OverLayBench: A Benchmark for Layout-to-Image Generation with Dense Overlaps
机构 * UC San Diego（加州大学圣地亚哥分校） ； Lambda, Inc（Lambda公司）
Comments Accepted to NeurIPS 2025 Dataset&Benchmark Track
期刊&会议
NeurIPS
Conference on Neural Information Processing Systems · 会议 · Machine Learning
A Gradient Flow Approach to Solving Inverse Problems with Latent Diffusion Models
Comments Accepted at the 2nd Workshop on Frontiers in Probabilistic Inference: Sampling Meets Learning, 39th Conference on Neural Information Processing Systems (NeurIPS 2025)
ConViS-Bench: Estimating Video Similarity Through Semantic Concepts
机构 * University of Trento（特伦托大学） ； Fondazione Bruno Kessler (FBK)（布鲁诺·凯斯勒基金会）
Comments Accepted to NeurIPS 2025
Video Killed the Energy Budget: Characterizing the Latency and Power Regimes of Open Text-to-Video Models
机构 * Hugging Face
Comments 10 pages. Accepted as an oral presentation at the NeurIPS 2025 NextVid Workshop (San Diego, December 6, 2025)
Position: Human-Robot Interaction in Embodied Intelligence Demands a Shift From Static Privacy Controls to Dynamic Learning
Comments To be published in NeurIPS 2025 Workshop on Bridging Language, Agent, and World Models for Reasoning and Planning
The Transparent Earth: A Multimodal Foundation Model for the Earth's Subsurface
机构 * Energy and Natural Resources Security Group（能源与自然资源安全组） ； Los Alamos National Laboratory（洛斯阿拉莫斯国家实验室）
Comments Accepted at the Neurips 2025 AI4Science Workshop
Unveiling Chain of Step Reasoning for Vision-Language Models with Fine-grained Rewards
机构 * Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所） ； School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院） ； Beijing Academy of Artificial Intelligence（北京人工智能研究院）
Comments Accepted by NeurIPS 2025
Exploring Heterophily in Graph-level Tasks
机构 * Doctoral Program of Computer Science University of Helsinki（赫尔辛基大学计算机科学博士项目） ； Research Program in Systems Oncology Faculty of Medicine University of Helsinki（赫尔辛基大学医学学院系统肿瘤研究计划） ； Centre for Information Sciences and Systems Nanyang Technological University（南洋理工大学信息科学与系统中心） ； University of Montreal（蒙特利尔大学） ； Mila Quebec Artificial Intelligence Institute（魁北克人工智能研究所）
Comments Accectped by NeurIPS 2025 Workshop, New Perspectives in Advancing Graph Machine Learning (NPGML)
TriFusion-AE: Language-Guided Depth and LiDAR Fusion for Robust Point Cloud Processing
机构 * Department of Mechanical Engineering（机械工程系） ； Indian Institute of Technology Bombay（印度理工学院班加罗尔） ； Mumbai, India（孟买，印度）
Comments 39th Conference on Neural Information Processing Systems (NeurIPS 2025) Workshop
Securing the Language of Life: Inheritable Watermarks from DNA Language Models to Proteins
Comments Accepted by NeurIPS 2025
Adaptive Kernel Design for Bayesian Optimization Is a Piece of CAKE with LLMs
机构 * The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳）） ； University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校） ； University of Athens（雅典大学）
Comments Accepted as Poster at NeurIPS 2025
StableGuard: Towards Unified Copyright Protection and Tamper Localization in Latent Diffusion Models
机构 * South China University of Technology（南方科技大学） ； Singapore Management University（新加坡国立管理学院） ； Dongguan University of Technology（东莞大学）
Comments Accepted by NeurIPS 2025
HyRF: Hybrid Radiance Fields for Memory-efficient and High-quality Novel View Synthesis
Comments Accepted at NeurIPS 2025
Rethinking Evaluation of Infrared Small Target Detection
机构 * Dalian University of Technology（大连理工大学） ； Yale University（耶鲁大学） ； Nanyang Technological University（南洋理工大学）
Comments NeurIPS 2025; Evaluation Toolkit: https://github.com/lartpang/PyIRSTDMetrics; Correct a few typos
Large Language Models as End-to-end Combinatorial Optimization Solvers
机构 * Eindhoven University of Technology（埃因霍温理工大学） ； Singapore Management University（新加坡管理学院）
Journal ref The 39th Annual Conference on Neural Information Processing Systems (NeurIPS 2025)
Foresight: Adaptive Layer Reuse for Accelerated and High-Quality Text-to-Video Generation
机构 * The University of British Columbia（不列颠哥伦比亚大学） ； d-Matrix
Comments Accepted at the 39th Conference on Neural Information Processing Systems (NeurIPS), 2025
In-Context Edit: Enabling Instructional Image Editing with In-Context Generation in Large Scale Diffusion Transformer
机构 * ReLER, CCAI, Zhejiang University（研发实验室、中国人工智能学会、浙江大学） ； DBMI, HMS, Harvard University（生物医学信息研究所、哈佛医学院、哈佛大学）
Comments Accepted by NeurIPS 2025, there will be future updates for camera ready version. Code: https://github.com/River-Zhang/ICEdit
ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning
机构 * Baichuan Inc.（北川公司） ； University of Chinese Academy of Sciences（中国科学院大学） ； Tongji University（同济大学） ； The University of Edinburgh（爱丁堡大学） ； Zhejiang University（浙江大学）
Comments Accepted to NeurIPS 2025
Least squares variational inference
Comments NeurIPS 2025, 41 pages, 8 figures
Language Models Can Predict Their Own Behavior
机构 * Information Sciences Institute（信息科学研究所） ； University of Southern California（南加州大学）
Comments Presented at the Thirty-Ninth Annual Conference on Neural Information Processing Systems (2025)
SparseDiT: Token Sparsification for Efficient Diffusion Transformer
机构 * Zhejiang University（浙江大学） ； Damo Academy, Alibaba Group（阿里达摩院） ； Hupan Lab（虎斑实验室）
Comments 39th Conference on Neural Information Processing Systems (NeurIPS 2025)
DiffusionBlend: Learning 3D Image Prior through Position-aware Diffusion Score Blending for 3D Computed Tomography Reconstruction
Journal ref Neural Information Processing Systems (NeurIPS), 2024
Learning Image Priors through Patch-based Diffusion Models for Solving Inverse Problems
机构 * Department of Electrical and Computer Engineering University of Michigan（电气与计算机工程系 华盛顿大学）
Journal ref Neural Information Processing Systems (NeurIPS), 2024
