibrated Hierarchical Interpretable Image Classification
标题:CHiQPM:校准的分层可解释图像分类
链接:https://arxiv.org/abs/2511.20779
作者:Thomas Norrenbrock,Timo Kaiser,Sovan Biswas,Neslihan Kose,Ramesh Manuvinakurike,Bodo Rosenhahn
备注:Accepted to NeurIPS 2025
表征(2篇)
【1】Odin: Oriented Dual-module Integration for Text-rich Network Representation Learning
标题:Odin:面向双模块集成,用于丰富文本的网络表示学习
链接:https://arxiv.org/abs/2511.21416
作者:Kaifeng Hong,Yinglong Zhang,Xiaoying Hong,Xuewen Xia,Xing Xu
备注:32 pages, 2 figures
【2】BRIDGE: Building Representations In Domain Guided Program Verification
标题:BRIDGE:在领域引导的程序验证中构建表示
链接:https://arxiv.org/abs/2511.21104
作者:Robert Joseph George,Carson Eisenach,Udaya Ghai,Dominique Perrault-Joncas,Anima Anandkumar,Dean Foster
备注:Approx. 31 pages including appendices, 11 figures, 4 tables. Empirical study of LLM-based verified program synthesis in Lean4 (code, specs, and proofs)
3D|3D重建等相关(1篇)
【1】TraceGen: World Modeling in 3D Trace Space Enables Learning from Cross-Embodiment Videos
标题:TraceGen:3D痕迹空间中的世界建模支持从跨化身视频中学习
链接:https://arxiv.org/abs/2511.21690
作者:Seungjae Lee,Yoonkyo Jung,Inkook Chun,Yao-Chih Lee,Zikui Cai,Hongjia Huang,Aayush Talreja,Tan Dat Dao,Yongyuan Liang,Jia-Bin Huang,Furong Huang
优化|敛散性(3篇)
【1】Mean-Field Limits for Two-Layer Neural Networks Trained with Consensus-Based Optimization
标题:采用基于启发的优化训练的两层神经网络的平均场极限
链接:https://arxiv.org/abs/2511.21466
作者:William De Deyn,Michael Herty,Giovanni Samaey
【2】Evolved SampleWeights for Bias Mitigation: Effectiveness Depends on Optimization Objectives
标题:用于缓解偏差的改进样本权重:有效性取决于优化目标
链接:https://arxiv.org/abs/2511.20909
作者:Anil K. Saini,Jose Guadalupe Hernandez,Emily F. Wong,Debanshi Misra,Jason H. Moore
【3】ST-PPO: Stabilized Off-Policy Proximal Policy Optimization for Multi-Turn Agents Training
标题:ST-PPO:用于多回合代理训练的稳定的政策外近端政策优化
链接:https://arxiv.org/abs/2511.20718
作者:Chenliang Li,Adel Elmahdy,Alex Boyd,Zhongruo Wang,Alfredo Garcia,Parminder Bhatia,Taha Kass-Hout,Cao Xiao,Mingyi Hong
预测|估计(4篇)
【1】The Directed Prediction Change - Efficient and Trustworthy Fidelity Assessment for Local Feature Attribution Methods
标题:有向预测变化-本地特征归因方法的高效且值得信赖的保真度评估
链接:https://arxiv.org/abs/2511.21363
作者:Kevin Iselborn,David Dembinsky,Adriano Lucieri,Andreas Dengel
备注:13 pages, 10 figures, 5 tables, accepted at AAAI SECURE-AI4H workshop
【2】I-GLIDE: Input Groups for Latent Health Indicators in Degradation Estimation
标题:I-GLIDE:退化估计中潜在健康指标的输入组
链接:https://arxiv.org/abs/2511.21208
作者:Lucas Thil,Jesse Read,Rim Kaddah,Guillaume Doquet
备注:Included in the conference series: Joint European Conference on Machine Learning and Knowledge Discovery in Databases
