Reka Open-Sources RIDM, Extracting Camera and Motor Commands from Raw Video
RekaAILabs · x · 2026-10-02
Reka AI released its Inverse Dynamics Model (RIDM), a compact model that extracts low-level camera/motor commands directly from raw video. Motivation: standard simulated environments lack real-world physics and noise, and interactive world models need video labeled with low-level actions that real footage rarely has. RIDM was trained entirely on video games yet generalizes to real-world footage. Weights are open-sourced under Apache 2.0 on Hugging Face, with a research note accompanying the release.
More from Embodied
- Figure's data collection project Index crosses 1 million signed-up users — adcock_brett · 2026-10-02
- DATAFARM: aligning TAMP demos to VLA pretraining distribution unlocks planning plus dexterity — tomssilver · 2026-10-02
- Wearable AI lets you capture thoughts by voice anywhere you go — broodsugar · 2026-10-02
- UniWAM unifies physical reasoning, world generation, and action prediction for robots — zhenjun_zhao · 2026-10-02
- CloudAnalyzer: browser-based LiDAR tools for SLAM map fixes and Lanelet2 editing in Rust+WASM — rsasaki0109 · 2026-10-02
- Ego-Exo4D-HM: SMPL-H reconstructions for 523 hours of egocentric-exocentric video, open-sourced — geopavlakos · 2026-10-02