[0] Equivariant Ray Embeddings for Implicit Multi-View Depth Estimation[cs.CV] 标题：SE(3)同变射影嵌入用于隐式多视图深度估计 作者：Yinshuang Xu, Dian Chen, Katherine Liu, Sergey Zakharov, Rares Ambrus, Kostas Daniilidis, Vitor Guizilini 链接：http://arxiv.org/abs/2411.07326 备注：Accepted at NeurIPS 2024
[1] Semi-Truths: A Large-Scale Dataset of AI-Augmented Images for Evaluating Robustness of AI-Generated Image detectors[cs.CV] 标题：半真信息：用于评估AI生成图像检测器鲁棒性的大型AI增强图像数据集 作者：Anisha Pal, Julia Kruk, Mansi Phute, Manognya Bhattaram, Diyi Yang, Duen Horng Chau, Judy Hoffman 链接：http://arxiv.org/abs/2411.07472 代码：https://github.com/J-Kruk/SemiTruths 备注：Accepted at NeurIPS 2024 Track Datasets & Benchmarks Track
[2] Quantifying Knowledge Distillation Using Partial Information Decomposition[cs.CV] 标题：量化使用部分信息分解的知识蒸馏 作者：Pasan Dissanayake, Faisal Hamman, Barproda Halder, Ilia Sucholutsky, Qiuyi Zhang, Sanghamitra Dutta 链接：http://arxiv.org/abs/2411.07483 备注：Accepted at NeurIPS 2024 Machine Learning and Compression Workshop
[3] LAUREL: Learned Augmented Residual Layer[cs.CV] 标题：学习增强残差层：LAUREL 作者：Gaurav Menghani, Ravi Kumar, Sanjiv Kumar 链接：http://arxiv.org/abs/2411.07501 备注：Accepted at the 2nd Efficient Systems for Foundation Models Workshop at the International Conference on Machine Learning (ICML) 2024
[4] SoundSil-DS: Deep Denoising and Segmentation of Sound-field Images with Silhouettes[eess.IV] 标题：声音场图像轮廓辅助深度降噪与分割方法 作者：Risako Tanigawa, Kenji Ishikawa, Noboru Harada, Yasuhiro Oikawa 链接：http://arxiv.org/abs/2411.07517 代码：https://github.com/nttcslab/soundsil-ds 备注：13 pages, 12 figures, 5 tables. Accepted by WACV 2025
[5] HiCoM: Hierarchical Coherent Motion for Streamable Dynamic Scene with 3D Gaussian Splatting[cs.CV] 标题：高一级相干运动：带有3D高斯片的方法的流式动态场景 作者：Qiankun Gao, Jiarui Meng, Chengxiang Wen, Jie Chen, Jian Zhang 链接：http://arxiv.org/abs/2411.07541 代码：https://github.com/gqk/HiCoM 备注：Accepted to NeurIPS 2024; Code is avaliable at this https URL
[6] 3D Focusing-and-Matching Network for Multi-Instance Point Cloud Registration[cs.CV] 标题：三维聚焦与配准多实例点云注册网络 作者：Liyuan Zhang, Le Hui, Qi Liu, Bo Li, Yuchao Dai 链接：http://arxiv.org/abs/2411.07740 代码：https://github.com/zlynpu/3DFMNet 备注：Accepted to NeurIPS 2024
[7] Feature Fusion Transferability Aware Transformer for Unsupervised Domain Adaptation[cs.CV] 标题：特征融合迁移性意识的无监督域适应Transformer 作者：Xiaowei Yu, Zhe Huang, Zao Zhang 链接：http://arxiv.org/abs/2411.07794 备注：IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2025
[8] Diverse capability and scaling of diffusion and auto-regressive models when learning abstract rules[cs.CV] 标题：扩散模型和自回归模型在学习抽象规则时的多样性和扩展能力 作者：Binxu Wang, Jiaqi Shang, Haim Sompolinsky 链接：http://arxiv.org/abs/2411.07873 备注：12 pages, 5 figures. Accepted to NeurIPS2024 Workshop on System 2 Reasoning At Scale as long paper
自然语言处理会议: 8篇
[0] SetLexSem Challenge: Using Set Operations to Evaluate the Lexical and Semantic Robustness of Language Models[cs.CL] 标题：设置LexSem挑战：利用集合运算评估语言模型的词汇和语义鲁棒性 作者：Bardiya Akhbari, Manish Gawali, Nicholas A. Dronen 链接：http://arxiv.org/abs/2411.07336 代码：https://github.com/amazon-science/SetLexSem-Challenge 备注：10 pages, 8 figures, NeurIPS 2024 Datasets and Benchmarks track
[1] Multi-head Span-based Detector for AI-generated Fragments in Scientific Papers[cs.CL] 标题：多头部基于 spans 的检测器用于科学论文中的 AI 生成片段 作者：German Gritsai, Ildar Khabutdinov, Andrey Grabovoy 链接：http://arxiv.org/abs/2411.07343 期刊：ACL, Proceedings of the Fourth Workshop on Scholarly Document Processing (SDP 2024), 2024, 220-225
[2] Toward Optimal Search and Retrieval for RAG[cs.CL] 标题：关于RAG最优搜索与检索的研究 作者：Alexandria Leto, Cecilia Aguerrebere, Ishwar Bhati, Ted Willke, Mariano Tepper, Vy Ai Vo 链接：http://arxiv.org/abs/2411.07396 备注：Accepted to NeurIPS 2024 Workshop ATTRIB
[3] Fair Summarization: Bridging Quality and Diversity in Extractive Summaries[cs.CL] 标题：公平摘要：桥梁提取摘要中的质量和多样性 作者：Sina Bagheri Nezhad, Sayan Bandyapadhyay, Ameeta Agrawal 链接：http://arxiv.org/abs/2411.07521
备注：Accepted at Algorithmic Fairness through the Lens of Metrics and Evaluation Workshop @ NeurIPS 2024
[4] Problem-Oriented Segmentation and Retrieval: Case Study on Tutoring Conversations[cs.CL] 标题：问题导向的分割与检索：辅导对话案例研究 作者：Rose E. Wang, Pawan Wirawarn, Kenny Lam, Omar Khattab, Dorottya Demszky 链接：http://arxiv.org/abs/2411.07598 代码：https://github.com/rosewang2008/posr 备注：EMNLP 2024 Findings. Our code and dataset are open-sourced at this https URL
[5] Mitigating Bias in Queer Representation within Large Language Models: A Collaborative Agent Approach[cs.CL] 标题：缓解大型语言模型中Queer表现中的偏见：合作智能体方法 作者：Tianyi Huang (1), Arya Somasundaram (1) ((1) App-In Club) 链接：http://arxiv.org/abs/2411.07656 备注：NeurIPS 2024 Queer in AI Workshop
[6] Likelihood as a Performance Gauge for Retrieval-Augmented Generation[cs.CL] 标题：检索增强生成中的似然作为性能指标 作者：Tianyu Liu, Jirui Qi, Paul He, Arianna Bisazza, Mrinmaya Sachan, Ryan Cotterell 链接：http://arxiv.org/abs/2411.07773 代码：https://github.com/lyutyuh/poptimizer 备注：Under review at NAACL 2025. Code is available at this https URL
[7] Trustful LLMs: Customizing and Grounding Text Generation with Knowledge Bases and Dual Decoders[cs.CL] 标题：信任型大型语言模型：利用知识库和双重解码器定制和归一化文本生成 作者：Xiaofeng Zhu, Jaya Krishna Mandivarapu 链接：http://arxiv.org/abs/2411.07870 期刊：EMNLP CustomNLP4U 2024
