HKUST(GZ) lab lands 3 CoRL 2026 papers, unveils terrain-adaptive robot motion model
Scobleizer · x · 2026-09-06
HKUST(GZ)'s Junwei Liang lab announced 3 papers accepted at CoRL 2026:
- Perceptive Behavior Foundation Model: adapts human motion priors to robot-centric terrain. A single policy takes arbitrary flat-ground human-motion references (one-leg backflips, stair dances, obstacle crossings) and uses onboard vision to resolve footholds, swing clearance, and contact timing, without changing the raw kinematic command interface. Terrain-Conformal References (TCRS) supervise training offline, and a zero-initialized residual vision pathway applies corrections only where terrain demands. Live demo runs in-browser via MuJoCo WASM + ONNX Runtime.
- MeshMimic: geometry-aware humanoid motion learning through 3D scene reconstruction.
- Look Before You Move: agent-interface-aligned supervision for open-world mobile manipulation; code and models coming soon.
More from Embodied
- HKU's TILDE Distills Embodied Foundation Models into Robot Policies — hkuhk · 2026-10-23
- 10 of 12 Beta Robots Worked Without Fine-Tuning — Do We Still Need It? — micoolcho · 2026-10-23
- EmbodiedEvo lets robot agents self-train, banking reusable Skills and Lessons across tasks — jiqizhixin · 2026-10-23
- KAIST's FRED lifts robot policy success from 19.4% to 50% via self-distilled future video representations — kaist-ai · 2026-10-23
- GALAX Launches World's First RTX 5080 With Dual 12V-2x6 Connectors at $3000 — chemist_slime · 2026-10-23
- Figure prints 81 minutes of robot data per second, spent ~$8.1M on data last week — joecole · 2026-10-23