Researcher — paper.dinq.me

2026 顶会论文

作者位次 #9/11ICLR 2026Poster· Computer Vision / Vision Models & Multimodal

ENACT: Evaluating Embodied Cognition with World Modeling of Egocentric Interaction

Qineng Wang · Wenlong Huang · Yu Zhou · Hang Yin · Tianwei Bao · Jianwen Lyu · Weiyu Liu · Ruohan Zhang · Jiajun Wu · Li Fei-Fei · Manling Li

多模态评测与基准OpenReview

作者位次 #12/14ICLR 2026Poster

MoMaGen: Generating Demonstrations under Soft and Hard Constraints for Multi-Step Bimanual Mobile Manipulation

Chengshu Li · Mengdi Xu · Arpit Bahety · Hang Yin · Yunfan Jiang · Huang Huang · Josiah Wong · Sujay Garlanka · Cem Gokmen · Ruohan Zhang · Weiyu Liu · Jiajun Wu · Roberto Martín-Martín · Li Fei-Fei

OpenReview

作者位次 #12/14ICLR 2026Poster· Computer Vision / Vision Models & Multimodal

Theory of Space: Can Foundation Models Construct Spatial Beliefs through Active Exploration?

Pingyue Zhang · Zihan Huang · Yue Wang · Jieyu Zhang · Letian Xue · Zihan Wang · Qineng Wang · Keshigeyan Chandrasegaran · Ruohan Zhang · Yejin Choi · Ranjay Krishna · Jiajun Wu · Li Fei-Fei · Manling Li

多模态理论与学习动力学OpenReview

作者位次 #12/14ICLR 2026Poster

Spatial Mental Modeling from Limited Views

Qineng Wang · Baiqiao Yin · Pingyue Zhang · Jianshu Zhang · Kangrui Wang · Zihan Wang · Jieyu Zhang · Keshigeyan Chandrasegaran · Han Liu · Ranjay Krishna · Saining Xie · Jiajun Wu · Li Fei-Fei · Manling Li

OpenReview

作者位次 #5/5ICLR 2026Poster

Product of Experts for Visual Generation

Yunzhi Zhang · Carson Murtuza-Lanier · Zizhang Li · Yilun Du · Jiajun Wu

多模态OpenReview

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

ROSETTA: Constructing Code-Based Reward from Unconstrained Language Preference

Sanjana Srivastava · Kangrui Wang · Yung-Chieh Chan · Tianyuan Dai · Manling Li · Ruohan Zhang · Mengdi Xu · Jiajun Wu · Li Fei-Fei

对齐与偏好代码OpenReview

作者位次 #4/4ICLR 2026Poster· Applications / Neuroscience, Cognitive Science

Neuro-Symbolic Decoding of Neural Activity

Yanchen Wang · Joy Hsu · Ehsan Adeli · Jiajun Wu

代码OpenReview

作者位次 #6/7ICLR 2026Poster· Computer Vision / 3D Rendering & Reconstruction

GenFusion: Feed-forward Human Performance Capture via Progressive Canonical Space Updates

YoungJoong Kwon · Yao He · Hee Jung Choi · Chen Geng · Zhengmao Liu · Jiajun Wu · Ehsan Adeli

多模态社会与人本OpenReview

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

Choreographing a World of Dynamic Objects

Yanzhe Lyu · Chen Geng · Karthik Dharmarajan · Yunzhi Zhang · Hadi Alzayer · Shangzhe Wu · Jiajun Wu

多模态OpenReview 项目页

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

AnyLift: Scaling Motion Reconstruction from Internet Videos via 2D Diffusion

Hongjie Li · Heng Yu · Jiaman Li · Hong-Xing Yu · Ehsan Adeli · C. Karen Liu · Jiajun Wu

多模态OpenReview 项目页

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

WonderZoom: Multi-Scale 3D World Generation

Jin Cao · Hong-Xing Yu · Jiajun Wu

多模态OpenReview 项目页

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

NeuROK: Generative 4D Neural Object Kinematics

Chen Geng · Guangzhao He · Yue Gao · Yunzhi Zhang · Shangzhe Wu · Jiajun Wu

多模态OpenReview 项目页

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

VLIC: Vision-Language Models As Perceptual Judges for Human-Aligned Image Compression

Kyle Sargent · Ruiqi Gao · Philipp Henzler · Charles Herrmann · Aleksander Holynski · Li Fei-Fei · Jiajun Wu · Jason Y. Zhang

多模态对齐与偏好效率与系统OpenReview 项目页

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

ART: Articulated Reconstruction Transformer

Zizhang Li · Cheng Zhang · Zhengqin Li · Henry Howard-Jenkins · Zhaoyang Lv · Chen Geng · Jiajun Wu · Richard Newcombe · Jakob Engel · Zhao Dong

