Publications

An updated list of all publications can be found on my Google Scholar profile.

Action-Free Reasoning for Policy Generalization

Jaden Clark , Suvir Mirchandani, Dorsa Sadigh, Suneel Belkhale

ArXiv Preprint

TLDR: We propose a new way to train generalist robot polices from human video data via action reasoning.

Efficiently Generating Expressive Quadruped Behaviors via Language-Guided Preference Learning

Jaden Clark , Joey Hejna, Dorsa Sadigh

ICRA 2025

TLDR: We introduce a novel approach that leverages priors generated by pre-trained LLMs alongside the precision of preference learning to generate robot behaviors that closely align with human expectations.

Zero-shot Shark Tracking and Biometrics from Aerial Imagery

Chinmay Lalgudi, Mark Leone Jaden Clark , Sergio Madrigal-Mora, Mario Espinoza

ArXiv Preprint

TLDR: We demonstrate the pre-trained models can effectively track arbitrary shark species in various environments and be used to extract key biometrics.

Efficient Exploration for Embodied Question Answering

Allen Ren Jaden Clark , Anushri Dixit, Masha Itkina, Anirudha Majumdar, Dorsa Sadigh

RSS 2024

TLDR: We combine VLM semantic reasoning and rigorous uncertainty quantification to enable agents to efficiently explore relevant regions of unknown 3D environments, and stop to answer questions about them with calibrated confidence.

Online Path Repair: Adapting to Robot Failures in Multi-Robot Aerial Surveys

Jaden Clark , Kunal Shah, Mac Schwager

Robotics and Automation Letters, IROS 2024

TLDR: We propose a novel method to efficiently replan multi-robot aerial surveys online.

Learned Objectives for Game Theoretic Planning

Keiko Nagami* Jaden Clark *, Mac Schwager

IROS 2023: 1st Workshop on Multi-Agent Dynamic Games

TLDR: We show that using learned trajectory predictors as objectives decreases planning horizon and improves performance of game-theoretic planners.

Tail Control Enhances Gliding in Arboreal Lizards: An Integrative Study Using a 3D Geometric Model and Numerical Simulation

Jaden Clark , Christopher Clark, Timothy Higham

Integrative and Comparative Biology

TLDR: We propose a novel numerical simulation to study gliding flight and show that tail control plays a significant role in Draco flight control.