Researcher — paper.dinq.me

2026 顶会论文

作者位次 #6/7ICML 2026Oral· Applications / Robotics

From Abstraction to Instantiation: Learning Behavioral Representation for Vision-Language-Action Model

Bing Hu · Zaijing Li · Rui Shao · Junda Chen · April Hua Liu · Wei-Shi Zheng · Liqiang Nie

可解释性多模态OpenReview

作者位次 #8/9ICML 2026Poster· Applications / Robotics

VLANeXt: Recipes for Building Strong VLA Models

Xiao-Ming Wu · Bin Fan · Kang Liao · Jian-Jian Jiang · Runze Yang · Yihang Luo · Zhonghua Wu · Wei-Shi Zheng · Chen Change Loy

OpenReview

作者位次 #6/6ICML 2026Poster· Applications / Computer Vision

ObjEmbed: Towards Universal Multimodal Object Embeddings

Shenghao Fu · Yukun Su · Fengyun Rao · Jing LYU · Xiaohua Xie · Wei-Shi Zheng

多模态OpenReview

作者位次 #6/6ICML 2026Poster· Applications / Computer Vision

Seg-ReSearch: Segmentation with Interleaved Reasoning and External Search

Tianming Liang · Qirui Du · Jian-Fang Hu · Haichao Jiang · Zicheng Lin · Wei-Shi Zheng

推理多模态检索与知识OpenReview

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

Beyond Mimicry: Learning Whole-Body Human-Humanoid Interaction from Human-Human Demonstrations

Wei-Jin Huang · Yue-Yi Zhang · Yi-Lin Wei · Zhi-Wei Xia · Juantao Tan · Yuan-Ming Li · Zhilin Zhao · Wei-Shi Zheng

多模态社会与人本OpenReview 项目页

作者位次 #6/6CVPR 2026Poster· Computer Vision & Pattern Recognition

WeDetect: Fast Open-Vocabulary Object Detection as Retrieval

Shenghao Fu · Yukun Su · Fengyun Rao · Jing LYU · Xiaohua Xie · Wei-Shi Zheng

多模态检索与知识OpenReview 项目页

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

CycleManip: Enabling Cycle-based Manipulation via Effective History Perception and Understanding

Yi-Lin Wei · Haoran Liao · Yuhao Lin · Pengyue Wang · Zhizhao Liang · Guiliang Liu · Wei-Shi Zheng

多模态OpenReview 项目页

作者位次 #6/7CVPR 2026Poster· Computer Vision & Pattern Recognition

Long-RVOS: A Comprehensive Benchmark for Long-term Referring Video Object Segmentation

Tianming Liang · Haichao Jiang · Yuting Yang · Chaolei Tan · Shuai Li · Wei-Shi Zheng · Jian-Fang Hu

多模态评测与基准OpenReview 项目页

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

Bridging Domain Expertise and Generalization for Performance Estimation

Shuxuan Li · Zhilin Zhao · Quyu Kong · Wei-Shi Zheng

多模态理论与学习动力学OpenReview 项目页

作者位次 #4/5CVPR 2026Poster· Computer Vision & Pattern Recognition

SGS-Intrinsic: Semantic-Invariant Gaussian Splatting for Sparse-View Indoor Inverse Rendering

Jiahao Niu · Rongjia Zheng · Wenju Xu · Wei-Shi Zheng · Qing Zhang

多模态OpenReview 项目页

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

Refer-Agent: A Collaborative Multi-Agent System with Reasoning and Reflection for Referring Video Object Segmentation

Haichao Jiang · Tianming Liang · Wei-Shi Zheng · Jian-Fang Hu

智能体与工具多模态推理OpenReview 项目页

作者位次 #7/8CVPR 2026Poster· Computer Vision & Pattern Recognition

RehearseVLA: Simulated Post-Training for VLAs with Physically-Consistent World Model

Junjin Xiao · Yandan Yang · Xinyuan Chang · Ronghan Chen · Feng Xiong · Mu Xu · Wei-Shi Zheng · Qing Zhang

多模态强化学习与后训练社会与人本OpenReview 项目页

作者位次 #4/5CVPR 2026Poster· Computer Vision & Pattern Recognition

Learning Explicit Continuous Motion Representation for Dynamic Gaussian Splatting from Monocular Videos