【3】Phase-Aware Code-Aided EM Algorithm for Blind Channel Estimation in PSK-Modulated OFDM
标题:PSK调制的CDMA盲信道估计的相感知码辅助EM算法
链接:https://arxiv.org/abs/2511.21340
作者:Chin-Hung Chen,Ivana Nikoloska,Wim van Houtum,Yan Wu,Alex Alvarado
备注:preprint
【4】Estimation in high-dimensional linear regression: Post-Double-Autometrics as an alternative to Post-Double-Lasso
标题:多维线性回归中的估计:双重自动测量后作为双重套索后的替代方案
链接:https://arxiv.org/abs/2511.21257
作者:Sullivan Hué,Sébastien Laurent,Ulrich Aiounou,Emmanuel Flachaire
其他神经网络|深度学习|模型|建模(31篇)
【1】ToolOrchestra: Elevating Intelligence via Efficient Model and Tool Orchestration
标题:Tools Orchestra:通过高效的模型和工具规划提升智能
链接:https://arxiv.org/abs/2511.21689
作者:Hongjin Su,Shizhe Diao,Ximing Lu,Mingjie Liu,Jiacheng Xu,Xin Dong,Yonggan Fu,Peter Belcak,Hanrong Ye,Hongxu Yin,Yi Dong,Evelina Bakhturina,Tao Yu,Yejin Choi,Jan Kautz,Pavlo Molchanov
备注:21 pages, 6 figures
【2】DSD: A Distributed Speculative Decoding Solution for Edge-Cloud Agile Large Model Serving
标题:DSD:边缘云敏捷大型模型服务的分布式推测解码解决方案
链接:https://arxiv.org/abs/2511.21669
作者:Fengze Yu,Leshu Li,Brad McDanel,Saiqian Zhang
【3】Escaping the Verifier: Learning to Reason via Demonstrations
标题:逃离验证者:通过演示学习推理
链接:https://arxiv.org/abs/2511.21667
作者:Locke Cai,Ivan Provilkov
【4】Scale-Agnostic Kolmogorov-Arnold Geometry in Neural Networks
标题:神经网络中的规模不可知的Kolmogorov-Arnold几何
链接:https://arxiv.org/abs/2511.21626
作者:Mathew Vanherreweghe,Michael H. Freedman,Keith M. Adams
【5】Merge and Bound: Direct Manipulations on Weights for Class Incremental Learning
标题:合并与束缚:对类增量学习权重的直接操纵
链接:https://arxiv.org/abs/2511.21490
作者:Taehoon Kim,Donghwan Jang,Bohyung Han
【6】SUPN: Shallow Universal Polynomial Networks
标题:SUPN:浅泛多边网络
链接:https://arxiv.org/abs/2511.21414
作者:Zachary Morrow,Michael Penwarden,Brian Chen,Aurya Javeed,Akil Narayan,John D. Jakeman
备注:25 pages, supplementary material
【7】Best Practices for Machine Learning Experimentation in Scientific Applications
标题:科学应用中机器学习实验的最佳实践
链接:https://arxiv.org/abs/2511.21354
作者:Umberto Michelucci,Francesca Venturini
【8】Learning Multi-Order Block Structure in Higher-Order Networks
标题:在更高级网络中学习多阶块结构
链接:https://arxiv.org/abs/2511.21350
作者:Kazuki Nakajima,Yuya Sasaki,Takeaki Uno,Masaki Aida
备注:38 pages, 10 figures, and 7 tables
【9】A Physics-Informed U-net-LSTM Network for Data-Driven Seismic Response Modeling of Structures
标题:用于数据驱动结构地震响应建模的物理信息U-net-LSTM网络
链接:https://arxiv.org/abs/2511.21276
作者:Sutirtha Biswas,Kshitij Kumar Yadav
【10】Dynamic Stratified Contrastive Learning with Upstream Augmentation for MILP Branching
