MolmoMotion: AI2's 4B VLM forecasts 3D point trajectories from language instructions
rsasaki0109 · x · 2026-10-03
MolmoMotion is a 4B vision-language model that forecasts 3D point trajectories under natural-language action instructions. Given a short RGB observation history, user-specified 2D query points with initial 3D positions, and a language description of the intended action, it predicts each point's 3D trajectory up to 2 seconds ahead in the camera-frame-at-t₀ coordinate system. The learned motion prior transfers to robotics planning and motion-guided video generation.
More from Embodied
- ETH's Anymal robot completes 10km autonomous alpine hike with VLM-guided ROAM system — ChongZzZhang · 2026-11-19
- iFixit tears down Apple HomeView: lots of glue and 'endless frustration' — Resident-Fall4351 · 2026-11-19
- Removing human video drops robot OOD success from 60% to 7%: generalization comes from human video — gui_penedo · 2026-11-19
- PSYONIC's prosthetic Ability Hand now used by 90+ robotics orgs, raising Series A — DhowCIO · 2026-11-19
- Simulator misspecification breeds overconfidence: sim-to-real study on SPEED+ — Nikolay Dolgov · 2026-11-19
- Doppel world model renders the robot body and beats action-only baselines across 8 embodiments — mangahomanga · 2026-11-19