Understanding and Improving Adversarial Robustness of Neural Probabilistic Circuits
机构 * University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
Comments NeurIPS 2025 Camera Ready
期刊&会议
NeurIPS
Conference on Neural Information Processing Systems · 会议 · Machine Learning
Document Summarization with Conformal Importance Guarantees
机构 * Signal 1 AI ； Layer 6 AI
Comments NeurIPS 2025. Code is available at https://github.com/layer6ai-labs/conformal-importance-summarization
A Theory of Multi-Agent Generative Flow Networks
机构 * Huawei Technologies Canada（华为加拿大公司） ； Tianjin University（天津大学） ； Zhejiang University（浙江大学） ； Huawei Noah’s Ark Lab（华为诺亚实验室）
Comments Accepted at SPIGM Workshop NeurIPS 2025
MARS: A Malignity-Aware Backdoor Defense in Federated Learning
机构 * Faculty of Data Science, City University of Macau（澳门城市大学数据科学学院） ； School of Computing, Australian National University（澳大利亚国立大学计算机学院） ； Ant Group（蚂蚁集团） ； School of Cyber Science and Engineering, Huazhong University of Science and Technology（华中科技大学网络安全工程学院） ； School of Computer Science and Technology, Huazhong University of Science and Technology（华中科技大学计算机科学与技术学院） ； College of Computing and Data Science, Nanyang Technological University（南洋理工大学计算与数据科学学院） ； School of Information and Communication Technology, Griffith University（格里菲斯大学信息与通信技术学院）
Comments NeurIPS 2025
TempSamp-R1: Effective Temporal Sampling with Reinforcement Fine-Tuning for Video LLMs
机构 * VCIP, School of Computer Science, Nankai University（VCIP，计算机科学学院，南开大学） ； ByteDance Inc.（字节跳动公司）
Comments Accepted at NeurIPS 2025
AHA -- Predicting What Matters Next: Online Highlight Detection Without Looking Ahead
机构 * University of Southern California（南加州大学） ； DEVCOM Army Research Laboratory（陆军研究实验室）
Comments Accepted at NeurIPS 2025, 32 pages, 5 figures
Topological Feature Compression for Molecular Graph Neural Networks
Comments Accepted at Thirty-ninth Conference on Neural Information Processing Systems (NeurIPS) 2025 AI4Science Workshop
Journal ref Thirty-ninth Conference on Neural Information Processing Systems (NeurIPS) 2025 AI4Science Workshop
ReasonFlux-PRM: Trajectory-Aware PRMs for Long Chain-of-Thought Reasoning in LLMs
机构 * UIUC（伊利诺伊大学香槟分校） ； Princeton University（普林斯顿大学） ； Cornell University（康奈尔大学） ； ByteDance（字节跳动）
Comments Accepted by NeurIPS 2025. Project: https://github.com/Gen-Verse/ReasonFlux
Co-Evolving LLM Coder and Unit Tester via Reinforcement Learning
机构 * University of Chicago（芝加哥大学） ； Princeton University（普林斯顿大学） ； Peking University（北京大学） ； ByteDance Seed（字节跳动种子）
Comments NeurIPS 2025 Spotlight. Project: https://github.com/Gen-Verse/CURE
MMaDA: Multimodal Large Diffusion Language Models
机构 * Princeton University（普林斯顿大学） ； Peking University（北京大学） ； Tsinghua University（清华大学） ； ByteDance Seed（字节跳动种子）
Comments NeurIPS 2025. Project: https://github.com/Gen-Verse/MMaDA
R&D-Agent-Quant: A Multi-Agent Framework for Data-Centric Factors and Model Joint Optimization
机构 * Carnegie Mellon University（卡内基梅隆大学） ； Microsoft Research Asia（微软亚洲研究院） ； Hong Kong University of Science and Technology（香港科学与技术大学） ； University of Oxford（牛津大学）
Comments 42 pages,11figures, NeurIPS 2025
Rethinking Circuit Completeness in Language Models: AND, OR, and ADDER Gates
机构 * Hang Chen School of Computer Science and Technology Xi’an Jiaotong University（Hang Chen 计算机科学与技术学院 西安交通大学） ； Jiaying Zhu School of Computer Science and Engineering The Chinese University of Hong Kong（Jiaying Zhu 计算科学与工程学院 香港中文大学） ； Xinyu Yang School of Computer Science and Technology Xi’an Jiaotong University（Xinyu Yang 计算机科学与技术学院 西安交通大学） ； Wenya Wang School of Computer Science and Engineering Nanyang Technological University（Wenya Wang 计算科学与工程学院 新加坡国立大学）
Comments accepted by NeurIPS 2025 (poster)
HermesFlow: Seamlessly Closing the Gap in Multimodal Understanding and Generation
机构 * Peking University（北京大学） ； Tsinghua University（清华大学） ； Mila - Québec AI Institute（魁北克人工智能研究所）
Comments NeurIPS 2025. Code: https://github.com/Gen-Verse/HermesFlow
Strassen Attention, Split VC Dimension and Compositionality in Transformers
机构 * University of Chile（智利大学） ； CENIA ； IPPT PAN（波兰国家物理与天文学研究所） ； IMC UC（UC大学医学中心）
Comments Accepted at NeurIPS 2025
Hybrid Summary Statistics
