MetaMind: Modeling Human Social Thoughts with Metacognitive Multi-Agent Systems
机构 * Tsinghua University（清华大学）
Comments NeurIPS 2025 Spotlight
期刊&会议
NeurIPS
Conference on Neural Information Processing Systems · 会议 · Machine Learning
Highlighting What Matters: Promptable Embeddings for Attribute-Focused Image Retrieval
Comments NeurIPS 2025; 27 pages, 6 figures
VideoRFT: Incentivizing Video Reasoning Capability in MLLMs via Reinforced Fine-Tuning
机构 * Beijing Institute of Technology（北京理工大学） ； Shenzhen University（深圳大学）
Comments Accepted by NeurIPS 2025. Code: https://github.com/QiWang98/VideoRFT
Aux-Think: Exploring Reasoning Strategies for Data-Efficient Vision-Language Navigation
机构 * Renmin University of China（中国人民大学） ； Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing（北京未来区块链与隐私计算先进创新中心） ； Horizon Robotics（地平线机器人）
Journal ref NeurIPS 2025
Time Travel is Cheating: Going Live with DeepFund for Real-Time Fund Investment Benchmarking
机构 * The Hong Kong University of Science and Technology (Guangzhou)（香港理工大学（广州）） ； Paradoox AI Research（Paradoox AI研究院）
Comments NeurIPS 2025 Datasets and Benchmarks Track
Mind the (Data) Gap: Evaluating Vision Systems in Small Data Applications
机构 * The Ohio State University（俄亥俄州立大学） ； Rensselaer Polytechnic Institute（拉特格斯理工学院）
Comments 5 pages (main text), 3 figures. Accepted at the Imageomics Workshop at NeurIPS 2025
OpenLex3D: A Tiered Evaluation Benchmark for Open-Vocabulary 3D Scene Representations
Comments NeurIPS 2025
ParetoQ: Improving Scaling Laws in Extremely Low-bit LLM Quantization
机构 * Meta AI
Comments NeurIPS 2025. Model weights are available at https://huggingface.co/collections/facebook/mobilellm-6722be18cb86c20ebe113e95
ChunkKV: Semantic-Preserving KV Cache Compression for Efficient Long-Context LLM Inference
机构 * The Hong Kong University of Science and Technology (Guangzhou)（香港科学与技术大学（广州）） ； CSE, The Hong Kong University of Science and Technology（香港科学与技术大学计算机科学与工程系） ； Guangzhou HKUST Fok Ying Tung Research Institute（广州HKUST福 Ying Tung研究 institute） ； Terminus Technologies
Comments NeurIPS 2025
Evaluating multiple models using labeled and unlabeled data
机构 * Department of Computer Science, Cornell University（康奈尔大学计算机科学系） ； Department of Electrical Engineering & Computer Science, MIT（麻省理工学院电子工程与计算机科学系） ； Sloan School of Management, MIT（麻省理工学院斯隆管理学院） ； Department of Electrical Engineering & Computer Sciences, UC Berkeley（伯克利大学电子工程与计算机科学系）
Comments To appear at NeurIPS 2025
Go With the Flow: Fast Diffusion for Gaussian Mixture Models
机构 * Georgia Institute of Technology（佐治亚理工学院） ； University of Oklahoma（俄克拉荷马大学） ； FAMU-FSU College of Engineering（佛罗里达大学-佛罗里达州立大学工程学院） ； Florida State University（佛罗里达州立大学）
Comments NIPS 2025 (spotlight)
Tracing Back the Malicious Clients in Poisoning Attacks to Federated Learning
Comments Conference on Neural Information Processing Systems (NeurIPS) 2025
ACCO: Accumulate While You Communicate for Communication-Overlapped Sharded LLM Training
Journal ref The Thirty-ninth Annual Conference on Neural Information Processing Systems, Dec 2025, San diego (Californie), United States
When "Competency" in Reasoning Opens the Door to Vulnerability: Jailbreaking LLMs via Novel Complex Ciphers
机构 * Arizona State University（亚利桑那州立大学）
Comments Published in Reliable ML from Unreliable Data workshop @ NeurIPS 2025
Competitive Advantage Attacks to Decentralized Federated Learning
Comments Conference on Neural Information Processing Systems (NeurIPS) 2025
Replicable Clustering
Comments to be published in NeurIPS 2023
