CoRL 2026: Meta-Ctrl predicts robot plan failures before the LLM planner writes them
guyvdb · x · 2026-11-11
Meta-Ctrl, a CoRL 2026 Spotlight paper, uses exact inference (no sampling) to predict robot plan failures before the LLM task planner commits to them. On VirtualHome, Llama 3 8B outperforms GPT-5.5 and Claude Opus 4.8. Spotlight talk at 8:30 am, poster #104.
Related event: Meta-Ctrl Predicts Robot Plan Failures, Beating GPT-5.5(2 posts)→
More from Embodied
- Open-source dual-arm robot solves tangram puzzles with 90 demos, ~60% success — DanGrover · 2026-11-12
- Robotics has three regional playbooks: China volume, Europe inspection, US pilots — ingliguori · 2026-11-12
- 3,500 Laser-Armed AI Submarine Robots Patrol Norwegian Salmon Farms — philfung · 2026-11-12
- Model Autonomously Designs a Surgical-Robot-Style Robotic Arm CAD After 75 Minutes — _Stocko_ · 2026-11-12
- Dev releases local world model turning any image into interactive video, runs on RTX 3060 — lucidml_lover · 2026-11-12
- RoboRisk benchmark shows foundation models pose high harm rates in robotics; LEASH harness cuts risk — UoLiverpool · 2026-11-12