Embodied Turing Machines paper explores stateful code for robot recursive self-improvement
_akhaliq · x · 2026-10-14
A new Hugging Face paper, Embodied Turing Machines, explores robot recursive self-improvement via stateful code.
- Authors stress benchmarks were not used for development and no oracle values are used in code
- Positioned not as a RoboDojo SOTA attempt but as a way to efficiently generate simulator trajectories and a framework for thinking about embodied tasks
- Explicitly not a rival to WAMs, VLAs or agentic methods — just a test of how far code-only RSI can go
Related event: Embodied Turing Machines: Code-Only Robot Policies(3 posts)→
More from Embodied
- Meta researcher recruiting multimodal and robotics interns for next summer, no background needed — liuzhuang1234 · 2026-10-14
- UNITAS: a 1.7B 3D-native world action model hits 99.8% on LIBERO and 85% on real tasks — CUHKSZ · 2026-10-14
- Frontier LLM scores on real robot benchmark double every 6 weeks, 15% to 48% in 3 months — ycombinator · 2026-10-14
- Raven Prism AI glasses launch set for October 28 in San Francisco — smtabatabaie · 2026-10-14
- DeLorean joins Airspeeder International Series, first American team debuting in November — evilrabbit_ · 2026-10-14
- Gemini 4 Argon taught Apptronik's Apollo humanoid cornhole from video, sinking 7 straight throws — GoogleDeepMind · 2026-10-14