From Pixels to Views: Learning Angular-Aware and Physics-Consistent Representations for Light Field Microscopy
机构 * University of Science and Technology of China（中国科学技术大学）
Comments Accepted by NeurIPS 2025
期刊&会议
NeurIPS
Conference on Neural Information Processing Systems · 会议 · Machine Learning
LooGLE v2: Are LLMs Ready for Real World Long Dependency Challenges?
机构 * Institute for Artificial Intelligence, Peking University（北京大学人工智能研究院） ； National Key Laboratory of General Artificial Intelligence, BIGAI（通用人工智能国家重点实验室，BIGAI） ； School of Computer Science and Technology, Beijing Institute of Technology（北京理工大学计算机科学与技术学院）
Comments NeurIPS 2025 Datasets and Benchmarks Track
Iteratively Refined Early Interaction Alignment for Subgraph Matching based Graph Retrieval
机构 * UC San Diego（加州大学圣地亚哥分校） ； IIT Bombay（印度理工学院班加罗尔）
Journal ref Neurips 2024 paper
SRSR: Enhancing Semantic Accuracy in Real-World Image Super-Resolution with Spatially Re-Focused Text-Conditioning
机构 * Amazon（亚马逊公司） ； The University of Sydney（悉尼大学） ； Australian National University（澳大利亚国立大学）
Comments Accepted at NeurIPS 2025
Multi-Modal Masked Autoencoders for Learning Image-Spectrum Associations for Galaxy Evolution and Cosmology
Comments 8 pages, 3 figures, 1 table, accepted to NeurIPS 2025 Workshop ML4PS
Semi-supervised Vertex Hunting, with Applications in Network and Text Analysis
机构 * Harvard University（哈佛大学）
Journal ref NeurIPS 2025
Random Search Neural Networks for Efficient and Expressive Graph Learning
机构 * University of Michigan（密歇根大学）
Comments NEURIPS 2025; version with full appendix
Single-Teacher View Augmentation: Boosting Knowledge Distillation via Angular Diversity
机构 * GIST（韩国科学技术院） ； POSTECH（延世大学） ； MIT CSAIL（麻省理工学院计算机科学与人工智能实验室）
Comments Accepted to NeurIPS 2025
Evaluating Multimodal Large Language Models on Core Music Perception Tasks
机构 * Department of Psychology, Music and Audio Research Laboratory（心理学系、音乐与音频研究实验室） ； Department of Electronic Engineering and Computer Science（电子工程与计算机科学系）
Comments Accepted to the NeurIPS 2025 Workshop on AI for Music (AI4Music), 16 pages, 1 figure, 3 tables
GraphTOP: Graph Topology-Oriented Prompting for Graph Neural Networks
机构 * University of Virginia（弗吉尼亚大学） ； University of Connecticut Storrs（康涅狄格大学斯特劳斯分校）
Comments Accepted by the 39 Annual Conference on Neural Information Processing Systems (NeurIPS 2025)
Benchmarking Egocentric Multimodal Goal Inference for Assistive Wearable Agents
机构 * Meta Reality Labs（Meta 现实实验室） ； Meta FAIR
Comments Accepted as a spotlight paper at the 39th Conference on Neural Information Processing Systems (NeurIPS 2025)
Extragradient Method for $(L_0, L_1)$-Lipschitz Root-finding Problems
机构 * Johns Hopkins University（约翰霍普金斯大学）
Comments Published in NeurIPS 2025, 44 pages, 6 Figures
Johnson-Lindenstrauss Lemma Beyond Euclidean Geometry
Comments Accepted to Neurips 2025
T2SMark: Balancing Robustness and Diversity in Noise-as-Watermark for Diffusion Models
机构 * University of Science and Technology of China（中国科学技术大学） ； Anhui Province Key Laboratory of Digital Security（安徽省数字安全重点实验室） ； National University of Singapore（新加坡国立大学）
Comments Accepted by NeurIPS 2025
Mapping Faithful Reasoning in Language Models
机构 * King’s College London（伦敦国王学院） ； Spotify UK（Spotify英国分公司） ； University of Oxford（牛津大学） ； Spotify Spain（Spotify西班牙分公司）
