JW
Jiajun Wu
cs.CVcs.AIcs.LGcs.ROcs.GRcs.CLstat.MLcs.SDeess.AScs.HC
On Valency
published · living versionsW_gfc2k2gw·v1 · currentpublished
BEHAVIOR-Spatial Benchmark: Evaluating Spatial Understanding for Robotics
with Sirui Chen, Huang Huang, Qineng Wang, Wenlong Huang +3
1 version
W_kqtrhgqx·v1published
W_jpwn4st9·v1published
Preprints & journals
309 papers in the corpus · 2012–2026BrickBench: Evaluating Agentic Brick Design2610.12452v1 · Peter Kulits, Yiqing Xu, R. Kenny Jones et al.2026 · 0 citationsarXiv
RoboRender: Robot-Oriented Video Generation for Visual Sim-to-Real Transfer2610.09254v1 · Huang Huang, Wensi Ai, Ziyu Chen et al.2026 · 0 citationsarXiv
Cross-Embodiment Robot Foundation World Models with Latent Actions2610.10846v1 · Huang Huang, Sriram Yenamandra, Arjun Majumdar et al.2026 · 0 citationsarXiv
OpenWAM: An Open Framework for Composable World-Action Models2610.07922v1 · Heng Yu, David D. Yuan, Juze Zhang et al.2026 · 0 citationsarXiv
Co-Evolving Robot Orchestrators and Policies through Deployment2610.09228v1 · Xilun Zhang, Maggie Wang, Erik Bauer et al.2026 · 0 citationsarXiv
MobileVISTA: Generative Data Augmentation for Pose Generalization in Mobile Manipulation2610.07511v1 · Suzannah Wistreich, Stephen Tian, Isabella Huang et al.2026 · 0 citationsarXiv
Robot Learning with Visual Predicted Force2610.04741v2 · Haonan Chen, Feiyang Wu, Yuxiang Ma et al.2026 · 0 citationsarXiv
4DCodeBench: Benchmarking Agents on Inverse Graphics of Dynamic Scenes2610.03715v1 · Ruihong Shen, Ziga Kovacic, Peter Kulits et al.2026 · 0 citationsarXiv
DITTO-X: Forward and Reverse Teleoperation for Dexterous Manipulation and Human Intervention2610.00781v2 · Zhanpeng He, Joaquin Palacios, Zhangyu Wang et al.2026 · 0 citationsarXiv
ECoMEM: Explicit Concept Memory for Memory-Dependent Robot Control2610.00801v1 · Yize Liu, Ke Wang, Mac Schwager et al.2026 · 0 citationsarXiv
TMem: Learning Test-Time Memory for Robotics2609.36720v1 · Yize Liu, Huang Huang, Yining Hong et al.2026 · 0 citationsarXiv
DexAgent: An Agentic Human2Sim2Robot Framework for Dexterous Manipulation with Self-Evolving Tool Library2609.35318v2 · Youhui Wang, Yunzhu Li, Li Fei-Fei et al.2026 · 0 citationsarXiv
Objectively Measured Life Space Using Participants' Mobile Phones: Cross-Sectional Study.42766793 · Odden, Michelle C, Tan, Annabel X, Lai, Sylvie Dobrota et al.2026 · 0 citationsJMIR formative research. 2026;10:e73128
MindTopo: Can Foundation Models Reason in Topological Space?2609.11900v1 · Yunfei Ge, Anbang Liu, Qineng Wang et al.2026 · 0 citationsarXivon Valency
MetaRSI / RSI2: A Meta-Recursive Self-Improving System for Recursive Self-Improving Systems Themselves2609.06396v2 · Zihan Tan, Leixin Sun, Zitong Shi et al.2026 · 0 citationsarXiv
Kirin: Animal Motion Generation from In-the-Wild Video2609.01823v1 · Brian Nlong Zhao, Zhuoyang Pan, James M. Rehg et al.2026 · 0 citationsarXiv
One Demonstration, Many Objects: Generalizing Manipulation via Local Contact Geometry2609.01938v2 · Satvik Sharma, Samrat Sahoo, Huang Huang et al.2026 · 0 citationsarXiv
Visual General Intelligence: A White Paper2608.25924v1 · Hirokatsu Kataoka, Yoshihiro Fukuhara, Yonglong Tian et al.2026 · 0 citationsarXiv
TrAct: Bridging Robot Control and Visual Prediction with Visual Tracks2608.24101v4 · Zhi Cao, Howard Ji, Kevin Zhang et al.2026 · 0 citationsarXiv
Masked Visual Actions for Unified World Modeling2607.19343v1 · Hadi Alzayer, Wenlong Huang, Haonan Chen et al.2026 · 0 citationsarXiv
A vision foundation model for single-cell biology via spatial gene cartography2607.14163v1 · Ridvan Yesiloglu, Sakib Mostafa, James Zou et al.2026 · 0 citationsarXiv
APIVOT: Adaptive Planning with Interleaved Vision-Language Thoughts2607.08024v1 · Emily Jin, Joy Hsu, Yiqing Xu et al.2026 · 0 citationsarXiv
CoStream: Composing Simple Behaviors for Generalizable Complex Manipulation2606.26423v2 · Haonan Chen, Yuxiang Ma, Stephen Tian et al.2026 · 0 citationsarXiv
InSight: Self-Guided Skill Acquisition via Steerable VLAs2606.24884v2 · Maggie Wang, Lars Osterberg, Stephen Tian et al.2026 · 0 citationsarXiv
