📰 NeurIPS 2025 — accepted papers

NeurIPS 2025 is the 2025 edition of the Conference on Neural Information Processing Systems (NeurIPS), held in San Diego, United States, 2–7 December 2025. OpenAlex lists 5,819 papers of it; our library holds 6 with our summaries. Below: the most cited papers, every accepted paper, and ours with their topics, authors and institutions.

Most cited papers

By their OpenAlex citations; a paper with our summary links to its page here, the others to the original.

1. YOLOv12: Attention-Centric Real-Time Object DetectorsYunjie Tian, Qixiang Ye, David Doermann744 citations
2. MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language ModelsChaoyou Fu, Peixian Chen, Yunhang Shen et al.143 citations · our summary
3. UMA: A Family of Universal Models for AtomsBrandon M. Wood, Misko Dzamba, Xiang Fu et al.79 citations
4. Why Do Multi-Agent LLM Systems Fail?Mert Cemri, Melissa Pan, Shuyi Yang et al.48 citations
5. Scaling Unlocks Broader Generation and Deeper Functional Understanding of ProteinsAadyot Bhatnagar, Sarthak Jain, Joel Beazer et al.44 citations
6. Self Forcing: Bridging the Train-Test Gap in Autoregressive Video DiffusionXun Huang, Zhengqi Li, Guande He et al.42 citations
7. Flow-GRPO: Training Flow Matching Models via Online RLJie Liu, Gongye Liu, Jiajun Liang et al.40 citations
8. MoGe-2: Accurate Monocular Geometry with Metric Scale and Sharp DetailsRuicheng Wang, Sicheng Xu, Yue Dong et al.37 citations
9. Video-R1: Reinforcing Video Reasoning in MLLMsKaituo Feng, Kaixiong Gong, Bohao Li et al.37 citations
10. Mean Flows for One-step Generative ModelingZhengyang Geng, Mingyang Deng, Xingjian Bai et al.35 citations

All accepted papers (5,819)

The most cited first; 6 with our summary link to their page here, the others to the original.

1. YOLOv12: Attention-Centric Real-Time Object DetectorsYunjie Tian, Qixiang Ye, David Doermann744 citations
2. MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language ModelsChaoyou Fu, Peixian Chen, Yunhang Shen et al.143 citations · our summary
3. UMA: A Family of Universal Models for AtomsBrandon M. Wood, Misko Dzamba, Xiang Fu et al.79 citations
4. Why Do Multi-Agent LLM Systems Fail?Mert Cemri, Melissa Pan, Shuyi Yang et al.48 citations
5. Scaling Unlocks Broader Generation and Deeper Functional Understanding of ProteinsAadyot Bhatnagar, Sarthak Jain, Joel Beazer et al.44 citations
6. Self Forcing: Bridging the Train-Test Gap in Autoregressive Video DiffusionXun Huang, Zhengqi Li, Guande He et al.42 citations
7. Flow-GRPO: Training Flow Matching Models via Online RLJie Liu, Gongye Liu, Jiajun Liang et al.40 citations
8. MoGe-2: Accurate Monocular Geometry with Metric Scale and Sharp DetailsRuicheng Wang, Sicheng Xu, Yue Dong et al.37 citations
9. Video-R1: Reinforcing Video Reasoning in MLLMsKaituo Feng, Kaixiong Gong, Bohao Li et al.37 citations
10. Mean Flows for One-step Generative ModelingZhengyang Geng, Mingyang Deng, Xingjian Bai et al.35 citations
11. A-Mem: Agentic Memory for LLM AgentsWujiang Xu, Zujie Liang, Kai Mei et al.34 citations · our summary
12. The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem ComplexityParshin Shojaee, Iman Mirzadeh, Keivan Alizadeh et al.33 citations
13. DAPO: An Open-Source LLM Reinforcement Learning System at ScaleQiying Yu, Zheng Zhang, Ruofei Zhu et al.30 citations
14. Gymnasium: A Standard Interface for Reinforcement Learning EnvironmentsMark Towers, Ariel Kwiatkowski, John Balis et al.29 citations
15. AgentNet: Decentralized Evolutionary Coordination for LLM-based Multi-Agent SystemsYingxuan Yang, Huacan Chai, Shuai Shao et al.26 citations
16. Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial IntelligenceDiankun Wu, Fangfu Liu, Yi‐Hsin Hung et al.26 citations
17. ImgEdit: A Unified Image Editing Dataset and BenchmarkYe Yang, Xianyi He, Zongjian Li et al.25 citations
18. AutoVLA: A Vision-Language-Action Model for End-to-End Autonomous Driving with Adaptive Reasoning and Reinforcement Fine-TuningZewei Zhou, Tianhui Cai, Seth Z. Zhao et al.23 citations
19. Large Language Diffusion ModelsShen Nie, Fengqi Zhu, Zebin You et al.23 citations · our summary
20. OCRBench v2: An Improved Benchmark for Evaluating Large Multimodal Models on Visual Text Localization and ReasoningLing Fu, Zhebin Kuang, Jiajun Song et al.22 citations
21. Position: Towards Bidirectional Human-AI AlignmentHua Shen, Tiffany Knearem, Reshmi Ghosh et al.22 citations
22. Titans: Learning to Memorize at Test TimeAli Behrouz, Peilin Zhong, Vahab Mirrokni21 citations
23. Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-FreeZihan Qiu, Zekun Wang, Bo Zheng et al.19 citations
24. MMaDA: Multimodal Large Diffusion Language ModelsLing Yang, Ye Tian, Bowen Li et al.19 citations
25. PerturBench: Benchmarking Machine Learning Models for Cellular Perturbation AnalysisYan Wu, Esther Wershof, Sebastian M. Schmon et al.19 citations

