Robustifying Learning-Augmented Caching Efficiently without Compromising 1-Consistency
Comments Accepted to NeurIPS 2025. https://neurips.cc/virtual/2025/poster/116615
期刊&会议
NeurIPS
Conference on Neural Information Processing Systems · 会议 · Machine Learning
Motion Matters: Compact Gaussian Streaming for Free-Viewpoint Video Reconstruction
机构 * College of Applied Technology, Shenzhen University（深圳大学应用技术学院） ； College of Big Data and Internet, Shenzhen Technology University（深圳科技大学大数据与互联网学院） ； College of Electronics and Information Engineering, Shenzhen University（深圳大学电子与信息工程学院） ； Department of Computer Science, City University of Hong Kong（香港城市大学计算机科学系） ； Pengcheng Laboratory, Shenzhen（深圳鹏城实验室） ； School of Electronic and Computer Engineering, Peking University（北京大学电子与计算机工程学院）
Comments Accepted by NeurIPS 2025
Transformer Copilot: Learning from The Mistake Log in LLM Fine-tuning
机构 * University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校） ； Princeton University（普林斯顿大学）
Comments NeurIPS 2025 Spotlight
Towards Effective Federated Graph Foundation Model via Mitigating Knowledge Entanglement
机构 * Sun Yat-sen University（中山大学） ； Beijing Institute of Technology（北京理工大学） ； Shandong University（山东大学） ； Augusta University（奥古斯塔大学）
Comments Accepted by NeurIPS 2025
Enhancing the Outcome Reward-based RL Training of MLLMs with Self-Consistency Sampling
机构 * Xi’an Jiaotong University（西安交通大学） ； University of Science and Technology of China（中国科学技术大学） ； SenseTime Research（商汤科技研究院）
Comments Accepted to NeurIPS 2025 (The Thirty-Ninth Annual Conference on Neural Information Processing Systems)
Impact of Layer Norm on Memorization and Generalization in Transformers
Comments NeurIPS 2025
GraphFaaS: Serverless GNN Inference for Burst-Resilient, Real-Time Intrusion Detection
Comments Accepted by ML For Systems workshop at Neural Information Processing Systems (NeurIPS 2025)
Improving Perturbation-based Explanations by Understanding the Role of Uncertainty Calibration
机构 * Siemens AG（西门子股份公司） ； LMU Munich（慕尼黑大学） ； Munich Center for Machine Learning (MCML)（慕尼黑机器学习中心） ； Goethe University Frankfurt（法兰克福歌德大学） ； German Cancer Research Center (DKFZ)（德国癌症研究中心） ； German Cancer Consortium (DKTK)（德国癌症联合会）
Comments 39th Conference on Neural Information Processing Systems (NeurIPS 2025)
Product distribution learning with imperfect advice
机构 * Department of Computer Science University of Warwick（沃里克大学计算机科学系） ； Harvard University（哈佛大学） ； College of Computing & Data Science Nanyang Technological University（南洋理工大学计算机科学与数据科学学院）
Comments Full version (11 pages). To be published in NeurIPS 2025
Torch-Uncertainty: A Deep Learning Framework for Uncertainty Quantification
机构 * U2IS, ENSTA, Institut Polytechnique de Paris（U2IS、ENSTA、巴黎理工学院）
Comments NeurIPS 2025 Spotlight
Towards Leveraging Sequential Structure in Animal Vocalizations
机构 * Idiap Research Institute（IDiap研究机构） ； Ecole Polytechnique Fédérale de Lausanne（洛桑联邦理工学院）
Comments Accepted at NeurIPS workshop (AI for Non-Human Animal Communication)
RobIA: Robust Instance-aware Continual Test-time Adaptation for Deep Stereo
机构 * Ewha Womans University（成均馆大学） ； Soongsil University（顺天大学）
Comments Accepted by Neural Information Processing Systems (NeurIPS) 2025
Opinion: Towards Unified Expressive Policy Optimization for Robust Robot Learning
机构 * Eastern Institute of Technology（东部技术研究所） ； University of Nottingham（诺丁汉大学） ； SIMTech, Agency for Science, Technology and Research (A*STAR)（SIMTech，科技研究局（A*STAR）） ； Southern University of Science and Technology（南方科技大学）
Comments Accepted by NeurIPS 2025 Workshop on Embodied World Models for Decision Making