机构 * Imperial College London（伦敦帝国学院） ； Tsinghua University（清华大学） ； Sorbonne Université（索邦大学） ； Center for Computational Astrophysics, Flatiron Institute（Flatiron研究所计算天体物理学中心） ； Oxford University（牛津大学）
Comments 7 pages, 4 figures. Accepted to ML4PS2024 at NeurIPS 2024. Code available at https://github.com/tlmakinen/hybridStats
Copycats: the many lives of a publicly available medical imaging dataset
机构 * IT University of Copenhagen（哥本哈根IT大学） ； University of Copenhagen（哥本哈根大学）
Comments NeurIPS 2024 Track on Datasets and Benchmarks. Please note that v1 has a different title
Spatio-Temporal Directed Graph Learning for Account Takeover Fraud Detection
Comments This paper has been accepted at NeurIPS 2025 workshop New Perspective in Graph Machine Learning (NPGML)
Uncovering Graph Reasoning in Decoder-only Transformers with Circuit Tracing
Comments Accepted by the Workshop on Efficient Reasoning, Neurips 2025
Automated Multi-Agent Workflows for RTL Design
机构 * Chandra Family Department of Electrical and Computer Engineering（查克拉家族电子与计算机工程系）
Comments Accepted: ML for Systems Workshop NeurIPS 2025
Generative Model Inversion Through the Lens of the Manifold Hypothesis
机构 * TMLR Group, Department of Computer Science, Hong Kong Baptist University（香港 Baptist 大学计算机科学系） ； Sydney AI Centre, The University of Sydney（悉尼大学人工智能中心） ； School of Computing and Information Systems, The University of Melbourne（墨尔本大学计算与信息系） ； McCombs School of Business, The University of Texas at Austin（德克萨斯大学奥斯汀分校麦科姆斯商学院）
Comments NeurIPS 2025
EndoBench: A Comprehensive Evaluation of Multi-Modal Large Language Models for Endoscopy Analysis
机构 * Chinese University of Hong Kong（中国香港大学） ； City University of Hong Kong（香港城市大学） ； University of Oxford（牛津大学） ； Shanghai AI Laboratory（上海人工智能实验室） ； The Sixth Affiliated Hospital, Sun Yat-sen University（中山大学第六附属医院）
Comments 40 pages, 22 figures; Accepted by NeurIPS 2025 Dataset and Benchmark Track
Langevin Unlearning: A New Perspective of Noisy Gradient Descent for Machine Unlearning
机构 * Department of Electrical and Computer Engineering（电气与计算机工程系） ； Georgia Institute of Technology（佐治亚理工学院） ； Department of Mathematics（数学系） ； Massachusetts Institute of Technology（麻省理工学院）
Comments NeurIPS 2024 Spotlight. Revise calculation errors
One Filters All: A Generalist Filter for State Estimation
机构 * School of Vehicle and Mobility, Tsinghua University（清华大学车辆与移动系统学院） ； College of Engineering, Peking University（北京大学工程学院） ； College of AI, Tsinghua University（清华大学人工智能学院）
Comments NeurIPS 2025
Learnable Sampler Distillation for Discrete Diffusion Models
机构 * University of Electronic Science and Technology of China（电子科学与技术大学）
Comments NeurIPS 2025
Exploration with Foundation Models: Capabilities, Limitations, and Hybrid Approaches
机构 * School of Electronic Engineering and Computer Science（电子工程与计算机科学学院）
Comments 16 pages, 7 figures. Accepted for presentation at the 39th Conference on Neural Information Processing Systems (NeurIPS 2025) Workshop on the Foundations of Reasoning in Language Models (FoRLM)
Towards Self-Supervised Foundation Models for Critical Care Time Series
机构 * David S. Hippocampus Department of Computer Science Cranberry-Lemon University（Cranberry-Lemon大学计算机科学系）
Comments Accepted to NeurIPS 2025 workshop Learning from Time Series for Health (TS4H)
LatentGuard: Controllable Latent Steering for Robust Refusal of Attacks and Reliable Response Generation
Comments 9-page NeurIPS 2025 preprint including 3 figures and 1 table, with additional appendix material. Prepared using the NeurIPS 2025 preprint template and compiled with pdfLaTeX. All references are included via the provided .bbl file. Figures are in PDF format. No external supplementary files. All necessary style files and images are included
Linear Transformers Implicitly Discover Unified Numerical Algorithms
机构 * Boston University（波士顿大学） ； University of Virginia（弗吉尼亚大学）
Comments To appear at NeurIPS 2025
Calibrated Reasoning: An Explanatory Verifier for Dynamic and Efficient Problem-Solving
机构 * Applied AI Research, Cerebras（应用人工智能研究，Cerebras）
Comments 39th Conference on Neural Information Processing Systems (NeurIPS 2025) Workshop: Efficient Reasoning
Non-Clairvoyant Scheduling with Progress Bars
Comments NeurIPS 2025
