Symbolic world models strike back: mu0 beats pi0.5 with 1/100 of the data
furongh · x · 2026-09-04
Furong Huang cites Gary Marcus's 2020 argument for symbolic world models, now validated in physical AI: the mu0 model beats pi0.5 on real-world robot tasks using only 1/100 of the training data.
Marcus adds that GPT-6 Astra performs well precisely by inducing and using symbolic world models, leaving open questions: how general is this ability, how does it work, and can such models reliably follow explicit instructions?
More from Embodied
- Neuralink co-founder Philip Sabes launches Arbor Neuroscience to make brain stimulation predictable — soumitrashukla9 · 2026-09-04
- NVIDIA AGX Thor + RealSense hits 75ms per VLM depth inference, ~10-12 FPS scenes — chrismatthieu · 2026-09-04
- In-context learning hints at a "GPT moment" for robotics — chris_j_paxton · 2026-09-04
- Developer builds web-connected interactive desktop device with Claude, blown away by the model's craft — EricBuess · 2026-09-04
- Runway and NVIDIA's GWM Worlds 2 brings world models to embodied AI training — tlakomy · 2026-09-04
- Raspberry Pi's SPOKE: an RP2040 disc with 27 capacitive touch pads that doubles as a MIDI controller — JeremyCMorgan · 2026-09-04