标题:用于MILP分支的具有上游增强的动态分层对比学习
链接:https://arxiv.org/abs/2511.21107
作者:Tongkai Lu,Shuai Ma,Chongyang Tao
备注:18 pages
【11】G-Net: A Provably Easy Construction of High-Accuracy Random Binary Neural Networks
标题:G-Net:一种可证明简单的高精度随机二元神经网络构建
链接:https://arxiv.org/abs/2511.21063
作者:Alireza Aghasi,Nicholas Marshall,Saeid Pourmand,Wyatt Whiting
【12】Estimating Ising Models in Total Variation Distance
标题:总变异距离估计伊辛模型
链接:https://arxiv.org/abs/2511.21008
作者:Constantinos Daskalakis,Vardis Kandiros,Rui Yao
【13】Readout-Side Bypass for Residual Hybrid Quantum-Classical Models
标题:剩余混合量子经典模型的读出端旁路
链接:https://arxiv.org/abs/2511.20922
作者:Guilin Zhang,Wulan Guo,Ziqi Tan,Hongyang He,Hailong Jiang
备注:5 pages, 1 figure, 6 tables
【14】Probabilistic Hash Embeddings for Online Learning of Categorical Features
标题:用于分类特征在线学习的概率散列嵌入
链接:https://arxiv.org/abs/2511.20893
作者:Aodong Li,Abishek Sankararaman,Balakrishnan Narayanaswamy
备注:AAAI 2026 Oral
【15】Test-Time Alignment of Text-to-Image Diffusion Models via Null-Text Embedding Optimisation
标题:通过空文本嵌入优化实现文本到图像扩散模型的测试时间对齐
链接:https://arxiv.org/abs/2511.20889
作者:Taehoon Kim,Henry Gouk,Timothy Hospedales
【16】A review on data fusion in multimodal learning analytics and educational data mining
标题:多模式学习分析和教育数据挖掘中的数据融合回顾
链接:https://arxiv.org/abs/2511.20871
作者:Wilson Chango,Juan A. Lara,Rebeca Cerezo,Cristóbal Romero
【17】Pre-train to Gain: Robust Learning Without Clean Labels
标题:预训练以获得收益:没有干净标签的稳健学习
链接:https://arxiv.org/abs/2511.20844
作者:David Szczecina,Nicholas Pellegrino,Paul Fieguth
备注:5 pages, 3 figures
【18】Primal: A Unified Deterministic Framework for Quasi-Orthogonal Hashing and Manifold Learning
标题:Primal:准垂直哈希和Manifold学习的统一确定性框架
链接:https://arxiv.org/abs/2511.20839
【19】Autoregressive Surrogate Modeling of the Solar Wind with Spherical Fourier Neural Operator
标题:基于球面傅里叶神经元算子的太阳风自回归代理模型
链接:https://arxiv.org/abs/2511.20830
作者:Reza Mansouri,Dustin Kempton,Pete Riley,Rafal Angryk
备注:IEEE Conference on Data Mining (ICDM 2025)
【20】Effects of Initialization Biases on Deep Neural Network Training Dynamics
标题:时间偏差对深度神经网络训练动态的影响
链接:https://arxiv.org/abs/2511.20826
作者:Nicholas Pellegrino,David Szczecina,Paul W. Fieguth
备注:5 pages, 2 figures, submitted to the 11th Annual Conference on Vision and Intelligent Systems
【21】Conformal Safety Monitoring for Flight Testing: A Case Study in Data-Driven Safety Learning
标题:飞行测试的保形安全监控:数据驱动安全学习的案例研究
链接:https://arxiv.org/abs/2511.20811
作者:Aaron O. Feldman,D. Isaiah Harp,Joseph Duncan,Mac Schwager
备注:ICRA 2025 Workshop on Robot safety under uncertainty from intangible specifications
