ETH researcher vibe-codes SuperMimic reproduction in about an hour
ETH Zurich's Chong Zhang introduced a world-model-plus-APG paradigm that speeds up humanoid whole-body tracking training 1000x, reproducing SuperMimic on a single GPU in roughly 1.24 hours with Claude's coding help, passing LAFAN in about 1.5 GPU hours.
2026-10-22 ~ 2026-10-22 · 2 related posts
- Episode 1: UC Berkeley's SuperMimic Cuts Humanoid Training GPU Time by Over 1000x(2026-10-22, 2 posts)
- Episode 2: ETH researcher vibe-codes SuperMimic reproduction in about an hour(2026-10-22, 2 posts)
- World model + APG: single-GPU 1.24h reproduction of SuperMimic humanoid control — ChongZzZhang · 2026-10-22
- ETH researcher vibe-codes SuperMimic reproduction in 1 hour, LAFAN training in 1.5 GPUh — ChongZzZhang · 2026-10-22