Zero-shot LLM Fable beats fine-tuned pi0.5 VLA on memory tasks 64 vs 7
paigeinsf · x · 2026-11-12
From paigeinsf at Physical Intelligence (thread 1/4): zero-shot Fable 5.2 is strong at what LLMs are good at — memory and long-horizon tasks. On a cups-and-blocks task requiring ordered uncovering, Fable averaged 64/100 versus 7 for fine-tuned π0.5; on long-horizon tasks Fable scored 47 against π0.5's 27.
More from Embodied
- Meta Releases XRStereo: ~18k-Sequence Synthetic Stereo Dataset on Hugging Face — _akhaliq · 2026-11-12
- Hacking the open-source Anker recorder into a real-time voice input device with Qwen 0.6B ASR — vista8 · 2026-11-12
- Liquid AI lays out roadmap to put AI on half the world's devices via model-hardware co-design — JosephJacks_ · 2026-11-12
- Wayve unveils Learned Safety Envelope: end-to-end trained live risk prediction for AI driving — alexgkendall · 2026-11-12
- Pro-0 trains dexterous robot hands from human demos with zero on-robot data — chris_j_paxton · 2026-11-12
- Chris Paxton endorses "the age of deploy cos" to bridge robotics' demo-to-deployment gap — chris_j_paxton · 2026-11-12