【22】Physics Steering: Causal Control of Cross-Domain Concepts in a Physics Foundation Model
标题:物理引导:物理基础模型中跨领域概念的因果控制
链接:https://arxiv.org/abs/2511.20798
作者:Rio Alexa Fear,Payel Mukhopadhyay,Michael McCabe,Alberto Bietti,Miles Cranmer
备注:16 Pages, 9 Figures. Code available at https://github.com/DJ-Fear/walrus_steering
【23】Spatio-Temporal Trajectory Foundation Model - Recent Advances and Future Directions
标题:时空轨迹基础模型-最新进展和未来方向
链接:https://arxiv.org/abs/2511.20729
作者:Sean Bin Yang,Ying Sun,Yunyao Cheng,Yan Lin,Kristian Torp,Jilin Hu
备注:This paper has been accepted by CIKM 2025 STIntelligence Workshop
【24】Prototype-Guided Non-Exemplar Continual Learning for Cross-subject EEG Decoding
标题:用于跨学科脑电解码的原型引导非示例连续学习
链接:https://arxiv.org/abs/2511.20696
作者:Dan Li,Hye-Bin Shin,Yeon-Woo Choi
备注:4 pages, 2 figures, 14th IEEE International Winter Conference on Brain-Computer Interface Conference 2026
【25】Dual-Domain Deep Learning Method to Accelerate Local Basis Functions Computation for Reservoir Simulation in High-Contrast Porous Media
标题:双域深度学习方法加速局部基函数计算,以用于高对比度多孔媒体中的储层模拟
链接:https://arxiv.org/abs/2511.20685
【26】On Evolution-Based Models for Experimentation Under Interference
标题:基于进化的干扰实验模型
链接:https://arxiv.org/abs/2511.21675
作者:Sadegh Shirani,Mohsen Bayati
【27】Phase Transition for Stochastic Block Model with more than $\sqrt{n}$ Communities (II)
链接:https://arxiv.org/abs/2511.21526
作者:Alexandra Carpentier,Christophe Giraud,Nicolas Verzelen
【28】Differentiable Physics-Neural Models enable Learning of Non-Markovian Closures for Accelerated Coarse-Grained Physics Simulations
标题:可微物理-神经模型使加速粗粒度物理模拟的非马尔可夫闭包的学习成为可能
链接:https://arxiv.org/abs/2511.21369
作者:Tingkai Xue,Chin Chun Ooi,Zhengwei Ge,Fong Yew Leong,Hongying Li,Chang Wei Kang
【29】Data-Driven Assessment of Concrete Slab Integrity via Impact-Echo Signals and Neural Networks
标题:通过冲击回声信号和神经网络对混凝土板完整性进行数据驱动评估
链接:https://arxiv.org/abs/2511.21080
作者:Yeswanth Ravichandran,Duoduo Liao,Charan Teja Kurakula
备注:Accepted by IEEE Big Data 2025
【30】Deep Learning as a Convex Paradigm of Computation: Minimizing Circuit Size with ResNets
标题:深度学习作为计算的凸范式:使用ResNet最小化电路大小
链接:https://arxiv.org/abs/2511.20888
【31】A Set of Rules for Model Validation
标题:模型验证的一套规则
链接:https://arxiv.org/abs/2511.20711
其他(31篇)
【1】Agentic Learner with Grow-and-Refine Multimodal Semantic Memory
标题:具有成长和完善多模式语义记忆的抽象学习者
链接:https://arxiv.org/abs/2511.21678
作者:Weihao Bo,Shan Zhang,Yanpeng Sun,Jingjing Wu,Qunyi Xie,Xiao Tan,Kunbin Chen,Wei He,Xiaofan Li,Na Zhao,Jingdong Wang,Zechao Li
【2】Through the telecom lens: Are all training samples important?
标题:通过电信镜头:所有训练样本都重要吗?