多模态OpenReview 项目页

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

Coupled Diffusion Sampling for Training-Free Multi-View Image Editing

Hadi Alzayer · Yunzhi Zhang · Chen Geng · Jia-Bin Huang · Jiajun Wu

多模态OpenReview 项目页

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

PerpetualWonder: Long-horizon Action-conditioned 4D Scene Generation

Jiahao Zhan · Zizhang Li · Hong-Xing Yu · Jiajun Wu

多模态OpenReview 项目页

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

Dream2Flow: Bridging Video Generation and Open-World Manipulation with 3D Object Flow

Karthik Dharmarajan · Wenlong Huang · Jiajun Wu · Li Fei-Fei · Ruohan Zhang

多模态OpenReview

作者位次 #6/6ICRA 2026Oral· Robotics & Automation

Learning Composable Skills by Discovering Spatial and Temporal Structure with Foundation Models

Neil Nie · Wenlong Huang · Jiayuan Mao · Li Fei-Fei · Weiyu Liu · Jiajun Wu

OpenReview

作者位次 #4/5ICRA 2026Oral· Robotics & Automation

Retargeting Matters: General Motion Retargeting for Humanoid Motion Tracking

João Pedro Araújo · Yanjie Ze · Pei Xu · Jiajun Wu · C. Karen Liu

社会与人本OpenReview

作者位次 #7/9ICRA 2026Oral· Robotics & Automation

IMPASTO: Integrating Model-Based Planning with Learned Dynamics Models for Robotic Oil Painting Reproduction

Yingke Wang · Hao Li · Yifeng Zhu · Hong-Xing Yu · Ken Goldberg · Li Fei-Fei · Jiajun Wu · Yunzhu Li · Ruohan Zhang

推理OpenReview

作者位次 #8/9ICRA 2026Oral· Robotics & Automation

Twist2 : Scalable, Portable, and Holistic Humanoid Data Collection System

Yanjie Ze · Siheng Zhao · Weizhuo Wang · Angjoo Kanazawa · Rocky Duan · Pieter Abbeel · Guanya Shi · Jiajun Wu · C. Karen Liu

社会与人本OpenReview

作者位次 #5/6ICRA 2026Oral· Robotics & Automation

Phys2Real: Fusing VLM Priors with Interactive Online Adaptation for Uncertainty-Aware Sim-to-Real Manipulation

Maggie Wang · Stephen Tian · Aiden Swann · Ola Shorinwa · Jiajun Wu · Mac Schwager

多模态OpenReview

作者位次 #9/10AAAI 2026Poster· Artificial Intelligence

10 Open Challenges Steering the Future of Vision-Language-Action Models

Soujanya Poria · Navonil Majumder · Chia-Yu Hung · Amir Ali Bagherzadeh · Chuan Li · Kenneth Kwok · Ziwei Wang · Cheston Tan · Jiajun Wu · David Hsu

可解释性多模态OpenReview

一作AAAI 2026Poster· Artificial Intelligence

Discovering Hybrid World Representations with Co-Evolving Foundation Models

Jiajun Wu · Yunzhi Zhang · Hong-Xing Yu · Joy Hsu · Jiayuan Mao

可解释性OpenReview

Jiajun Wu

获取完整研究档案

联系方式

2026 顶会论文

ENACT: Evaluating Embodied Cognition with World Modeling of Egocentric Interaction

MoMaGen: Generating Demonstrations under Soft and Hard Constraints for Multi-Step Bimanual Mobile Manipulation

Theory of Space: Can Foundation Models Construct Spatial Beliefs through Active Exploration?

Spatial Mental Modeling from Limited Views

Product of Experts for Visual Generation

ROSETTA: Constructing Code-Based Reward from Unconstrained Language Preference

Neuro-Symbolic Decoding of Neural Activity

GenFusion: Feed-forward Human Performance Capture via Progressive Canonical Space Updates

Choreographing a World of Dynamic Objects

AnyLift: Scaling Motion Reconstruction from Internet Videos via 2D Diffusion

WonderZoom: Multi-Scale 3D World Generation

NeuROK: Generative 4D Neural Object Kinematics

VLIC: Vision-Language Models As Perceptual Judges for Human-Aligned Image Compression

ART: Articulated Reconstruction Transformer

Coupled Diffusion Sampling for Training-Free Multi-View Image Editing

PerpetualWonder: Long-horizon Action-conditioned 4D Scene Generation

Dream2Flow: Bridging Video Generation and Open-World Manipulation with 3D Object Flow

Learning Composable Skills by Discovering Spatial and Temporal Structure with Foundation Models

Retargeting Matters: General Motion Retargeting for Humanoid Motion Tracking

IMPASTO: Integrating Model-Based Planning with Learned Dynamics Models for Robotic Oil Painting Reproduction

Twist2 : Scalable, Portable, and Holistic Humanoid Data Collection System

Phys2Real: Fusing VLM Priors with Interactive Online Adaptation for Uncertainty-Aware Sim-to-Real Manipulation

10 Open Challenges Steering the Future of Vision-Language-Action Models

Discovering Hybrid World Representations with Co-Evolving Foundation Models

常见合作者