Berkeley diffusion model generates RL policy weights, letting a real G1 dance
FinanceYF5 · x · 2026-10-26
Berkeley researchers trained a diffusion model on the weights of thousands of reinforcement learning policies, generating new policies that let a real Unitree G1 walk, dance, and throw spinning kicks.
Also featured: KAIST's Humanoid v0.9, with onboard vision, can push up to 35 kg and lift 20 kg — then celebrated with a moonwalk.
Related event: Berkeley Generates RL Policies with Diffusion Models for Real Robot Skills(2 posts)→
More from Embodied
- Microduck team publishes deep dives: relocalizes within 2cm using a 64-pixel depth sensor — mishig25 · 2026-10-26
- Robot's elbow-assisted get-up move goes viral for its humanlike fluidity — iamfakhrealam · 2026-10-26
- Chinese eVTOL EHang EH216-S completes nearly 100,000 flights across 23 countries — LoganGrasby · 2026-10-26
- Toyota bets $6.4 billion a year on humanoid robots and factory automation — The Decoder · 2026-10-26
- Robot runs a video generation model as its policy: frozen FLUX beats VLAs — lukas_m_ziegler · 2026-10-26
- RoboJudge: 800 human-annotated videos benchmark MLLM judges for embodied video generation — CUHK-CSE · 2026-10-26