链接:https://arxiv.org/abs/2511.21668
作者:Shruti Bothe,Illyyne Saffar,Aurelie Boisbunon,Hasan Farooq,Julien Forgeat,Md Moin Uddin Chowdhury
备注:8pages, 1 table, 8 figures
【3】EvilGenie: A Reward Hacking Benchmark
标题:EvilGenie:奖励黑客基准
链接:https://arxiv.org/abs/2511.21654
作者:Jonathan Gabor,Jayson Lynch,Jonathan Rosenfeld
【4】Continual Error Correction on Low-Resource Devices
标题:低资源设备上的连续错误纠正
链接:https://arxiv.org/abs/2511.21652
作者:Kirill Paramonov,Mete Ozay,Aristeidis Mystakidis,Nikolaos Tsalikidis,Dimitrios Sotos,Anastasios Drosou,Dimitrios Tzovaras,Hyunjun Kim,Kiseok Chang,Sangdok Mo,Namwoong Kim,Woojong Yoo,Jijoong Moon,Umberto Michieli
备注:ACM MMSys 2025
【5】On the Origin of Algorithmic Progress in AI
标题:论人工智能数学进步的起源
链接:https://arxiv.org/abs/2511.21622
作者:Hans Gundlach,Alex Fogelson,Jayson Lynch,Ana Trisovic,Jonathan Rosenfeld,Anmol Sandhu,Neil Thompson
【6】TAB-DRW: A DFT-based Robust Watermark for Generative Tabular Data
标题:TAB-DRW:一种基于DFT的生成式表格数据鲁棒水印
链接:https://arxiv.org/abs/2511.21600
作者:Yizhou Zhao,Xiang Li,Peter Song,Qi Long,Weijie Su
【7】A decoupled alignment kernel for peptide membrane permeability predictions
标题:肽膜渗透性预测的脱钩排列核心
链接:https://arxiv.org/abs/2511.21566
作者:Ali Amirahmadi,Gökçe Geylan,Leonardo De Maria,Farzaneh Etminani,Mattias Ohlsson,Alessandro Tibo
备注:submitted to Journal of Cheminformatics
【8】Going with the Speed of Sound: Pushing Neural Surrogates into Highly-turbulent Transonic Regimes
标题:与声速同行:将神经替代物推入高度湍流的跨音速状态
链接:https://arxiv.org/abs/2511.21474
作者:Fabian Paischer,Leo Cotteleer,Yann Dreze,Richard Kurle,Dylan Rubini,Maurits Bleeker,Tobias Kronlachner,Johannes Brandstetter
备注:NeurIPS 2025 ML4PS Workshop
【9】Controlling changes to attention logits
标题:控制注意力日志的更改
链接:https://arxiv.org/abs/2511.21377
作者:Ben Anson,Laurence Aitchison
【10】RISC-V Based TinyML Accelerator for Depthwise Separable Convolutions in Edge AI
标题:基于RISC-V的TinyML加速器,用于边缘AI中的依赖可分离卷积
链接:https://arxiv.org/abs/2511.21232
作者:Muhammed Yildirim,Ozcan Ozturk
备注:13 pages, 7 tables, 14 figures
【11】Robust Gene Prioritization via Fast-mRMR Feature Selection in high-dimensional omics data
标题:通过多维组学数据中的Fast-mRMR特征选择进行稳健的基因优先级排序
链接:https://arxiv.org/abs/2511.21211
作者:Rubén Fernández-Farelo,Jorge Paz-Ruza,Bertha Guijarro-Berdiñas,Amparo Alonso-Betanzos,Alex A. Freitas
【12】Generative Early Stage Ranking
标题:世代早期排名
链接:https://arxiv.org/abs/2511.21095
作者:Juhee Hong,Meng Liu,Shengzhi Wang,Xiaoheng Mao,Huihui Cheng,Leon Gao,Christopher Leung,Jin Zhou,Chandra Mouli Sekar,Zhao Zhu,Ruochen Liu,Tuan Trieu,Dawei Sun,Jeet Kanjani,Rui Li,Jing Qian,Xuan Cao,Minjie Fan,Mingze Gao
【13】Deceptron: Learned Local Inverses for Fast and Stable Physics Inversion
标题:Deceptron:快速稳定物理倒置的学习局部倒置
链接:https://arxiv.org/abs/2511.21076
作者:Aaditya L. Kachhadiya
