Researcher — paper.dinq.me

2026 顶会论文

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

Draw-In-Mind: Rebalancing Designer-Painter Roles in Unified Multimodal Models Benefits Image Editing

Ziyun Zeng · David Junhao Zhang · Wei Li · Mike Zheng Shou

多模态OpenReview

作者位次 #2/2ICLR 2026Poster· Computer Vision / Image and Video Generation

TPDiff: Temporal Pyramid Video Diffusion Model

Lingmin Ran · Mike Zheng Shou

多模态OpenReview

作者位次 #2/2ICLR 2026Poster· Computer Vision / Image and Video Generation

D-AR: Diffusion via Autoregressive Models

Ziteng Gao · Mike Zheng Shou

多模态OpenReview

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

VideoMind: A Chain-of-LoRA Agent for Temporal-Grounded Video Reasoning

Ye Liu · Kevin Qinghong Lin · Chang-Wen Chen · Mike Zheng Shou

多模态推理智能体与工具OpenReview

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

The Consistency Critic: Correcting Inconsistencies in Generated Images via Reference-Guided Attentive Alignment

Ziheng Ouyang · Yiren Song · Yaoli Liu · Shihao Zhu · Qibin Hou · Ming-Ming Cheng · Mike Zheng Shou

多模态对齐与偏好OpenReview 项目页

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

The Image as Its Own Reward: Reinforcement Learning with Adversarial Reward for Image Generation

Weijia Mao · Hao Chen · Zhenheng Yang · Mike Zheng Shou

多模态安全强化学习与后训练OpenReview 项目页

作者位次 #3/4CVPR 2026Poster· Computer Vision & Pattern Recognition

FocusUI: Efficient UI Grounding via Position-Preserving Visual Token Selection

Mingyu Ouyang · Kevin Qinghong Lin · Mike Zheng Shou · Hwee Tou Ng

多模态效率与系统OpenReview 项目页

作者位次 #3/3CVPR 2026Poster· Computer Vision & Pattern Recognition

ShowUI-p: Flow-based Generative Models as GUI Dexterous Hands

Siyuan Hu · Kevin Qinghong Lin · Mike Zheng Shou

智能体与工具多模态OpenReview 项目页

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

RobotSeg: A Model and Dataset for Segmenting Robots in Image and Video

Haiyang Mei · Qiming Huang · Hai Ci · Mike Zheng Shou

多模态数据与预训练OpenReview 项目页

作者位次 #3/3CVPR 2026Poster· Computer Vision & Pattern Recognition

Edit2Perceive: Image Editing Diffusion Models Are Strong Dense Perceivers

Yiqing Shi · Yiren Song · Mike Zheng Shou

多模态OpenReview 项目页

作者位次 #3/3CVPR 2026Poster· Computer Vision & Pattern Recognition

MakeAnything: Harnessing Diffusion Transformers for Multi-Domain Procedural Sequence Generation

Yiren Song · Cheng Liu · Mike Zheng Shou

多模态OpenReview 项目页

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

Demo2Tutorial: From Human Experience to Multimodal Software Tutorials

Zechen Bai · Zhiheng Chen · Yiqi Lin · Kevin Qinghong Lin · Difei Gao · Xiangwu Guo · Xin Wang · Mike Zheng Shou

多模态代码社会与人本OpenReview 项目页

作者位次 #2/2CVPR 2026Poster· Computer Vision & Pattern Recognition

P-Flow: Prompting Visual Effects Generation

Rui Zhao · Mike Zheng Shou

多模态OpenReview 项目页

作者位次 #3/5ICRA 2026Oral· Robotics & Automation

MachaGrasp: Morphology-Aware Cross-Embodiment Dexterous Hand Articulation Generation for Grasping

Heng Zhang · Kevin Yuchen Ma · Mike Zheng Shou · Weisi Lin · Yan Wu

OpenReview

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

OptMark: Robust Multi-bit Diffusion Watermarking via Inference Time Optimization

Jiazheng Xing · Hai Ci · Hongbin Xu · Hangjie Yuan · Yong Liu · Mike Zheng Shou

安全效率与系统OpenReview

Mike Zheng Shou

获取完整研究档案

联系方式

2026 顶会论文

Draw-In-Mind: Rebalancing Designer-Painter Roles in Unified Multimodal Models Benefits Image Editing

TPDiff: Temporal Pyramid Video Diffusion Model

D-AR: Diffusion via Autoregressive Models

VideoMind: A Chain-of-LoRA Agent for Temporal-Grounded Video Reasoning

The Consistency Critic: Correcting Inconsistencies in Generated Images via Reference-Guided Attentive Alignment

The Image as Its Own Reward: Reinforcement Learning with Adversarial Reward for Image Generation

FocusUI: Efficient UI Grounding via Position-Preserving Visual Token Selection

ShowUI-p: Flow-based Generative Models as GUI Dexterous Hands

RobotSeg: A Model and Dataset for Segmenting Robots in Image and Video

Edit2Perceive: Image Editing Diffusion Models Are Strong Dense Perceivers

MakeAnything: Harnessing Diffusion Transformers for Multi-Domain Procedural Sequence Generation

Demo2Tutorial: From Human Experience to Multimodal Software Tutorials

P-Flow: Prompting Visual Effects Generation

MachaGrasp: Morphology-Aware Cross-Embodiment Dexterous Hand Articulation Generation for Grasping

OptMark: Robust Multi-bit Diffusion Watermarking via Inference Time Optimization

常见合作者