|
Hi I'm Dylan! I'm a masters student in the Berkeley Artificial Intelligence Research (BAIR) Lab, at UC Berkeley, advised by Jitendra Malik. I'm graduating Spring 2025, and currently looking for full-time roles in robotics, agents and computer vision. I graduated from the M.E.T program at UC Berkeley in 2024, recieving a B.S in Electrical Engineering and Computer Science and a B.S in Business Administration. I'm an avid whitetater kayaker and freeride skier for the Cal Ski Team. |
|
ResearchMy research interests include bridging the gap between robotic policies and the rich space of language agents. |
|
End-to-End Navigation with VLMs: Transforming Spatial Reasoning into Question-Answering
Dylan Goetting, Himanshu Gaurav Singh, Antonio Loquercio arXiv, 2024 project page / arXiv / video / code VLMnav: an embodied framework to transform a Vision and Language Model (VLM) into an end-to-end navigation policy. |
|
SSEAL: Self-Supervised Explorative Agent Learning
Evan Frick, Dylan Goetting, Dhruv Gautam Under review at ICML, 2025 1st place winner at Berkeley RDI's LLM Agents MOOC Hackathon (3000+ participants) paper / code / demo A novel framework for agents to autonomously explore their environment and synthesize learnings for downstream performance. |
|
VLA as Tools: Exploring the Space of Agentic Robot Generalists
Dylan Goetting 2024 paper A proposed system in which central planning agent, powered by a Large Language Model (LLM), interacts with the environment by iteratively prompting a VLA model. Through a carefully designed feedback module, the LLM can observe the outcome of such robotic trajectory, and use this information for downstream tasks. |
AdventuresI like to explore the world and document my adventures. Some videos are highlights from my YouTube channel. 
|
|
Template adapted from Jon Barron |