Intention Distillation lifts GR00T success from 64% to 85% on SimplerEnv
POSTECH · hf · 2026-08-31
POSTECH proposes Intention Distillation (INDI): during training a frozen VLM teacher distills behavior-level intent from the instruction, a coarse action summary, and execution video; the deployed VLA recovers this multimodal intent at an intermediate decoder layer to organize action prediction.
Results:
- GR00T-N1.7: 64.3% → 84.7% on SimplerEnv-Bridge
- 64.1% → 70.3% on RoboCasa Kitchen
- Consistent gains for π₀.₅ on both benchmarks
- Real-world average success 62.0% → 68.7%, up to 12pp on longer-horizon tasks
Analyses show the recovered latent captures behavior objective and execution progress.
More from Embodied
- Peking University's SimForcing distills simulation motion priors into robot world models — PekingUniversity · 2026-10-16
- NVIDIA and Mercedes-Benz Expand Partnership on Next-Gen Automated Driving — nvidia · 2026-10-16
- ~25,000 Humanoid Robots Shipped in H1 2026, Over 95% from Chinese Vendors — ingliguori · 2026-10-16
- openpilot brings stoplight-stopping autonomy to a 2019 Corolla — k7agar · 2026-10-16
- Hironobu Fujiyoshi publishes deck: from AI agents to Agentic Robotics — HirokatuKataoka · 2026-10-16
- CoDA co-evolves simulation and robot policies via shared failure memory, lifting OOD success from 5.3% to 27.6% — PLAN-Lab · 2026-10-16