Shin Seong Kim, Mingi Kwon, Jaeseok Jeong, Youngjung Uh
机构
*
Yonsei University(延世大学)
AI总结
本文提出一种结合真实图像的修正流方法,通过减少对生成数据的依赖,提升生成质量与稳定性。
CommentsMain paper: 10 pages (total 40 pages including appendix), 5 figures. Accepted at NeurIPS 2025 (Poster). Acknowledgment: Supported by the NRF of Korea (RS-2023-00223062) and IITP grants (RS-2020-II201361, RS-2024-00439762) funded by the Korean government (MSIT)
Journal refProceedings of the 39th Annual Conference on Neural Information Processing Systems (NeurIPS 2025)
机构
*
School of Advanced Interdisciplinary Sciences, University of Chinese Academy of Sciences(中国科学院大学先进交叉学科学院)
;
State Key Lab of Processors, Institute of Computing Technology, CAS(中国科学院计算技术研究所 processors 国家重点实验室)
;
Alibaba Group(阿里巴巴集团)
;
Sun Yat-sen University(中山大学)
M-GRPO: Stabilizing Self-Supervised Reinforcement Learning for Large Language Models with Momentum-Anchored Policy Optimization
M-GRPO:通过动量锚定策略优化稳定大语言模型的自监督强化学习
Bizhe Bai, Hongming Wu, Peng Ye, Tao Chen
机构
*
Shanghai Innovation Institute(上海创新研究院)
;
College of Future Information Technology, Fudan(复旦大学未来信息技术学院)
;
Shanghai AI Laboratory(上海人工智能实验室)
;
The Chinese University of Hong Kong(香港中文大学)
Comments10 pages, 3 figures. Expanded version of an extended abstract accepted at NeurIPS 2025 Workshop on VLM4RWD. Presents methodology and preliminary experimental results
Dynamical modeling of nonlinear latent factors in multiscale neural activity with real-time inference
多尺度神经活动中非线性潜在因子的动力学建模
Eray Erturk, Maryam M. Shanechi
机构
*
Department of Electrical and Computer Engineering(电气与计算机工程系)
;
University of Southern California(南加州大学)
;
Department of Computer Science(计算机科学系)
;
Department of Biomedical Engineering(生物医学工程系)
;
Neuroscience Graduate Program(神经科学研究生项目)
CommentsPublished at the 39th Annual Conference on Neural Information Processing Systems 2025. Code is available at https://github.com/ShanechiLab/mrine
Cross-Modal Representational Knowledge Distillation for Enhanced Spike-Informed LFP Modeling
跨模态表征知识蒸馏用于增强基于尖峰的LFP建模
Eray Erturk, Saba Hashemi, Maryam M. Shanechi
机构
*
Ming Hsieh Department of Electrical and Computer Engineering(明希斯电气与计算机工程系)
;
Thomas Lord Department of Computer Science(托马斯·劳德计算机科学系)
;
Alfred E. Mann Department of Biomedical Engineering(阿尔弗雷德·E·曼生物医学工程系)
;
Neuroscience Graduate Program University of Southern California(神经科学研究生项目美国南加州大学)
MetaTPT: Meta Test-time Prompt Tuning for Vision-Language Models
MetaTPT: 用于视觉-语言模型的元测试时间提示微调
Yuqing Lei, Yingjun Du, Yawen Huang, Xiantong Zhen, Ling Shao
机构
*
UCAS-Terminus AI Lab, University of Chinese Academic of Sciences(中国科学院大学Terminus AI实验室,中国科学院大学)
;
AIM Lab, University of Amsterdam(阿姆斯特丹大学AIM实验室)
;
Jarvis Research Center, Tencent Youtu Lab(腾讯优图实验室 Jarvis 研究中心)
;
Central Research Institue, United Imaging Healthcare Co., Ltd(联合影像医疗科技有限公司中央研究所)
De novo generation of functional terpene synthases using TpsGPT
利用 TpsGPT 从头设计功能性萜类合成酶
Hamsini Ramanathan, Roman Bushuiev, Matouš Soldát, Jirí Kohout, Téo Hebra, Joshua David Smith, Josef Sivic, Tomáš Pluskal
机构
*
Seattle Academy of Arts and Sciences (SAAS)(西雅图艺术与科学学院)
;
Czech Institute of Informatics, Robotics and Cybernetics (CIIRC)(捷克信息学、机器人学与自动控制研究所)
;
Czech Technical University(捷克技术大学)
AI总结
TpsGPT 通过微调蛋白质语言模型生成功能性萜类合成酶,验证了从头设计酶的可行性。
Comments11 pages, 8 figures, Accepted at the NeurIPS 2025 AI for Science and Machine Learning for Structural Biology 2025 workshops Fixed incorrect threshold in Fig 1
机构
*
Nankai International Advanced Research Institute (SHENZHEN·FUTIAN)(南开国际先进研究院(深圳·福田))
;
Peng Cheng Laboratory(鹏城实验室)
;
College of Computer Science, Nankai University(南开大学计算机学院)
;
Nanjing University of Science and Technology(南京理工大学)
;
Key Lab of SCCI, Dalian University of Technology(大连理工大学SCCI重点实验室)
AI总结
FlareX 通过结合 2D 合成和 3D 渲染,生成了一个包含 9,500 个 2D 模板和 3,000 个 3D 场景图像对的基于物理的镜头 flare 去除数据集。
Stealthy Yet Effective: Distribution-Preserving Backdoor Attacks on Graph Classification
隐秘而有效的:图分类中的分布保持后门攻击
Xiaobao Wang, Ruoxiao Sun, Yujun Zhang, Bingdao Feng, Dongxiao He, Luzhi Wang, Di Jin
机构
*
College of Intelligence and Computing, Tianjin University, Tianjin, China(天津大学智能与计算学院)
;
Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ), Shenzhen, China(广东人工智能与数字经济实验室(深圳))
;
College of Artificial Intelligence, Dalian Maritime University, Dalian, China(大连海事大学人工智能学院)
机构
*
The University of Hong Kong(香港大学)
;
Carnegie Mellon University(卡内基梅隆大学)
;
Johns Hopkins University(约翰霍普金斯大学)
;
University of California Irvine(加州大学尔湾分校)
;
Stanford University(斯坦福大学)
Leveraging Importance Sampling to Detach Alignment Modules from Large Language Models
利用重要性采样将对齐模块从大语言模型中分离出来
Yi Liu, Dianqing Liu, Mingye Zhu, Junbo Guo, Yongdong Zhang, Zhendong Mao
机构
*
State Key Laboratory of Communication Content Cognition, People’s Daily Online(通信内容认知国家重点实验室,人民在线)
;
University of Science and Technology of China(中国科学技术大学)