William Chen

Papers

Total Citations

H-Index

About

William Chen is an emerging researcher at the intersection of robotics, computer vision, and artificial intelligence, with a focus on leveraging large language and vision-language models to enhance robot perception and learning. His work addresses a fundamental challenge in autonomous systems: endowing robots with the kind of common-sense world knowledge that humans acquire naturally. Chen's most notable contribution, "Vision-Language Models Provide Promptable Representations for Reinforcement Learning" (2024), proposes a groundbreaking approach that harnesses the rich world knowledge encoded in vision-language models to accelerate reinforcement learning, moving agents beyond learning behaviors entirely from scratch. Complementing this, his 2022 work on 3D scene understanding demonstrates how pre-trained language models can bridge the gap between robotic perception and human-level contextual reasoning in household environments. His 2023 paper further extends this capability to both indoor and outdoor settings through language-enabled spatial ontologies, addressing the complexity of real-world deployment. With a growing citation record across three publications totaling 13 citations, Chen is establishing himself as a promising voice in embodied AI. His research is particularly relevant to students interested in robot learning, semantic scene understanding, and the practical application of foundation models to real-world autonomous systems.