Research
My research focuses on vision-language-action models, embodied reasoning, and robot learning — building generalizable agents that can perceive, reason, and act in the physical world. * denotes equal contribution.
2026·3 papers
TiPToP: A Modular Planning-Based Robot Manipulation System
William Shen, Nishanth Kumar, Sahit Chintalapudi, Jie Wang, Christopher Watson, Edward S. Hu, Jing Cao, Dinesh Jayaraman, Leslie Pack Kaelbling, Tomás Lozano-Pérez
tl;drWe propose a planning-based robotics system that solves complex real-world manipulation tasks directly from raw pixels and natural-language commands. Validated 'in-the-wild' at GRASP Lab.
OmniGuide: Universal Guidance Fields for Enhancing Generalist Robot Policies
Yunzhou Song*, Long Le*, Yong-Hyun Park, Jie Wang, Junyao Shi, Lingjie Liu, Jiatao Gu, Eric Eaton, Dinesh Jayaraman, Kostas Daniilidis
tl;drWe propose a a flexible framework that improves VLA performance on Spatial Reasoning tasks by leveraging prior knowledge from 3D foundation models, semantic-reasoning VLMs, and human trajectory.
AAWR: Real World Reinforcement Learning of Active Perception Behaviors
Edward S. Hu*, Jie Wang*, Xingfang Yuan*, Fiona Luo, Muyao Li, Gaspard Lambrechts, Oleh Rybkin, Dinesh Jayaraman
tl;drWe propose a simple robot learning recipe leveraging privileged information to train active perception policies on real robots.
2025·3 papers
RoboArena: Distributed Real-World Evaluation of Generalist Robot Policies
RoboArena Team
tl;drA distributed real-world evaluation framework for generalist robot policies.
ZeroMimic: Distilling Robotic Manipulation Skills from Web Videos
Junyao Shi, Zhuolun Zhao, Tianyou Wang, Ian Pedroza, Amy Luo, Jie Wang, Jason Ma, Dinesh Jayaraman
tl;drLearning robotic manipulation skills from web videos with zero-shot generalization.
Visionary Co-Driver: LLMs Enhance Driver Risk Perception with ARHUD
Xiang Wei, Ziyue Lei, Jie Wang, Qi Zheng, Yingying Huang, Tianyi Zhang, Lingyun Sun
tl;drUsing LLMs and Vision foundation models to analyze autonomous driving road scene, modeling the behavior of pedestrians. Construct a HUD system to evaluate the driver interaction.
2024·1 paper
Real-time V2V Communication Network Cooperative Control System through Distributed Database,
Xinwen Zhu, Zihao Li, Yuxuan Jiang, Jiazhen Xu, Jie Wang, and Xuyang Ba
tl;drUsing distributed databases for collision avoidance, verified on Quanser Car at crossroad scenario.
Blog Posts & Reports
Evaluating pi0 in the Wild: Strengths, Problems, and the Future of Generalist Robot Policies
Jie Wang*, Matthew Leonard, Kostas Daniilidis, Dinesh Jayaraman, Edward S. Hu
tl;drWe vibe-check pi0 across 300 trials on various manipulation tasks, summarize the insights and our observations in this blog.