VLF-MSC: Vision-Language Feature-Based Multimodal Semantic Communication System
Comments To appear in the AI4NextG Workshop at NeurIPS 2025
From Static Structures to Ensembles: Studying and Harnessing Protein Structure Tokenization
机构 * International Digital Economy Academy Shenzhen, China（国际数字经济学院深圳）
Comments NeurIPS 2025 AI for Science Workshop
AffordBot: 3D Fine-grained Embodied Reasoning via Multimodal Large Language Models
机构 * University of Science and Technology of China（科学技术大学） ； Singapore University of Technology and Design（新加坡科技设计大学） ； Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））
Comments NeurIPS 2025
MVU-Eval: Towards Multi-Video Understanding Evaluation for Multimodal LLMs
机构 * Nanjing University（南京大学） ； CASIA（中国科学院自动化研究所） ； Kuaishou Technology（快手科技） ； M-A-P
Journal ref The Thirty-Ninth Annual Conference on Neural Information Processing Systems (NeurIPS 2025)
Quantifying Climate Policy Action and Its Links to Development Outcomes: A Cross-National Data-Driven Analysis
机构 * School of Government University of Birmingham（政府学院伯明翰大学）
Comments This paper/proposal has been accepted as a poster in the NeurIPS 2025
Retrieval-Augmented Generation for Reliable Interpretation of Radio Regulations
机构 * KAUST（卡斯泰尔大学）
Comments 12 pages, 7 figures, AI4NextG @ NeurIPS 2025
Cameras as Relative Positional Encoding
机构 * UC Berkeley（伯克利大学） ； NVIDIA（NVIDIA公司） ； HKU（香港大学）
Comments Project Page: https://www.liruilong.cn/prope/
Journal ref NeurIPS 2025
Generalized Linear Mode Connectivity for Transformers
Comments Accepted to NeurIPS 2025 (Oral)
Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning
机构 * Qwen Team, Alibaba Inc.（通义团队，阿里巴巴公司） ； LeapLab, Tsinghua University（清华大学跃实验室）
Comments Accepted to NeurIPS 2025. 25 pages, 17 figures, 2 tables
R1-Compress: Long Chain-of-Thought Compression via Chunk Compression and Search
Comments Accepted by NeurIPS FoRLM Workshop
Constructing an Optimal Behavior Basis for the Option Keyboard
机构 * Institute of Informatics Federal University of Rio Grande do Sul（里约格朗德杜斯尔市联邦大学信息学院） ； Federal University of Rio Grande do Sul（里约格朗德杜斯尔市联邦大学） ； Google DeepMind（谷歌DeepMind） ； University of Massachusetts（马萨诸塞大学）
Comments To appear in the Proceedings of the Thirty-ninth Conference on Neural Information Processing Systems (NeurIPS), 2025
Matryoshka Pilot: Learning to Drive Black-Box LLMs with LLMs
机构 * Georgia Institute of Technology（佐治亚理工学院） ； Precur AI ； Google DeepMind（谷歌DeepMind）
Comments Accepted by NeurIPS 2025
Federated Behavioural Planes: Explaining the Evolution of Client Behaviour in Federated Learning
机构 * Università della Svizzera italiana（瑞士大学） ； INRAE Paris（巴黎国家农业研究院）
Comments [v3] Pre-print of the paper accepted to NeurIPS 2024 (30 pages)
Distribution Learning Meets Graph Structure Sampling
机构 * University of Warwick（沃里克大学） ； IIT Kanpur（印度理工学院坎普尔分校） ； National University of Singapore（新加坡国立大学） ； Centre for Quantum Technologies（量子技术中心） ； University of Nebraska-Lincoln（内布拉斯加大学林肯分校）
Comments Full version (50 pages, 2 figures). Shortened abstract as per arXiv criteria. To be published in NeurIPS 2025
Neural Correlates of Language Models Are Specific to Human Language
机构 * Department of Linguistics University of California, Berkeley（语言学系加州大学伯克利分校）
Comments To be presented at NeurIPS 2025 Workshops
Automated algorithm design via Nevanlinna-Pick interpolation
Comments Accepted to DynaFront Workshop at NeurIPS 2025
Succeed or Learn Slowly: Sample Efficient Off-Policy Reinforcement Learning for Mobile App Control
机构 * Huawei Noah’s Ark Lab（华为诺亚实验室） ； University College London（伦敦大学学院）
Comments NeurIPS 2025
