Researcher — paper.dinq.me

2026 顶会论文

作者位次 #9/9ICLR 2026Poster· Computer Vision / Image and Video Generation

Any-to-Bokeh: Arbitrary-Subject Video Refocusing with Video Diffusion Model

Yang Yang · Siming Zheng · Qirui Yang · Jinwei Chen · Boxi Wu · Xiaofei He · Deng Cai · Bo Li · Peng-Tao Jiang

多模态OpenReview

作者位次 #6/6ICLR 2026Poster· Computer Vision / Image and Video Generation

Trust but Verify: Adaptive Conditioning for Reference-Based Diffusion Super-Resolution via Implicit Reference Correlation Modeling

Yuan Wang · Yuhao Wan · Siming Zheng · Bo Li · Qibin Hou · Peng-Tao Jiang

多模态OpenReview

作者位次 #4/9ICLR 2026Poster· Computer Vision / Image and Video Generation

TS-Attn: Temporal-wise Separable Attention for Multi-Event Video Generation

Hongyu Zhang · Yufan Deng · Zilin Pan · Peng-Tao Jiang · Bo Li · Qibin Hou · Zhen Dong · Zhiyang Dou · Zhou Daquan

多模态OpenReview

作者位次 #6/7ICLR 2026Poster· Computer Vision / Image and Video Generation

I-DRUID: Layout to image generation via instance-disentangled representation and unpaired data

Fengxiang Yang · Tianyi Zheng · Bangjie Yin · Shice Liu · Jinwei Chen · Peng-Tao Jiang · Bo Li

多模态可解释性OpenReview

作者位次 #4/7CVPR 2026Poster· Computer Vision & Pattern Recognition

Time-Aware One Step Diffusion Network for Real-World Image Super-Resolution

Tianyi Zhang · Zheng-Peng Duan · Chun-Le Guo · Peng-Tao Jiang · Bo Li · Ming-Ming Cheng · Chongyi Li

多模态OpenReview 项目页

作者位次 #7/10CVPR 2026Poster· Computer Vision & Pattern Recognition

VisMem: Latent Vision Memory Unlocks Potential of Vision-Language Models

Xinlei Yu · Chengming Xu · Guibin Zhang · Zhangquan Chen · Yudong Zhang · Yongbo He · Peng-Tao Jiang · Jiangning Zhang · Xiaobin Hu · Shuicheng YAN

多模态检索与知识OpenReview 项目页

作者位次 #10/12CVPR 2026Spotlight· Computer Vision & Pattern Recognition

C^2FG: Control Classifier-Free Guidance via Score Discrepancy Analysis

Jiayang Gao · Tianyi Zheng · Jiayang Zou · Fengxiang Yang · Shice Liu · Luyao Fan · Zheyu Zhang · Hao Zhang · Jinwei Chen · Peng-Tao Jiang · Bo Li · Jia Wang

多模态OpenReview 项目页

作者位次 #3/4AAAI 2026Poster· Artificial Intelligence

Realism Control One-step Diffusion for Real-world Image Super Resolution

Zongliang Wu · Siming Zheng · Peng-Tao Jiang · Xin Yuan

多模态OpenReview

作者位次 #3/9AAAI 2026Poster· Artificial Intelligence

Bidirectional Noise Injection: Enhancing Diffusion Models via Coordinated Input-Output Perturbation

Tianyi Zheng · Jiayang Gao · Peng-Tao Jiang · Fengxiang Yang · Ben Wan · Hao Zhang · Jinwei Chen · Jia Wang · Bo Li

OpenReview

Peng-Tao Jiang

获取完整研究档案

联系方式

2026 顶会论文

Any-to-Bokeh: Arbitrary-Subject Video Refocusing with Video Diffusion Model

Trust but Verify: Adaptive Conditioning for Reference-Based Diffusion Super-Resolution via Implicit Reference Correlation Modeling

TS-Attn: Temporal-wise Separable Attention for Multi-Event Video Generation

I-DRUID: Layout to image generation via instance-disentangled representation and unpaired data

Time-Aware One Step Diffusion Network for Real-World Image Super-Resolution

VisMem: Latent Vision Memory Unlocks Potential of Vision-Language Models

C^2FG: Control Classifier-Free Guidance via Score Discrepancy Analysis

Realism Control One-step Diffusion for Real-world Image Super Resolution

Bidirectional Noise Injection: Enhancing Diffusion Models via Coordinated Input-Output Perturbation

常见合作者