NeurIPS

CORE: Constraint-Aware One-Step Reinforcement Learning for Simulation-Guided Neural Network Accelerator Design

Yifeng Xiao, Yurong Xu, Ning Yan, Masood Mortazavi, Pierluigi Nuzzo

机构 * University of California, Berkeley（加州大学伯克利分校） ； Futurewei Technologies（未来科技） 纠错

Comments Preprint. 10 pages + appendix. Submitted to NeurIPS 2025

AERO: A Redirection-Based Optimization Framework Inspired by Judo for Robust Probabilistic Forecasting

Karthikeyan Vaiapury

机构 * TCS Research and Innovation（TCS研究与创新） 纠错

Comments 15 pages, 1 figure, submitted to NeurIPS 2025 (preprint version)

TRUST -- Transformer-Driven U-Net for Sparse Target Recovery

Di An, Dylan Poppert, Jiayue Li, Mark Foster, Trac D. Tran

Comments 10 pages, 5 figures. Under review at NeurIPS 2025

Quotient Network -- A Network Similar to ResNet but Learning Quotients

Peng Hui, Jiamuyang Zhao, Changxin Li, Qingzhen Zhu

机构 * School of Agricultural Engineering（农业工程学院） ； Jiangsu University（江苏大学） ； School of Software Engineering（软件学院） ； Beihang University（北京航空航天大学） 纠错

Comments This manuscript is the original version submitted to NeurIPS 2024, which was later revised and published as "Quotient Network: A Network Similar to ResNet but Learning Quotients" in Algorithms 2024, 17(11), 521 (https://doi.org/10.3390/a17110521). Please cite the journal version when referring to this work

Journal ref Algorithms 2024, 17(11), 521

Neural Conditional Probability for Uncertainty Quantification

Vladimir R. Kostic, Karim Lounici, Gregoire Pacreau, Pietro Novelli, Giacomo Turri, Massimiliano Pontil

机构 * CSML, Istituto Italiano di Tecnologia（CSML，意大利技术研究院） ； University of Novi Sad（诺维萨大学） ； CMAP-Ecole Polytechnique（CMAP-巴黎高等学院） ； AI Centre, University College London（伦敦大学学院人工智能中心） 纠错

Comments Advances in Neural Information Processing Systems (NeurIPS) 2024

Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution

Meysam Alizadeh, Zeynab Samei, Daria Stetsenko, Fabrizio Gilardi

Comments 25 pages, 18 figures, NeurIPS formatting style

Probabilistic Forecasting for Building Energy Systems using Time-Series Foundation Models

Young Jin Park, Francois Germain, Jing Liu, Ye Wang, Toshiaki Koike-Akino, Gordon Wichern, Navid Azizan, Christopher R. Laughman, Ankush Chakrabarty

机构 * IEEE 纠错

Comments Preliminary version appeared in NeurIPS TSALM Workshop: https://neurips.cc/virtual/2024/103019

Quantifying First-Order Markov Violations in Noisy Reinforcement Learning: A Causal Discovery Approach

Naveen Mysore

Comments Under review for Neural Information Processing Systems 2025

Towards Data Governance of Frontier AI Models

Jason Hausenloy, Duncan McClements, Madhavendra Thakur

Comments Published at the NeurIPS 2024 Workshop on Regulatable ML

An Adversarial Perspective on Machine Unlearning for AI Safety

Jakub Łucki, Boyi Wei, Yangsibo Huang, Peter Henderson, Florian Tramèr, Javier Rando

机构 * ETH Zurich（苏黎世联邦理工学院） ； Princeton University（普林斯顿大学） 纠错

Comments Published in Transactions on Machine Learning Research (TMLR); Best technical paper at Neurips 2024 SoLaR workshop

Wait, that's not an option: LLMs Robustness with Incorrect Multiple-Choice Options

Gracjan Góral, Emilia Wiśnios, Piotr Sankowski, Paweł Budzianowski

机构 * University of Warsaw（华沙大学） ； Institute of Mathematics, Polish Academy of Sciences（波兰科学院数学研究所） ； MIM Solutions（MIM解决方案） ； K-Scale Labs（K-Scale实验室） ； IDEAS NCBR ； IDEAS Research Institute（IDEAS研究学院） 纠错

