Generating Novelty in Open-World Multi-Agent Strategic Board Games
Comments 16 pages, shorter version demonstrated in NeurIPS 2020
期刊&会议
NeurIPS
Conference on Neural Information Processing Systems · 会议 · Machine Learning
Towards Fair RAG: On the Impact of Fair Ranking in Retrieval-Augmented Generation
机构 * Carnegie Mellon University（卡内基梅隆大学）
Comments ICTIR 2025 (Oral); NeurIPS 2024 AFME Workshop (Spotlight)
Model-free Posterior Sampling via Learning Rate Randomization
机构 * CMAP, École Polytechnique（École Polytechnique 的 CMAP） ； HSE University（俄罗斯高等经济大学） ； Duisburg-Essen University（杜伊斯堡- Essen 大学） ； Google DeepMind（谷歌DeepMind） ； Mohamed Bin Zayed University of AI, UAE（阿联酋人工智能大学） ； IDEMIA ； ENS Lyon（里昂高等师范学院）
Comments This revision fixed an error connected to an incorrect use of Proposition 7 inside of Lemma 4, and a misprint in Lemma 12. In the current version, we modified the martingale construction and applied the same argument as before; no results need to be modified as a result of these fixes
Journal ref Advances in Neural Information Processing Systems 36 (NeurIPS 2023)
CLUES: Collaborative High-Quality Data Selection for LLMs via Training Dynamics
机构 * University of Cambridge, UK（剑桥大学） ； Imperial College London, UK（伦敦帝国学院） ； Samsung AI Center Cambridge（三星AI中心（剑桥）） ； Flower Labs（Flower实验室） ； AIWaves
Comments NeurIPS 2024
Zeroth-Order Federated Methods for Stochastic MPECs and Nondifferentiable Nonconvex Hierarchical Optimization
Comments A preliminary version of this article has been accepted at The 37th Annual Conference on Neural Information Processing Systems (NeurIPS 2023)
A Two-Scale Complexity Measure for Deep Learning Models
机构 * Department of Mathematics, University of Trento（特伦托大学数学系） ； DSH, Bruno Kessler Fondation（DSH布鲁诺·凯斯勒基金会） ； Department of Mathematics, ETH（苏黎世联邦理工学院数学系） ； IBM Quantum, IBM Research Europe（IBM量子计算，IBM欧洲研究院）
Journal ref Proceedings of NeurIPS 2024
Rank-1 Matrix Completion with Gradient Descent and Small Random Initialization
Comments NeurIPS 2023
Storing overlapping associative memories on latent manifolds in low-rank spiking networks
机构 * Champalimaud Centre for the Unknown（查普拉米乌德未知中心） ； Champalimaud Foundation（查普拉米乌德基金会）
Comments 17 pages, 5 figures; accepted to NeurIPS 2024 Workshop on Symmetry and Geometry in Neural Representations (NeurReps 2024)
DiReCT: Diagnostic Reasoning for Clinical Notes via Large Language Models
机构 * Premium Research Institute for Human Metaverse Medicine (WPI-PRIMe)（人类元宇宙医学高级研究机构（WPI-PRIMe）） ； Osaka University（大阪大学） ； Department of Cardiology, The First Affiliated Hospital of Dalian Medical University（大连医科大学第一附属医院心内科） ； Institute of Computing Technology, Chinese Academy of Science（中国科学院计算技术研究所） ； D3 Center, Osaka University（大阪大学D3中心） ； Agency for Science, Technology and Research (A*STAR)（科技研究局（A*STAR））
Comments Accepted by NeurIPS 2024 D&B Track
Deep Support Vectors
机构 * Seoul National University（首尔国立大学）
Comments Neurips 2024
Adversarial Robustness Unhardening via Backdoor Attacks in Federated Learning
机构 * University of Michigan, Michigan, USA（密歇根大学） ； Carnegie Mellon University, Pittsburgh, Pennsylvania, USA（卡内基梅隆大学）
Comments 15 pages, 8 main pages of text, 13 figures, 5 tables. Made for a Neurips workshop on backdoor attacks - extended version
AgentStealth: Reinforcing Large Language Model for Anonymizing User-generated Text
Comments This work has been submitted to NeurIPS 2025. Under review
FrankenBot: Brain-Morphic Modular Orchestration for Robotic Manipulation with Vision-Language Models
机构 * School of Future Technology, South China University of Technology（未来技术学院，华南理工大学） ； School of Software Engineering, South China University of Technology（软件工程学院，华南理工大学） ； Shien-Ming Wu School of Intelligent Engineering, South China University of Technology（智能工程学院，华南理工大学）
Comments 15 pages, 4 figures, under review of NeurIPS
Unveiling Causal Reasoning in Large Language Models: Reality or Mirage?