DIRECT: When and Where Should You Allocate Test-Time Compute in Embodied Planners?2606.12402v2 · Jadelynn Dao, Milan Ganai, Yasmina Abukhadra et al.2026 · 0 citationsarXiv
Aggregating LLM-Based Weak Verifiers for Spatial Layout Generation2606.05268v1 · Sharon Zhang, R. Kenny Jones, Jiajun Wu et al.2026 · 0 citationsarXiv
Linear Scaling Video VLMs for Long Video Understanding2605.31598v1 · Cristobal Eyzaguirre, Jiajun Wu, Juan Carlos Niebles2026 · 0 citationsarXiv
Planning with the Views2605.29563v4 · Kangrui Wang, Linjie Li, Zhengyuan Yang et al.2026 · 0 citationsarXiv
GPIC: A Giant Permissive Image Corpus for Visual Generation2605.30341v1 · Keshigeyan Chandrasegaran, Kyle Sargent, Suchir Agarwal et al.2026 · 0 citationsarXiv
NeuROK: Generative 4D Neural Object Kinematics2605.30347v1 · Chen Geng, Guangzhao He, Yue Gao et al.2026 · 0 citationsarXiv
Fishbone: From One 3D Asset to a Million Controllable Edits2605.24805v1 · Yumeng He, Xiaoying Wang, Peihao Li et al.2026 · 0 citationsarXiv
ESI-Bench: Towards Embodied Spatial Intelligence that Closes the Perception-Action Loop2605.18746v2 · Yining Hong, Jiageng Liu, Han Yin et al.2026 · 0 citationsarXiv
StereoPolicy: Improving Robotic Manipulation Policies via Stereo Perception2605.09989v3 · Evans Han, Yunfan Jiang, Yingke Wang et al.2026 · 0 citationsarXiv
World Model for Robot Learning: A Comprehensive Survey2605.00080v1 · Bohan Hou, Gen Li, Jindou Jia et al.2026 · 1 citationarXiv
AnyLift: Scaling Motion Reconstruction from Internet Videos via 2D Diffusion2604.17818v1 · Hongjie Li, Heng Yu, Jiaman Li et al.2026 · 0 citationsarXiv
Using large language models for embodied planning introduces systematic safety risks2604.18463v2 · Tao Zhang, Kaixian Qu, Zhibin Li et al.2026 · 0 citationsarXiv
RAGEN-2: Reasoning Collapse in Agentic RL2604.06268v1 · Zihan Wang, Chi Gui, Xing Jin et al.2026 · 0 citationsarXiv
Self-Consistency for LLM-Based Motion Trajectory Generation and Verification2603.29301v1 · Jiaju Ma, R. Kenny Jones, Jiajun Wu et al.2026 · 0 citationsarXiv
IMPASTO: Integrating Model-Based Planning with Learned Dynamics Models for Robotic Oil Painting Reproduction2603.29315v1 · Yingke Wang, Hao Li, Yifeng Zhu et al.2026 · 0 citationsarXiv
GenFusion: Feed-forward Human Performance Capture via Progressive Canonical Space Updates2603.28997v1 · Youngjoong Kwon, Yao He, Heejung Choi et al.2026 · 0 citationsarXiv
CaP-X: A Framework for Benchmarking and Improving Coding Agents for Robot Manipulation2603.22435v2 · Letian Fu, Justin Yu, Karim El-Refai et al.2026 · 0 citationsarXiv
Physion-Eval: Evaluating Physical Realism in Generated Video via Human Reasoning2603.19607v1 · Qin Zhang, Peiyu Jing, Hong-Xing Yu et al.2026 · 0 citationsarXiv
RealWonder: Real-Time Physical Action-Conditioned Video Generation2603.05449v1 · Wei Liu, Ziyu Chen, Zizhang Li et al.2026 · 0 citationsarXiv
Thinking with Spatial Code for Physical-World Video Reasoning2603.05591v1 · Jieneng Chen, Wenxin Ma, Ruisheng Yuan et al.2026 · 0 citationsarXiv
Learning from Trials and Errors: Reflective Test-Time Planning for Embodied LLMs2602.21198v3 · Yining Hong, Huang Huang, Manling Li et al.2026 · 0 citationsarXiv
Neuro-Symbolic Decoding of Neural Activity2603.03343v1 · Yanchen Wang, Joy Hsu, Ehsan Adeli et al.2026 · 0 citationsarXiv
SurfPhase: 3D Interfacial Dynamics in Two-Phase Flows from Sparse Videos2602.11154v1 · Yue Gao, Hong-Xing Yu, Sanghyeon Chang et al.2026 · 0 citationsarXiv
PerpetualWonder: Long-Horizon Action-Conditioned 4D Scene Generation2602.04876v2 · Jiahao Zhan, Zizhang Li, Hong-Xing Yu et al.2026 · 0 citationsarXiv
Theory of Space: Can Foundation Models Construct Spatial Beliefs through Active Exploration?2602.07055v1 · Pingyue Zhang, Zihan Huang, Yue Wang et al.2026 · 1 citationarXiv
Deep Sketch-Based 3D Modeling: A Survey2603.03287v1 · Alberto Tono, Jiajun Wu, Gordon Wetzstein et al.2026 · 2 citationsarXiv
Career total: 417 works. 309 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.