Carl Qi

Carl (Hanwen) Qi

I am a Ph.D. student at the University of Texas at Austin, where I am advised by Prof. Amy Zhang.

Pror to UT, I obtained my Master's degree at CMU, where I was advised by Prof. David Held. I obtained my undergraduate degree in CS and Applied Math at UC Berkeley, where I was fortunate to work with Prof. Pieter Abbeel and Prof. Aditya Grover.

carlq@utexas.edu / CV / LinkedIn / Google Scholar

News and Updates

May. 2026: I started my internship at Amazon, working on training foundational reward models for VLAs.

Jan. 2026: Our paper on VLM for robotic failure reasoning is accepted to ICLR 2026.

Dec. 2025: Two papers on entity-centric reinforcement learning and world modeling are accepted to both WMW (oral) and ICLR 2026.

Aug. 2025: I concluded my internship at Amazon Robotics, where I fine-tuned VLMs for failure reasoning.

Jan. 2025: Our paper on Entity-Centric Diffuser is accepted to ICLR 2025.

Research

I'm broadly interested in Reinforcement Learning, Computer Vision, and Robotics. My specific interests include object-centric learning, long-horizon reasoning, and generalization. My long-term research goal is to allow autonomous agents to act and learn in unstructured real world environments.

Preprints

	AnchorQ: Sample-Efficient Reinforcement Learning for Policy Improvement via Flow-Reversed Action Anchors Carl Qi, Weijun Dong, Xiaojie Wang, Peiyi Chen, Rahul Sajnani, Mingyuan Zhang, Amy Zhang, Jose Barreiros, Manikatan Nambi, Lillian J. Ratliff, Dylan Randle Preprint, 2026 Paper / Project Page
	Foresight: Iterative Reasoning About Clues that Matter for Navigation Arthur Zhang, Carl Qi, Donne Su, Xiangyun Meng, Amy Zhang, Joydeep Biswas Preprint, 2026 Paper / Project Page

Publications Selected All

	Self-Refining Vision Language Model for Robotic Failure Detection and Reasoning Carl Qi, Xiaojie Wang, Silong Yong, Stephen Sheng, Huitan Mao, Sriram Srinivasan, Manikantan Nambi, Amy Zhang, Yesh Dattatreya International Conference on Learning Representations (ICLR), 2026 Paper / Project Page
	VLLR: Generalizable Dense Reward for Long-Horizon Robotic Tasks Silong Yong, Stephen Sheng, Carl Qi, Xiaojie Wang, Evan Sheehan, Anurag Shivaprasad, Yaqi Xie, Katia Sycara, Yesh Dattatreya IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2026 Paper / Project Page
	Hierarchical Entity-centric Reinforcement Learning with Factored Subgoal Diffusion Dan Haramati, Carl Qi, Tal Daniel, Amy Zhang, Aviv Tamar, George Konidaris International Conference on Learning Representations (ICLR), 2026 World Modeling Workshop (WMW), 2026 Oral Paper / Project Page
	Latent Particle World Models: Self-supervised Object-centric Stochastic Dynamics Modeling Tal Daniel, Carl Qi, Dan Haramati, Amir Zadeh, Chuan Li, Aviv Tamar, Deepak Pathak, David Held International Conference on Learning Representations (ICLR), 2026 Oral (Top 1.18%) World Modeling Workshop (WMW), 2026 Oral Paper / Project Page
	EC-Diffuser: Multi-Object Manipulation via Entity-Centric Behavior Generation Carl Qi, Dan Haramati, Tal Daniel, Aviv Tamar, Amy Zhang International Conference on Learning Representations (ICLR), 2025 Paper / Project Page / Code
	Null Counterfactual Factor Interactions for Goal-Conditioned Reinforcement Learning Caleb Chuck, Fan Feng, Carl Qi, Chang Shi, Siddhant Agarwal, Amy Zhang, Scott Niekum International Conference on Learning Representations (ICLR), 2025 Paper
	Robot Air Hockey: A Manipulation Testbed for Robot Learning with Reinforcement Learning Caleb Chuck, Carl Qi, Michael Joseph Munje, Shuozhe Li, Max Rudolph, Chang Shi, Siddhant Agarwal, Harshit Sikchi, Abhinav Peri, Sarthak Dayal, Evan Kuo, Kavan Mehta, Anthony Wang, Peter Stone, Amy Zhang, Scott Niekum ICRA Workshop Manipulation Skills, 2024 Paper / Project Page / Code (coming soon)
	Learning Generalizable Tool-use Skills through Trajectory Generation Carl Qi, Yilin Wu, Lifan Yu, Haoyue, Liu, Bowen Jiang, Xingyu Lin, David Held IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2024 Paper / Project Page / Code
	Planning with Spatial-Temporal Abstraction from Point Clouds for Deformable Object Manipulation Xingyu Lin, Carl Qi, Yunchu Zhang, Zhiao Huang, Katerina Fragkiadaki, Yunzhu Li, Chuang Gan, David Held Conference on Robot Learning (CoRL), 2022 Paper / OpenReview / Project Page / Code
	Learning Closed-loop Dough Manipulation using a Differentiable Reset Module Carl Qi, Xingyu Lin, David Held IEEE Robotics and Automation Letters (RA-L), 2022 Paper / Project Page / Code Covered by [The Washington Post] [CMU SCS News (robots roll dough)]
	Imitating, Fast and Slow: Robust learning from demonstrations via decision-time planning Carl Qi, Pieter Abbeel, Aditya Grover Preprint, 2022 Paper

Teaching

	TA, 10-418/618: ML for Structured Data, Spring 2022 TA, 10-725: Convex Optimization, Fall 2021
	Instructor, CS188: Artificial Intelligence, Summer 2021 TA, CS188: Artificial Intelligence, Spring 2021 TA, CS188: Artificial Intelligence, Fall 2020 TA, CS188: Artificial Intelligence, Spring 2020 TA, CS188: Artificial Intelligence, Fall 2019

Website source taken from here.