Publications

2026

RoboVista: Evaluating Vision Language Models for Diverse Robot Applications
Shuangyu Xie, Kaiyuan Chen, Ziyang Chen, Simeon Adebola, Yixuan Huang, Zehan Ma, Tianshuang Qiu, Wentao Yuan, Dhruv Shah, Pannag Sanketi, Ken Goldberg
Robotics: Science and Systems (RSS)
LAP: Language-Action Pre-Training Enables Zero-shot Cross-Embodiment Transfer
Lihan Zha, Asher Hancock, Mingtong Zhang, Tony Yin, Yixuan Huang, Dhruv Shah, Allen Ren, Anirudha Majumdar
Robotics: Science and Systems (RSS)
Long-Context Robot Imitation Learning by Focusing on Key History Frames
Max Mark, Jacky Liang, Maria Attarian, Chuyuan Fu, Debidatta Dwibedi, Aviral Kumar, Dhruv Shah
Robotics: Science and Systems (RSS)
Visual Verification Enables Inference-time Steering and Autonomous Policy Improvement
Mingtong Zhang, Dhruv Shah
Robotics: Science and Systems (RSS)
PolaRiS: Scalable Real-to-Sim Evaluations for Generalist Robot Policies
Arhan Jain, Mingtong Zhang, Kanav Arora, William Chen, Marcel Torne, Muhammad Irshad, Sergey Zakharov, Yue Wang, Sergey Levine, Chelsea Finn, Wei-Chiu Ma, Dhruv Shah, Abhishek Gupta, Karl Pertsch
Robotics: Science and Systems (RSS)
OmniVLA: An Omni-Modal Vision-Language-Action Model for Robot Navigation
Noriaki Hirose, Catherine Glossop, Dhruv Shah, Sergey Levine
IEEE International Conference on Robotics and Automation (ICRA)
What Matters in Orchestrating Robot Policies: A Systematic Study of Hierarchical VLA Agents
Jiaheng Hu, Mohit Shridhar, Cewu Lu, Dhruv Shah, Hao-Tien Chiang, Jie Tan, Annie Xie
arXiv preprint
MolmoB0T: Large-Scale Simulation Enables Zero-Shot Manipulation
Abhay Deshpande, Rose Hendrix, Dhruv Shah
arXiv preprint
Grounding Robot Generalization in Training Data via Retrieval-Augmented VLMs
Jensen Gao, Dorsa Sadigh, Sandy Huang, Dhruv Shah
arXiv preprint
AsyncVLA: An Asynchronous VLA for Fast and Robust Navigation on the Edge
Noriaki Hirose, Catherine Glossop, Dhruv Shah, Sergey Levine
arXiv preprint
OmniVLA: An Omni-Modal Vision-Language-Action Model for Robot Navigation
Noriaki Hirose, Catherine Glossop, Dhruv Shah, Sergey Levine
IEEE International Conference on Robotics and Automation (ICRA)
What Matters in RL-Based Methods for Object-Goal Navigation? An Empirical Study and A Unified Framework
Hongze Wang, Boyang Sun, Jiaxu Xing, Fan Yang, Marco Hutter, Dhruv Shah, Davide Scaramuzza, Marc Pollefeys
European Conference on Computer Vision (ECCV)
A Taxonomy for Evaluating Generalist Robot Policies
Jensen Gao, Suneel Belkhale, Sudeep Dasari, Ashwin Balakrishna, Dhruv Shah, Dorsa Sadigh
IEEE Robotics and Automation Letters (RA-L)

2025

Evaluating Gemini Robotics Policies in a Veo World Simulator
Gemini Team, others
CAST: Counterfactual Labels Improve Instruction Following in Vision-Language-Action Models
Catherine Glossop, William Chen, Arjun Bhorkar, Dhruv Shah, Sergey Levine
arXiv preprint
Towards Data-Driven Metrics for Social Robot Navigation Benchmarking
Pilar Bachiller-Burgos, Ulysses Bernardet, Luis Calderita V, Pranup Chhetri, Anthony Francis, Noriaki Hirose, Noé Pérez, Dhruv Shah, Phani Singamaneni, Xuesu Xiao, others
arXiv preprint
Text to Robotic Assembly of Multi Component Objects using 3D Generative AI and Vision Language Models
Alexander Kyaw, Richa Gupta, Dhruv Shah, Anoop Sinha, Kory Mathewson, Stefanie Pender, Sachin Chitta, Yotto Koga, Faez Ahmed, Lawrence Sass, others
Advances in Neural Information Processing Systems (NeurIPS)
Traversability-Aware Legged Navigation by Learning from Real-World Visual Data
Hongbo Zhang, Zhongyu Li, Xuanqi Zeng, Laura Smith, Kyle Stachowicz, Dhruv Shah, Linzhu Yue, Zhitao Song, Weipeng Xia, Sergey Levine, others
IEEE Transactions on Robotics (T-RO)
STEER: Flexible Robotic Manipulation via Dense Language Grounding
Laura Smith, Alex Irpan, Montserrat Arenas, Sean Kirmani, Dmitry Kalashnikov, Dhruv Shah, Ted Xiao
IEEE International Conference on Robotics and Automation (ICRA)
Gemini Robotics 1.5: Pushing the Frontier of Generalist Robots with Advanced Embodied Reasoning, Thinking, and Motion Transfer
Gemini Team, others
Technical Report
Vision Language Models Are In-Context Value Learners
Yecheng Ma, Joey Hejna, Chuyuan Fu, Dhruv Shah, Jacky Liang, Zhuo Xu, Sean Kirmani, Peng Xu, Danny Driess, Ted Xiao, others
International Conference on Learning Representations (ICLR)
Humanity's Last Exam
Long Phan, others
Technical Report
Learning to Drive Anywhere with Model-Based Reannotation
Noriaki Hirose, Lydia Ignatova, Kyle Stachowicz, Catherine Glossop, Sergey Levine, Dhruv Shah
IEEE Robotics and Automation Letters (RA-L)
Guiding Data Collection via Factored Scaling Curves
Lihan Zha, Apurva Badithela, Michael Zhang, Justin Lidard, Jeremy Bao, Emily Zhou, David Snyder, Allen Ren, Dhruv Shah, Anirudha Majumdar
arXiv preprint
Autonomous Mario Kart in the Wild: Lessons Learned from the Earth Rover Challenge at IROS 2024
Xuesu Xiao, Jie Tan, Michael Cho, David Hsu, Dhruv Shah, Joanne Truong, Ted Xiao, Naoki Yokoyama, Wenhao Yu, Tingnan Zhang, others
IEEE Robotics & Automation Magazine, Vol. 32, 189–196
Google Scholar