See all 5,819 papers in NeurIPS 2025 — accepted papers →

📄 Papers with our summary in our library (6)

The most cited first (OpenAlex citations plus our library's).

1. A-MEM: Agentic Memory for LLM AgentsConference on Neural Information Processing Systems (NeurIPS)Wujiang Xu, Zujie Liang, Kai Mei, et al.2025 · 171 citations
2. Large Language Diffusion ModelsConference on Neural Information Processing Systems (NeurIPS)Shen Nie, Fengqi Zhu, Zebin You, et al.2025 · 164 citations
3. Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM ReasoningConference on Neural Information Processing Systems (NeurIPS)Shenzhi Wang, Le Yu, Chang Gao, et al.2025 · 142 citations
4. Open-Reasoner-Zero: An Open Source Approach to Scaling Up Reinforcement Learning on the Base ModelConference on Neural Information Processing Systems (NeurIPS)Jingcheng Hu, Yinmin Zhang, Qi Han, et al.2025 · 121 citations
5. MoBA: Mixture of Block Attention for Long-Context LLMsConference on Neural Information Processing Systems (NeurIPS)Enzhe Lu, Zhejun Jiang, Jingyuan Liu, et al.2025 · 75 citations
6. A Multi-Task Benchmark for Abusive Language Detection in Low-Resource SettingsConference on Neural Information Processing Systems (NeurIPS)Fitsum Gaim, Hoyun Song, Huije Lee, et al.2025 · 3 citations

🧭 Top topics

Topics of its works in our library, with the number of works on each.

🧠Language models & pretraining (2)🌱Low-resource languages (1)📏Evaluation & benchmarks (1)🧮Reasoning (1)Semitic languages (1)

📚 Fields

🖥️Computer Science (6)🎭Arts and Humanities (5)🤝Social Sciences (1)

🧑‍🔬 Top authors

Authors with a page who published here most often: their works here, and the citations of those works.

🏛️ Top institutions

Institutions on the bylines of its works here, by the number of works.

🎓Tsinghua UniversityBeijing · China3 works here🏢Ant GroupHangzhou · China2 works here🎓Renmin University of ChinaBeijing · China2 works here🎓Nanjing UniversityNanjing · China2 works here🎓Rutgers, The State University of New JerseyNew Brunswick · United States1 work here🏢MicrosoftRedmond · United States1 work here🎓Korea Advanced Institute of Science and TechnologyDaejeon · South Korea1 work here🎓University of Illinois Urbana-ChampaignUrbana · United States1 work here🎓National University of Defense TechnologyChangsha · China1 work here🎓Chinese University of Hong KongHong Kong · China1 work here🎓Sichuan UniversityChengdu · China1 work here🏢SalesforceSan Francisco · United States1 work here

Place and dates from the event's site or the ACL Anthology; works and citations from OpenAlex and our library.

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/venues/neural-information-processing-systems/2025/