Researcher — paper.dinq.me

2026 顶会论文

作者位次 #6/6ICLR 2026Poster

Exposing and Defending the Achilles' Heel of Video Mixture-of-Experts

songping wang · Qinglong Liu · Yueming Lyu · Ning Li · Ziwen He · Caifeng Shan

多模态效率与系统OpenReview

作者位次 #5/6ICLR 2026Poster· Computer Vision / Segmentation

Matting Anything 2: Towards Video Matting for Anything

Chenyi Zhang · Yiheng Lin · Yunchao Wei · Hongsong Wang · Caifeng Shan · Fang Zhao

多模态OpenReview

作者位次 #26/26ICLR 2026Poster· Computer Vision / Vision Models & Multimodal

SpineBench: A Clinically Salient, Level-Aware Benchmark Powered by the SpineMed-450k Corpus

Ming Zhao · Wenhui Dong · Yang Zhang · wangyou · Zhonghao Zhang · Zian Zhou · YUNZHI GUAN · Liukun Xu · Wei Peng · Zhaoyang Gong · Zhicheng Zhang · Dachuan li · Xiaosheng Ma · Yuli Ma · Jianing Ni · Changjiang Jiang · Lixia Tian · Chen Qixin · Xia Kaishun · Pingping Liu · Tongshun Zhang · ZhiqiangLiu · Zhongan Bi · Chenyang Si · Tiansheng Sun · Caifeng Shan

多模态评测与基准数据与预训练OpenReview

作者位次 #4/5ICLR 2026Poster· Computer Vision / Vision Models & Multimodal

HiTeA: Hierarchical Temporal Alignment for Training-Free Long-Video Temporal Grounding

Xinyi Xu · Hongsong Wang · Guo-Sen Xie · Caifeng Shan · Fang Zhao

多模态对齐与偏好OpenReview

作者位次 #5/5CVPR 2026Spotlight· Computer Vision & Pattern Recognition

PersonaVLM: Long-Term Personalized Multimodal LLMs

Chang Nie · Chaoyou Fu · YiFan Zhang · Haihua Yang · Caifeng Shan

多模态对齐与偏好OpenReview 项目页

作者位次 #7/7CVPR 2026Spotlight· Computer Vision & Pattern Recognition

One-to-More: High-Fidelity Training-Free Anomaly Generation with Attention Control

Haoxiang Rao · Zhao Wang · Chenyang Si · Yan Lyu · Yuanyi Duan · Fang Zhao · Caifeng Shan

多模态OpenReview 项目页

作者位次 #9/10CVPR 2026Poster· Computer Vision & Pattern Recognition

NOVA: Sparse Control, Dense Synthesis for Pair-Free Video Editing

Tianlin Pan · Jiayi Dai · Chenpu Yuan · Zhengyao Lv · Binxin Yang · Hubery Yin · Chen Li · Jing LYU · Caifeng Shan · Chenyang Si

多模态OpenReview 项目页

作者位次 #4/4CVPR 2026Poster· Computer Vision & Pattern Recognition

Beyond Weak Supervision: MLLMs-Guided Graded Knowledge Distillation for Unsupervised Camouflaged Object Detection

Huafeng Chen · Chenguang Zhu · Yueming Lyu · Caifeng Shan

多模态强化学习与后训练检索与知识OpenReview 项目页

作者位次 #8/8CVPR 2026Poster· Computer Vision & Pattern Recognition

RunawayEvil: Jailbreaking the Image-to-Video Generative Models

songping wang · Rufan Qian · Yueming Lyu · Qinglong Liu · Linzhuang Zou · Jie Qin · Songhua Liu · Caifeng Shan

多模态安全OpenReview 项目页

Caifeng Shan

获取完整研究档案

联系方式