备注:10 pages, 11 main figures. Accepted for poster presentation at the NeurIPS 2025 Machine Learning and the Physical Sciences Workshop
【14】Efficient Diffusion Planning with Temporal Diffusion
标题:具有时间扩散的有效扩散规划
链接:https://arxiv.org/abs/2511.21054
作者:Jiaming Guo,Rui Zhang,Zerun Li,Yunkai Gao,Shaohui Peng,Siming Lan,Xing Hu,Zidong Du,Xishan Zhang,Ling Li
备注:Accepted by the AAAI26 Conference Main Track
【15】Gated KalmaNet: A Fading Memory Layer Through Test-Time Ridge Regression
标题:门控KalmaNet:通过测试时间岭回归的衰落内存层
链接:https://arxiv.org/abs/2511.21016
作者:Liangzu Peng,Aditya Chattopadhyay,Luca Zancato,Elvis Nunez,Wei Xia,Stefano Soatto
备注:30 pages, 10 figures
【16】Operationalizing Quantized Disentanglement
标题:量化解纠缠的操作化
链接:https://arxiv.org/abs/2511.20927
作者:Vitoria Barin-Pacela,Kartik Ahuja,Simon Lacoste-Julien,Pascal Vincent
【17】Selecting Belief-State Approximations in Simulators with Latent States
标题:在具有潜在状态的模拟器中选择信念状态逼近
链接:https://arxiv.org/abs/2511.20870
【18】NOIR 2.0: Neural Signal Operated Intelligent Robots for Everyday Activities
标题:NOIR 2.0:用于日常活动的神经信号操作智能机器人
链接:https://arxiv.org/abs/2511.20848
作者:Tasha Kim,Yingke Wang,Hanvit Cho,Alex Hodges
备注:Conference on Robot Learning (CoRL 2024), CoRoboLearn
【19】Data-Driven Methods and AI in Engineering Design: A Systematic Literature Review Focusing on Challenges and Opportunities
标题:工程设计中的数据驱动方法和人工智能:关注挑战和机遇的系统性文献综述
链接:https://arxiv.org/abs/2511.20730
作者:Nehal Afifi,Christoph Wittig,Lukas Paehler,Andreas Lindenmann,Kai Wolter,Felix Leitenberger,Melih Dogru,Patric Grauberger,Tobias Düser,Albert Albers,Sven Matthiesen
【20】Gradient Descent Algorithm Survey
标题:梯度下降算法调查
链接:https://arxiv.org/abs/2511.20725
作者:Deng Fucheng,Wang Wanjie,Gong Ao,Wang Xiaoqi,Wang Fan
【21】Solving Diffusion Inverse Problems with Restart Posterior Sampling
标题:用重新开始后验采样法求解扩散反问题
链接:https://arxiv.org/abs/2511.20705
作者:Bilal Ahmed,Joseph G. Makin
【22】AssurAI: Experience with Constructing Korean Socio-cultural Datasets to Discover Potential Risks of Generative AI
标题:AssurAI:构建韩国社会文化数据集以发现生成人工智能潜在风险的经验
链接:https://arxiv.org/abs/2511.20686
作者:Chae-Gyun Lim,Seung-Ho Han,EunYoung Byun,Jeongyun Han,Soohyun Cho,Eojin Joo,Heehyeon Kim,Sieun Kim,Juhoon Lee,Hyunsoo Lee,Dongkun Lee,Jonghwan Hyeon,Yechan Hwang,Young-Jun Lee,Kyeongryul Lee,Minhyeong An,Hyunjun Ahn,Jeongwoo Son,Junho Park,Donggyu Yoon,Taehyung Kim,Jeemin Kim,Dasom Choi,Kwangyoung Lee,Hyunseung Lim,Yeohyun Jung,Jongok Hong,Sooyohn Nam,Joonyoung Park,Sungmin Na,Yubin Choi,Jeanne Choi,Yoojin Hong,Sueun Jang,Youngseok Seo,Somin Park,Seoungung Jo,Wonhye Chae,Yeeun Jo,Eunyoung Kim,Joyce Jiyoung Whang,HwaJung Hong,Joseph Seering,Uichin Lee,Juho Kim,Sunna Choi,Seokyeon Ko,Taeho Kim,Kyunghoon Kim,Myungsik Ha,So Jung Lee,Jemin Hwang,JoonHo Kwak,Ho-Jin Choi
