Huang Huang

Papers

Total Citations

H-Index

About

Huang Huang is a robotics researcher whose work sits at the intersection of robot manipulation, embodied AI, and large-scale foundation models applied to real-world robotic systems. Their research tackles some of the field's most challenging problems: enabling robots to intelligently search for hidden objects in cluttered environments and rapidly adapt to novel tasks from minimal demonstration. A central thread in Huang's work is **mechanical search** — the problem of moving objects to locate a fully occluded target. Their 2023 paper on shelf-based mechanical search (11 citations) introduced efficient stacking and destacking strategies, while a companion paper leveraged large vision and language models to inject semantic reasoning into the search process (4 citations), demonstrating that object-relationship knowledge meaningfully reduces search time. Perhaps most ambitiously, Huang's ICRT work (2025, 5 citations) advances in-context imitation learning through a causal transformer that autoregressively models sensorimotor trajectories — images, proprioception, and actions — enabling robots to generalize to new tasks from just a handful of demonstration examples, analogous to few-shot prompting in language models. Collectively, Huang's contributions reflect a sophisticated vision: building robots that reason semantically, search intelligently, and learn efficiently from context.