Comments Accepted for ACL 2025 Main Conference and NeurIPS 2024 FM-EduAssess Workshop

Connectivity Shapes Implicit Regularization in Matrix Factorization Models for Matrix Completion

Zhiwei Bai, Jiajie Zhao, Yaoyu Zhang

Comments 34 pages

Journal ref The Thirty-eighth Annual Conference on Neural Information Processing Systems (NeurIPS 2024)

An Adaptive Approach for Infinitely Many-armed Bandits under Generalized Rotting Constraints

Jung-hun Kim, Milan Vojnovic, Se-Young Yun

机构 * Seoul National University（首尔国立大学） ； London School of Economics（伦敦经济学院） ； KAIST AI（韩国科学技术院人工智能研究所） 纠错

Comments NeurIPS 2024

Open High-Resolution Satellite Imagery: The WorldStrat Dataset -- With Application to Super-Resolution

Julien Cornebise, Ivan Oršolić, Freddie Kalaitzis

机构 * University College London（伦敦大学学院） ； Why How Ltd（Why How有限公司） ； University of Oxford（牛津大学） 纠错

Comments Published in 36th Conference on Neural Information Processing Systems (NeurIPS 2022) Track on Datasets and Benchmarks

STEM-POM: Evaluating Language Models Math-Symbol Reasoning in Document Parsing

Jiaru Zou, Qing Wang, Pratyush Thakur, Nickvash Kani

机构 * University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校） 纠错

Comments ACL 2025; NeurIPS Math-AI 2024; Code and Data: https://github.com/jiaruzouu/STEM-PoM

A Flexible, Equivariant Framework for Subgraph GNNs via Graph Products and Graph Coarsening

Guy Bar-Shalom, Yam Eitan, Fabrizio Frasca, Haggai Maron

机构 * Computer Science Technion - Israel Institute of Technology（技术学院-以色列理工学院计算机科学系） ； Electrical & Computer Engineering Technion - Israel Institute of Technology（技术学院-以色列理工学院电气与计算机工程系） ； NVIDIA Research（NVIDIA研究） 纠错

Comments Published at NeurIPS 2024

Scaling Offline RL via Efficient and Expressive Shortcut Models

Nicolas Espinosa-Dice, Yiyi Zhang, Yiding Chen, Bradley Guo, Owen Oertell, Gokul Swamy, Kiante Brantley, Wen Sun

机构 * Cornell University（康奈尔大学） ； Carnegie Mellon University（卡内基梅隆大学） ； Harvard University（哈佛大学） 纠错

Comments 32 pages, 5 figures. Under review at NeurIPS 2025

Surf2CT: Cascaded 3D Flow Matching Models for Torso 3D CT Synthesis from Skin Surface

Siyeop Yoon, Yujin Oh, Pengfei Jin, Sifan Song, Matthew Tivnan, Dufan Wu, Xiang Li, Quanzheng Li

机构 * Massachusetts General Hospital and Harvard Medical School（麻省总医院和哈佛医学院） 纠错

Comments Neurips 2025 submitted

Enhancing Semi-supervised Learning with Zero-shot Pseudolabels

Jichan Chung, Irene Y. Chen

机构 * University of California, Berkeley（加州大学伯克利分校） ； University of California, San Francisco（加州大学旧金山分校） 纠错

Comments Under review for Neurips 2025

KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization

Coleman Hooper, Sehoon Kim, Hiva Mohammadzadeh, Michael W. Mahoney, Yakun Sophia Shao, Kurt Keutzer, Amir Gholami

机构 * University of California, Berkeley（加州大学伯克利分校） ； ICSI ； LBNL（劳伦斯伯克利国家实验室） 纠错

Comments NeurIPS 2024

Satellite Imagery and AI: A New Era in Ocean Conservation, from Research to Deployment and Impact (Version. 2.0)

Patrick Beukema, Favyen Bastani, Yawen Zheng, Piper Wolters, Henry Herzog, Joe Ferdinando