备注:16 pages, HuggingFace: https://huggingface.co/datasets/TTA01/AssurAI
【23】Harmonic Token Projection (HTP): A Vocabulary-Free, Training-Free, Deterministic, and Reversible Embedding Methodology
标题:调和代币投影(HTP):无词汇、无训练、确定性和可逆嵌入方法
链接:https://arxiv.org/abs/2511.20665
【24】On the Periodic Orbits of the Dual Logarithmic Derivative Operator
标题:关于二元对数导子的周期轨道
链接:https://arxiv.org/abs/2511.21283
作者:Xiaohang Yu,William Knottenbelt
【25】The Spheres Dataset: Multitrack Orchestral Recordings for Music Source Separation and Information Retrieval
标题:球体数据集:用于音乐源分离和信息检索的多轨弦录音
链接:https://arxiv.org/abs/2511.21247
作者:Jaime Garcia-Martinez,David Diaz-Guerra,John Anderson,Ricardo Falcon-Perez,Pablo Cabañas-Molero,Tuomas Virtanen,Julio J. Carabias-Orti,Pedro Vera-Candeas
【26】Lattice-to-total thermal conductivity ratio: a phonon-glass electron-crystal descriptor for data-driven thermoelectric design
标题:格子与总热导率比:用于数据驱动的热电设计的音素玻璃电子晶体描述符
链接:https://arxiv.org/abs/2511.21213
作者:Yifan Sun,Zhi Li,Tetsuya Imamura,Yuji Ohishi,Chris Wolverton,Ken Kurosaki
备注:15 pages, 7 figures
【27】Even with AI, Bijection Discovery is Still Hard: The Opportunities and Challenges of OpenEvolve for Novel Bijection Construction
标题:即使有了人工智能,双射发现仍然很困难:OpenEvolve在新型双射构建中的机遇和挑战
链接:https://arxiv.org/abs/2511.20987
作者:Davis Brown,Jesse He,Helen Jenne,Henry Kvinge,Max Vargas
备注:16 pages, 3 figures. This is an extended abstract submitted to FPSAC 2026
【28】Crowdsourcing the Frontier: Advancing Hybrid Physics-ML Climate Simulation via $50,000 Kaggle Competition
标题:前沿众包:通过50,000美元的Kaggle竞赛推进混合物理学-ML气候模拟
链接:https://arxiv.org/abs/2511.20963
作者:Jerry Lin,Zeyuan Hu,Tom Beucler,Katherine Frields,Hannah Christensen,Walter Hannah,Helge Heuer,Peter Ukkonnen,Laura A. Mansfield,Tian Zheng,Liran Peng,Ritwik Gupta,Pierre Gentine,Yusef Al-Naher,Mingjiang Duan,Kyo Hattori,Weiliang Ji,Chunhan Li,Kippei Matsuda,Naoki Murakami,Shlomo Ron,Marec Serlin,Hongjian Song,Yuma Tanabe,Daisuke Yamamoto,Jianyao Zhou,Mike Pritchard
备注:Main text: 29 pages, 10 figures. SI: 47 pages, 37 figures
【29】Fusion of classical and quantum kernels enables accurate and robust two-sample tests
标题:经典核和量子核的融合实现了准确且稳健的双样本测试
链接:https://arxiv.org/abs/2511.20941
作者:Yu Terada,Yugo Ogio,Ken Arai,Hiroyuki Tezuka,Yu Tanaka
备注:11 pages, 5 figures
【30】When Features Beat Noise: A Feature Selection Technique Through Noise-Based Hypothesis Testing
标题:当特征击败噪音时:通过基于噪音的假设测试的特征选择技术
链接:https://arxiv.org/abs/2511.20851
作者:Mousam Sinha,Tirtha Sarathi Ghosh,Ridam Pal
【31】The Human Brain as a Combinatorial Complex
标题:作为组合复合体的人脑
链接:https://arxiv.org/abs/2511.20692
作者:Valentina Sánchez,Çiçek Güven,Koen Haak,Theodore Papamarkou,Gonzalo Nápoles,Marie Šafář Postma
备注:Accepted as an Extended Abstract at the NeurReps Workshop, NeurIPS 2025
机器翻译由腾讯交互翻译提供,仅供参考
点击“阅读原文”获取带摘要的学术速递