CoRL 2026 Spotlight:Meta-Ctrl 用 Llama 3 8B 预判机器人计划失败,胜过 GPT-5.5
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.
所属事件:Meta-Ctrl 提前预测机器人计划失败,小模型胜 GPT-5.5(2 条相关)→
「具身」频道最新
- 机器人折毛巾现场翻车,机器人学家看完松了口气 — chris_j_paxton · 2026-11-12
- Nuro 播客:自动驾驶规模化瓶颈在产能、基建与监管 — R_D · 2026-11-12
- Cybercab 被追尾,研究员吐槽:最危险的是人类司机 — chris_j_paxton · 2026-11-12
- 新论文用重尾 Student-t 回归缩小机器人策略的回归与生成差距 — chris_j_paxton · 2026-11-12
- GTC柏林场外派对失控:原定百人小聚,2000人报名挤爆啤酒厂 — lukas_m_ziegler · 2026-11-12
- Lamport Robotics 机械臂 Pincer1 售 $1199,支持 SOL/USDC 支付 — R4nsack · 2026-11-12