CoRL Spotlight Meta-Ctrl predicts robot plan failures, Llama 3 8B beats GPT-5.5 on VirtualHome
guyvdb · x · 2026-11-11
Meta-Ctrl, a CoRL 2026 Spotlight paper, predicts robot plan failures before the LLM task planner writes them, using exact inference with no sampling.
Notably, Llama 3 8B outperforms GPT-5.5 and Claude Opus 4.8 on the VirtualHome benchmark, showing a small model with the right method can beat larger frontier models on this task. Talk at 8:30 am, Poster #104, 10:30–12.
Related event: Meta-Ctrl Predicts Robot Plan Failures, Beating GPT-5.5(2 posts)→
More from Embodied
- Robot fails at folding a towel, reassuring roboticists frontier models won't eat robotics yet — chris_j_paxton · 2026-11-12
- Nuro podcast: manufacturing, charging, and regulation gate robotaxi mass adoption — R_D · 2026-11-12
- Cybercab rear-ended by human driver, researcher quips: the problem is the humans — chris_j_paxton · 2026-11-12
- HT-Policy Uses Heavy-Tailed Student-t Regression to Close Robot Policy Gap — chris_j_paxton · 2026-11-12
- NVIDIA GTC Berlin Side Meetup Balloons to 2,000 Signups for a 500-Cap Brewery — lukas_m_ziegler · 2026-11-12
- Lamport Robotics' Pincer1 Robotic Arm Priced at $1,199, Payable Only in SOL or USDC — R4nsack · 2026-11-12