NeurIPS

UniMRSeg: Unified Modality-Relax Segmentation via Hierarchical Self-Supervised Compensation

Xiaoqi Zhao, Youwei Pang, Chenyang Yu, Lihe Zhang, Huchuan Lu, Shijian Lu, Georges El Fakhri, Xiaofeng Liu

机构 * Yale University, USA（耶鲁大学） ； Nanyang Technological University, Singapore（南洋理工大学） ； Dalian University of Technology, China（大连理工大学） 纠错

Comments Accepted by NeurIPS 2025

See&Trek: Training-Free Spatial Prompting for Multimodal Large Language Model

Pengteng Li, Pinhao Song, Wuyang Li, Weiyu Guo, Huizai Yao, Yijie Xu, Dugang Liu, Hui Xiong

机构 * HKUST(GZ)（香港科技大学（广州）） ； KU Leuven（比利时鲁文大学） ； EPFL（苏黎世联邦理工学院） ； SZU（深圳大学） 纠错

Comments Accepted by NeurIPS 2025

Inverse Optimization Latent Variable Models for Learning Costs Applied to Route Problems

Alan A. Lahoud, Erik Schaffernicht, Johannes A. Stork

机构 * Center of Applied Autonomous Sensor Systems (AASS), Örebro University（应用自主传感器系统中心（AASS），Örebro大学） ； Technology Transfer Center Kitzingen, Technical University of Applied Sciences Würzburg-Schweinfurt（基茨ingen技术转移中心，沃斯堡-施维林应用技术大学） 纠错

Comments Accepted at Neurips 2025

Efficient Pre-Training of LLMs via Topology-Aware Communication Alignment on More Than 9600 GPUs

Guoliang He, Youhe Jiang, Wencong Xiao, Kaihua Jiang, Shuguang Wang, Jun Wang, Zixian Du, Zhuo Jiang, Xinlei Zhang, Binhang Yuan, Eiko Yoneki

Comments NeurIPS 2025

Foundation Models as World Models: A Foundational Study in Text-Based GridWorlds

Remo Sasso, Michelangelo Conserva, Dominik Jeurissen, Paulo Rauber

机构 * School of Electronic Engineering and Computer Science（电子工程与计算机科学学院） 纠错

Comments 20 pages, 9 figures. Accepted for presentation at the 39th Conference on Neural Information Processing Systems (NeurIPS 2025) Workshop on Embodied World Models for Decision Making

Escaping saddle points without Lipschitz smoothness: the power of nonlinear preconditioning

Alexander Bodard, Panagiotis Patrinos

Comments Neurips 2025 (spotlight)

Hierarchical Self-Attention: Generalizing Neural Attention Mechanics to Multi-Scale Problems

Saeed Amizadeh, Sara Abdali, Yinheng Li, Kazuhito Koishida

机构 * Microsoft Redmond, WA 98052（微软红mond分校） 纠错

Comments In The Thirty-Ninth Annual Conference on Neural Information Processing Systems (NeurIPS 2025)

RGB-Only Supervised Camera Parameter Optimization in Dynamic Scenes

Fang Li, Hao Zhang, Narendra Ahuja

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

Comments NeurIPS 2025 Spotlight

GPSToken: Gaussian Parameterized Spatially-adaptive Tokenization for Image Representation and Generation

Zhengqiang Zhang, Rongyuan Wu, Lingchen Sun, Lei Zhang

机构 * The Hong Kong Polytechnic University（香港理工大学） ； OPPO Research Institute（OPPO研究院） 纠错

Comments Accepted by NIPS 2025

CLIPTTA: Robust Contrastive Vision-Language Test-Time Adaptation

Marc Lafon, Gustavo Adolfo Vargas Hakim, Clément Rambour, Christian Desrosier, Nicolas Thome

机构 * Conservatoire National des Arts et Métiers（法国国家艺术与工艺学院） ； Sorbonne Université（索邦大学） ； ETS Montreal（蒙特利尔ETS） ； Institut universitaire de France（法国国家科学研究中心） 纠错

Journal ref 39th Conference on Neural Information Processing Systems, NeurIPS 2025

Spatial Understanding from Videos: Structured Prompts Meet Simulation Data

Haoyu Zhang, Meng Liu, Zaijing Li, Haokun Wen, Weili Guan, Yaowei Wang, Liqiang Nie

机构 * Harbin Institute of Technology (Shenzhen)（哈尔滨工业大学（深圳）） ； Pengcheng Laboratory（鹏城实验室） ； Shandong Jianzhu University（山东建筑大学） 纠错

Comments Accepted by NeurIPS 2025 as a Spotlight

StreamBridge: Turning Your Offline Video Large Language Model into a Proactive Streaming Assistant

Haibo Wang, Bo Feng, Zhengfeng Lai, Mingze Xu, Shiyu Li, Weifeng Ge, Afshin Dehghan, Meng Cao, Ping Huang

机构 * Apple（苹果公司） ； Fudan University（复旦大学） 纠错

Comments Accepted by NeurIPS 2025

SPACE: SPike-Aware Consistency Enhancement for Test-Time Adaptation in Spiking Neural Networks

Xinyu Luo, Kecheng Chen, Pao-Sheng Vincent Sun, Chris Xing Tian, Arindam Basu, Haoliang Li

机构 * Department of Electrical Engineering, City University of Hong Kong（香港城市大学电子工程系） 纠错

Comments This paper has been accepted to NeurIPS 2025

Interpreting Learned Feedback Patterns in Large Language Models

Luke Marks, Amir Abdullah, Clement Neo, Rauno Arike, David Krueger, Philip Torr, Fazl Barez

机构 * Luke Marks ； Amir Abdullah ； Clement Neo ； Rauno Arike ； David Krueger ； Philip Torr ； Fazl Barez 纠错

Comments 19 pages, 8 figures. Accepted to NeurIPS 2024

Robust, Accurate Stochastic Optimization for Variational Inference

Akash Kumar Dhaka, Alejandro Catalina, Michael Riis Andersen, Måns Magnusson, Jonathan H. Huggins, Aki Vehtari

Journal ref NeurIPS 2020, 33:10961-1097

SeCodePLT: A Unified Platform for Evaluating the Security of Code GenAI

Yuzhou Nie, Zhun Wang, Yu Yang, Ruizhe Jiang, Yuheng Tang, Xander Davies, Yarin Gal, Bo Li, Wenbo Guo, Dawn Song

机构 * UC Santa Barbara（加州大学圣巴巴拉分校） ； UC Berkeley（加州大学伯克利分校） ； VirtueAI ； UIUC（伊利诺伊大学香槟分校） ； UChicago（芝加哥大学） ； University of Oxford（牛津大学） ； UK AI Safety Institute（英国人工智能安全研究所） 纠错

Comments Accepted to NeurIPS D&B track 2025