Xuankai Zhang · Junjin Xiao · Shangwei Huang · Wei-Shi Zheng · Qing Zhang

多模态可解释性OpenReview 项目页

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

You Only Erase Once: Erasing Anything without Bringing Unexpected Content

Yixing Zhu · Qing Zhang · Wenju Xu · Wei-Shi Zheng

多模态OpenReview 项目页

作者位次 #4/5SIGGRAPH 2026Oral· Computer Graphics (Conference Track)

Generative Texture Filtering

Rongjia Zheng · Shangwei Huang · Lei Zhu · Wei-Shi Zheng · Qing Zhang

OpenReview

作者位次 #7/7ICRA 2026Oral· Robotics & Automation

OmniDexGrasp: Generalizable Dexterous Grasping via Foundation Model and Force Feedback

Yi-Lin Wei · Zhexi Luo · Yuhao Lin · Mu Lin · Zhizhao Liang · Shuoyu Chen · Wei-Shi Zheng

理论与学习动力学OpenReview

作者位次 #5/5IROS 2026Poster· Generative Diffusion Policies for Visual Navigation

RaFM-Nav: Risk-Aware Flow Matching Policy for Collision-Free Visual Navigation

Liang Li · Wenbo Wang · Jian-Jian Jiang · Jingke Meng · Wei-Shi Zheng

多模态Vision-Based NavigationOpenReview

作者位次 #7/7AAAI 2026Poster· Artificial Intelligence

Exploring Surround-View Fisheye Camera 3D Object Detection

Changcai Li · Wenwei Lin · Zuoxun Hou · Gang Chen · Wei Zhang · Huihui Zhou · Wei-Shi Zheng

OpenReview

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

TechCoach: Towards Technical-Point-Aware Descriptive Action Coaching

Yuan-Ming Li · An-Lan Wang · Ling-An Zeng · Kun-Yu Lin · Yu-Ming Tang · Wei-Shi Zheng

OpenReview

作者位次 #7/8AAAI 2026Poster· Artificial Intelligence

DCAC: Dynamic Class-Aware Cache Creates Stronger Out-of-Distribution Detectors

Yanqi Wu · Qichao Chen · Runhe Lai · Xinhua Lu · Jia-Xin Zhuang · Zhilin Zhao · Wei-Shi Zheng · Ruixuan Wang

OpenReview

Wei-Shi Zheng

获取完整研究档案

联系方式

2026 顶会论文

From Abstraction to Instantiation: Learning Behavioral Representation for Vision-Language-Action Model

VLANeXt: Recipes for Building Strong VLA Models

ObjEmbed: Towards Universal Multimodal Object Embeddings

Seg-ReSearch: Segmentation with Interleaved Reasoning and External Search

Beyond Mimicry: Learning Whole-Body Human-Humanoid Interaction from Human-Human Demonstrations

WeDetect: Fast Open-Vocabulary Object Detection as Retrieval

CycleManip: Enabling Cycle-based Manipulation via Effective History Perception and Understanding

Long-RVOS: A Comprehensive Benchmark for Long-term Referring Video Object Segmentation

Bridging Domain Expertise and Generalization for Performance Estimation

SGS-Intrinsic: Semantic-Invariant Gaussian Splatting for Sparse-View Indoor Inverse Rendering

Refer-Agent: A Collaborative Multi-Agent System with Reasoning and Reflection for Referring Video Object Segmentation

RehearseVLA: Simulated Post-Training for VLAs with Physically-Consistent World Model

Learning Explicit Continuous Motion Representation for Dynamic Gaussian Splatting from Monocular Videos

You Only Erase Once: Erasing Anything without Bringing Unexpected Content

Generative Texture Filtering

OmniDexGrasp: Generalizable Dexterous Grasping via Foundation Model and Force Feedback

RaFM-Nav: Risk-Aware Flow Matching Policy for Collision-Free Visual Navigation

Exploring Surround-View Fisheye Camera 3D Object Detection

TechCoach: Towards Technical-Point-Aware Descriptive Action Coaching

DCAC: Dynamic Class-Aware Cache Creates Stronger Out-of-Distribution Detectors

常见合作者