ModAR: a 30.1M robot world model trained from scratch beats a 6B video-model baseline
CSProfKGD · x · 2026-09-17
Adamjhung's team questions whether RGB pixels are the right representation for robot world-action models, arguing RGB wastes capacity on fine-grained details irrelevant to robot policies.
- DINO features, point tracks, and depth capture semantics, motion, and geometry — but no single modality suffices.
- ModAR predicts the future one modality at a time, with each prediction informing the next, trained from scratch.
- The 30.1M scratch-trained model outperforms a 6B video-model-initialized baseline fine-tuned for robotics.
More from Embodied
- ANYbotics begins customer deliveries of ANYmal X, first legged robot certified for explosive atmospheres — lukas_m_ziegler · 2026-11-02
- RAM prices tripled, so Tesla cut a third of memory from Optimus's brain — aakashgupta · 2026-11-02
- Too lazy on weekends? Watch this robot tidy up a desktop — flngr · 2026-11-02
- Wearing Whoop and Apple Watch on a single dual-slot band — tinyfool · 2026-11-02
- REA: async brain-cerebellum runtime for robots where policies never wait on the LLM — Pengfei Zhou · 2026-11-02
- Robot Combat Sports Coming to Japan with a Permanent Arena in Tokyo — cixliv · 2026-11-02