机构 * Intelligent Game and Decision Lab（智能游戏与决策实验室） ； National University of Defense Technology（国防科技大学） ； University of Melbourne（墨尔本大学） ； University of Sydney（悉尼大学） ； Hong Kong Baptist University（香港 Baptist 大学）
Comments 24 pages, accepted at NeurIPS 2024
Journal ref Advances in Neural Information Processing Systems, 2024, 37: 96640-96670
The Mamba in the Llama: Distilling and Accelerating Hybrid Models
机构 * Cornell University（康奈尔大学） ； University of Geneva（日内瓦大学） ； Together AI ； Princeton University（普林斯顿大学）
Comments NeurIPS 2024. v4 updates: mention concurrent work of speculative decoding for SSM
Transferring disentangled representations: bridging the gap between synthetic and real images
机构 * MaLGa-DIBRIS, Università degli studi di Genova（马尔加-迪布里兹大学）
Comments Accepted to NeurIPS, 2024
High-dimensional Contextual Bandit Problem without Sparsity
机构 * New York University（纽约大学） ； The University of Tokyo（东京大学） ； RIKEN Center for AIP（理化学研究所AIP中心）
Journal ref Advances in Neural Information Processing Systems, 36, 49416-49427, 2023
FORTRESS: Frontier Risk Evaluation for National Security and Public Safety
机构 * Scale AI
Comments 12 pages, 7 figures, submitted to NeurIPS
SA-Solver: Stochastic Adams Solver for Fast Sampling of Diffusion Models
机构 * University of Chinese Academy of Sciences（中国科学院大学） ； Huawei Noah’s Ark Lab（华为诺亚实验室） ； Peking University（北京大学） ； Academy of Mathematics and Systems Science, Chinese Academy of Sciences（中国科学院数学与系统科学研究院）
Comments Accepted in NeurIPS 2023
T-Rex: Task-Adaptive Spatial Representation Extraction for Robotic Manipulation with Vision-Language Models
机构 * School of Software Engineering, South China University of Technology（软件工程学院，华南理工大学） ； School of Future Technology, South China University of Technology（未来技术学院，华南理工大学） ； Shien-Ming Wu School of Intelligent Engineering, South China University of Technology（智能工程学院，华南理工大学）
Comments submitted to NeurIPS 2025
AntiGrounding: Lifting Robotic Actions into VLM Representation Space for Decision Making
机构 * School of Software Engineering, South China University of Technology（软件工程学院，华南理工大学） ； School of Future Technology, South China University of Technology（未来技术学院，华南理工大学） ； Shien-Ming Wu School of Intelligent Engineering, South China University of Technology（智能工程学院，华南理工大学）
Comments submitted to NeurIPS 2025
Tangent Space Causal Inference: Leveraging Vector Fields for Causal Discovery in Dynamical Systems
机构 * Department of Electrical and Computer Engineering（电气与计算机工程系） ； Stony Brook University（石溪大学）
Comments 18 pages, 7 figures. Accepted to NeurIPS 2024
Unscrambling disease progression at scale: fast inference of event permutations with optimal transport
机构 * Sussex AI Centre Department of Informatics University of Sussex（苏塞克斯大学人工智能中心信息学院） ； Hawkes Institute Department of Computer Science University College London（霍克斯研究所计算机科学学院）
Comments Camera-ready version of paper accepted to NeurIPS 2024
SpokenWOZ: A Large-Scale Speech-Text Benchmark for Spoken Task-Oriented Dialogue Agents
机构 * DAMO Academy, Alibaba Group（阿里巴巴集团大模型研究院） ； Computer Science and Engineering Division, University of Michigan（密歇根大学计算机科学与工程系） ； Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学光明人工智能学院）
Comments NeurIPS 2023
Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack)
机构 * Centre for Quantum Software and Information（量子软件与信息中心） ； University of Technology, Sydney（悉尼技术大学）
Comments Under review for Neurips 2025
Self-Preference Bias in LLM-as-a-Judge
机构 * SB Intuitions
Comments Accepted at NeurIPS 2024 Safe Generative AI Workshop
On Learning Multi-Modal Forgery Representation for Diffusion Generated Video Detection
机构 * Shanghai Jiao Tong University（上海交通大学） ； Michigan State University（密歇根州立大学） ； Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）
Comments 10 pages, 9 figures, published in NeurIPS 2024
Sheaf Hypergraph Networks
机构 * University of Cambridge（剑桥大学） ； University of Rome, La Sapienza（罗马大学）
Comments Accepted at Neural Information Processing Systems (NeurIPS 2023)
Bridging Text and Crystal Structures: Literature-driven Contrastive Learning for Materials Science
机构 * Toyota Motor Corporation（丰田汽车公司） ； OMRON SINIC X Corporation（OMRON SINIC X公司） ； Randeft, Inc.（Randeft公司） ； The University of Osaka（大阪大学）
Comments 19 pages, 8 figures. Accepted to Machine Learning: Science and Technology (2025). Preliminary versions appeared at NeurIPS 2024 AI4Mat and CVPR 2025 MM4Mat workshops
QTIP: Quantization with Trellises and Incoherence Processing
机构 * Cornell University（康奈尔大学）
Comments NeurIPS 2024 Spotlight