Comments 9 pages, Accepted to the Mechanistic Interpretability Workshop at NeurIPS 2025
Transformer Key-Value Memories Are Nearly as Interpretable as Sparse Autoencoders
机构 * Tohoku University（东大大学） ； RIKEN（理化学研究所） ； MBZUAI（马克斯·普朗克人工智能研究所）
Comments NeurIPS 2025
Accident Anticipation via Temporal Occurrence Prediction
机构 * School of Computer Science, Wuhan University（武汉大学计算机学院） ； Zhongguancun Academy（中关村学院） ； Didi Chuxing（滴滴出行）
Comments Accepted by NIPS 2025
LUNA: Efficient and Topology-Agnostic Foundation Model for EEG Signal Analysis
机构 * Integrated Systems Laboratory, ETH Zürich（瑞士苏黎世联邦理工学院集成系统实验室）
Comments NeurIPS camera-ready version, 27 pages, 10 figures, 13 tables
Diffusion-Driven Two-Stage Active Learning for Low-Budget Semantic Segmentation
Comments Accepted to NeurIPS 2025
OptiTree: Hierarchical Thoughts Generation with Tree Search for LLM Optimization Modeling
机构 * MoE Key Laboratory of Brain-inspired Intelligent Perception and Cognition, University of Science and Technology of China（脑启发式感知与认知联合实验室，中国科学技术大学） ； Noah’s Ark Lab, Huawei Technologies（华为诺亚实验室） ； Tianjin University（天津大学）
Comments Published at NeurIPS 2025
Towards General Modality Translation with Contrastive and Predictive Latent Diffusion Bridge
机构 * Bosch AI Center（博世人工智能中心） ； Ben-Gurion University of the Negev（巴伊兰大学） ； Technical University of Munich（慕尼黑技术大学）
Comments Accepted as a poster at NeurIPS 2025
Beyond Fertility: Analyzing STRR as a Metric for Multilingual Tokenization Evaluation
机构 * University of Alberta（阿尔伯塔大学） ； Princess Nourah Bint Abdulrahman University（努拉·阿卜杜勒拉赫曼王后大学） ； Dialpad Qatar Computing Research Institute（阿联酋迪拜计算研究所） ； Amazon AGI（亚马逊人工智能研究所）
Comments NeurIPS 2025 Workshop
One Stone with Two Birds: A Null-Text-Null Frequency-Aware Diffusion Models for Text-Guided Image Inpainting
Comments 27 pages, 11 figures, to appear at NeurIPS 2025
Retrv-R1: A Reasoning-Driven MLLM Framework for Universal and Efficient Multimodal Retrieval
机构 * City University of Hong Kong（香港城市大学） ； Tencent（腾讯） ； Zhejiang University（浙江大学）
Comments NeurIPS 2025
EuroSpeech: A Multilingual Speech Corpus
机构 * ETH Zurich（苏黎世联邦理工学院）
Comments Published in the 39th Conference on Neural Information Processing Systems (NeurIPS 2025) Track on Datasets and Benchmark
Differentiable Structure Learning and Causal Discovery for General Binary Data
Comments 30 pages, 6 figures, to appear at NeurIPS 2025
SceneWeaver: All-in-One 3D Scene Synthesis with an Extensible and Self-Reflective Agent
机构 * State Key Laboratory of General Artificial Intelligence, BIGAI（1 通用人工智能国家重点实验室、BIGAI） ； Tsinghua University（2 清华大学）
Comments Accepted by NeurIPS 2025, 26 pages
Self-Supervised Discovery of Neural Circuits in Spatially Patterned Neural Responses with Graph Neural Networks
机构 * Department of Electronic Engineering（电子工程系） ； Department of Artificial Intelligence（人工智能系） ； Hanyang University（翰阳大学）
Comments To appear in NeurIPS 2025
EvoBrain: Dynamic Multi-Channel EEG Graph Modeling for Time-Evolving Brain Networks
机构 * Department of Neurosurgery, Graduate School of Medicine, The University of Osaka, Japan（大阪大学医学研究生院神经外科） ； Institute for Advanced Co-Creation Studies, The University of Osaka, Japan（大阪大学先进协同研究机构）
Comments Accepted by NeurIPS 2025 (spotlight)
Beyond the Average: Distributional Causal Inference under Imperfect Compliance
Comments Proceedings of the Neural Information Processing Systems (NeurIPS) 2025