机构 * Allen Institute for AI (Ai2)（人工智能研究所（Ai2）） 纠错

Comments 8 pages, 3 figures, NeurIPS Computational Sustainability 2023 best paper

DES-LOC: Desynced Low Communication Adaptive Optimizers for Training Foundation Models

Alex Iacob, Lorenzo Sani, Mher Safaryan, Paris Giampouras, Samuel Horváth, Andrej Jovanovic, Meghdad Kurmanji, Preslav Aleksandrov, William F. Shen, Xinchi Qiu, Nicholas D. Lane

Comments Keywords: Distributed Training, Foundation Models, Large Language Models, Optimizers, Communication Efficiency, Federated Learning, Distributed Systems, Optimization Theory, Scaling, Robustness. Preprint, under review at NeurIPS

Language Model Alignment in Multilingual Trolley Problems

Zhijing Jin, Max Kleiman-Weiner, Giorgio Piatti, Sydney Levine, Jiarui Liu, Fernando Gonzalez, Francesco Ortu, András Strausz, Mrinmaya Sachan, Rada Mihalcea, Yejin Choi, Bernhard Schölkopf

机构 * Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所） ； ETH Zürich（苏黎世联邦理工学院） ； University of Toronto（多伦多大学） ； University of Washington（华盛顿大学） ； Allen Institute for AI (AI2)（人工智能研究所） ； Carnegie Mellon University（卡内基梅隆大学） ； University of Trieste（特里斯坦大学） ； University of Michigan（密歇根大学） 纠错

Comments ICLR 2025 Spotlight, Best Paper @ NeurIPS 2024 Workshop on Pluralistic Alignment

Edit Distance Robust Watermarks via Indexing Pseudorandom Codes

Noah Golowich, Ankur Moitra

机构 * MIT（麻省理工学院） 纠错

Comments Appeared in NeurIPS 2024

A Decision-Language Model (DLM) for Dynamic Restless Multi-Armed Bandit Tasks in Public Health

Nikhil Behari, Edwin Zhang, Yunfan Zhao, Aparna Taneja, Dheeraj Nagaraj, Milind Tambe

机构 * MIT（麻省理工学院） ； Harvard University（哈佛大学） ； GE Healthcare（通用电气医疗） ； Google（谷歌） 纠错

Journal ref Advances in Neural Information Processing Systems 37 (NeurIPS 2024)

Unpaired Image-to-Image Translation for Segmentation and Signal Unmixing

Nikola Andrejic, Milica Spasic, Igor Mihajlovic, Petra Milosavljevic, Djordje Pavlovic, Filip Milisavljevic, Uros Milivojevic, Danilo Delibasic, Ivana Mikic, Sinisa Todorovic

机构 * Diffine LLC（Diffine公司） 纠错

Comments submitted to NeurIPs 2025

Machine Theory of Mind and the Structure of Human Values

Paul de Font-Reaulx

机构 * Department of Philosophy University of Michigan, Ann Arbor（哲学系 密歇根大学） 纠错

Comments This paper was originally submitted and accepted to the 2023 NeurIPS MP2 Workshop

CLEVRER-Humans: Describing Physical and Causal Events the Human Way

Jiayuan Mao, Xuelin Yang, Xikun Zhang, Noah D. Goodman, Jiajun Wu

机构 * MIT（麻省理工学院） ； Stanford University（斯坦福大学） 纠错

Comments Version 3. NeurIPS 2022 (Dataset and Benchmark Track). First two authors contributed equally. Project page: https://sites.google.com/stanford.edu/clevrer-humans/home

Tensorization is a powerful but underexplored tool for compression and interpretability of neural networks

Safa Hamreras, Sukhbinder Singh, Román Orús

机构 * Donostia International Physics Center（Donostia国际物理中心） ； Multiverse Computing 纠错

Comments This article has been prepared for submission as a "Position paper" following the guidelines provided at https://neurips.cc/Conferences/2025/CallForPositionPapers

Information-theoretic Generalization Analysis for Expected Calibration Error

Futoshi Futami, Masahiro Fujisawa

Comments Accepted by the 38th Conference on Neural Information Processing Systems (NeurIPS2024), 52 pages, 6 figures