Hongtao Wang

Perceptive General Motion Tracking pipeline for humanoid robots that learns terrain adaptation from independently selected motion references and terrains, providing a unified policy for terrain-adaptive locomotion, diverse whole-body behaviors, and teleoperation in complex environments.

Robots using the SWAP model achieved record-breaking parkour feats, including a 2.13 m jump and a 1.63 m climb, demonstrating the power of symmetry in robotic learning.

Gaze behaviors learned through reinforcement alone can lead to unprecedented humanoid locomotion capabilities, including a record 1.2m gap traversal.

LLM agents are alarmingly susceptible to memory poisoning via conversational attacks, achieving 95% success rates even against agents with selective memory mechanisms.

LLMs can drastically improve entity resolution accuracy, but only if you intelligently integrate them into a global graph refinement process that minimizes query costs.