Researcher — paper.dinq.me

2026 顶会论文

作者位次 #4/4ICLR 2026Poster· Deep Learning / Generative Models and Autoencoders

Eliminating VAE for Fast and High-Resolution Generative Detail Restoration

Yan Wang · Shijie Zhao · Junlin Li · Li zhang

OpenReview

作者位次 #5/7ICLR 2026Oral

Reasoning as Representation: Rethinking Visual Reinforcement Learning in Image Quality Assessment

Shijie Zhao · Xuanyu Zhang · Weiqi Li · Junlin Li · Li zhang · Tianfan Xue · Jian Zhang

多模态推理可解释性OpenReview

作者位次 #5/5ICLR 2026Poster· Deep Learning / Generative Models and Autoencoders

GenDR: Lighten Generative Detail Restoration

Yan Wang · Shijie Zhao · Kexin Zhang · Junlin Li · Li zhang

OpenReview

作者位次 #9/9ICLR 2026Poster· Computer Vision / Vision Models & Multimodal

Self-Evolving Vision-Language Models for Image Quality Assessment via Voting and Ranking

Wen Wen · Tianwu Zhi · Kanglong Fan · Yang Li · Xinge Peng · Yabin ZHANG · Yiting Liao · Junlin Li · Li zhang

多模态OpenReview

作者位次 #5/9ICLR 2026Poster· Computer Vision / Image and Video Generation

Realtime Video Frame Interpolation using One-Step Diffusion Sampling

Yongrui Ma · Shijie Zhao · Mingde Yao · Junlin Li · Li zhang · Xiaohong Liu · Qi Dou · Jinwei Gu · Tianfan Xue

多模态OpenReview

作者位次 #6/7ICLR 2026Poster

Improved Adversarial Diffusion Compression for Real-World Video Super-Resolution

Bin Chen · Weiqi Li · Shijie Zhao · Xuanyu Zhang · Junlin Li · Li zhang · Jian Zhang

安全多模态效率与系统OpenReview

作者位次 #8/9CVPR 2026Poster· Computer Vision & Pattern Recognition

TempR1: Improving Temporal Understanding of MLLMs via Temporal-Aware Multi-Task Reinforcement Learning

Tao Wu · Li Yang · Gen Zhan · Yabin ZHANG · Yiting Liao · Junlin Li · Deliang Fu · Li zhang · Limin Wang

多模态强化学习与后训练OpenReview 项目页

作者位次 #5/9CVPR 2026Poster· Computer Vision & Pattern Recognition

Bi-directional Autoregressive Diffusion for Large Complex Motion Interpolation

Yongrui Ma · Shijie Zhao · Mingde Yao · Junlin Li · Li zhang · Xiaohong Liu · Qi Dou · Jinwei Gu · Tianfan Xue

多模态OpenReview 项目页

作者位次 #8/10CVPR 2026Poster· Computer Vision & Pattern Recognition

UARE: A Unified Vision-Language Model for Image Quality Assessment, Restoration, and Enhancement

Weiqi Li · Xuanyu Zhang · Bin Chen · Jingfen Xie · Yan Wang · Kexin Zhang · Junlin Li · Li zhang · Jian Zhang · Shijie Zhao

多模态OpenReview 项目页

作者位次 #4/5AAAI 2026Poster· Artificial Intelligence

Spatio-Temporal Distortion Aware Omnidirectional Video Super-Resolution

Hongyu An · Xinfeng Zhang · Shijie Zhao · Li zhang · Ruiqin Xiong

多模态OpenReview

作者位次 #5/6AAAI 2026Poster· Artificial Intelligence

VQ-Insight: Teaching VLMs for AI-Generated Video Quality Understanding via Progressive Visual Reinforcement Learning

Xuanyu Zhang · Weiqi Li · Shijie Zhao · Junlin Li · Li zhang · Jian Zhang

多模态强化学习与后训练OpenReview

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

Collaboratively "Copy & Paste" 2D-3D Features for Complex Video-to-Video Motion Editing

Jia-Xing Zhong · Shijie Zhao · Junlin Li · Li zhang

多模态OpenReview

Li zhang

获取完整研究档案

联系方式

2026 顶会论文

Eliminating VAE for Fast and High-Resolution Generative Detail Restoration

Reasoning as Representation: Rethinking Visual Reinforcement Learning in Image Quality Assessment

GenDR: Lighten Generative Detail Restoration

Self-Evolving Vision-Language Models for Image Quality Assessment via Voting and Ranking

Realtime Video Frame Interpolation using One-Step Diffusion Sampling

Improved Adversarial Diffusion Compression for Real-World Video Super-Resolution

TempR1: Improving Temporal Understanding of MLLMs via Temporal-Aware Multi-Task Reinforcement Learning

Bi-directional Autoregressive Diffusion for Large Complex Motion Interpolation

UARE: A Unified Vision-Language Model for Image Quality Assessment, Restoration, and Enhancement

Spatio-Temporal Distortion Aware Omnidirectional Video Super-Resolution

VQ-Insight: Teaching VLMs for AI-Generated Video Quality Understanding via Progressive Visual Reinforcement Learning

Collaboratively "Copy & Paste" 2D-3D Features for Complex Video-to-Video Motion Editing

常见合作者