MolmoAct 2 tops robot board at 46% success with just 300 demos
DJiafei · x · 2026-09-29
MolmoAct 2 tops the leaderboard at 46% success using only 300 demos, and holds its first grasp best when objects move. But it's also the biggest and slowest: up to 110 H100-hours to train, and long inference times make it struggle with fast motions.
More from Embodied
- SeeQ robot project retrospective: 'things just worked' when the ML was done right — aviral_kumar2 · 2026-09-29
- CMU's SeeQ: generalist robot value function on a VLM nearly doubles real-world task success — aviral_kumar2 · 2026-09-29
- Tech Workers Let ChatGPT, Claude and Grok Drive a Real Toyota Corolla; Only One Model Finished — 404 Media · 2026-09-29
- Forlinx's 20-TOPS M.2 AI Accelerator Supports PCIe Cascading for Local LLM Inference — DeliciousBelt9520 · 2026-09-29
- Rumor: OpenAI Pays $380k-$460k for Control Engineers to Bake Robotics into GPT-6 — xeophon · 2026-09-29
- General Intuition raises $220M more at $6.2B valuation for realtime world models — lucasmeijer · 2026-09-29