Qwen shows in-context learning of body-part steering, sharing a map across bodies
Sauers_ · x · 2026-11-13
Researcher Sauers reports that Qwen appears to do in-context learning of body-part steering: from contextual examples alone, the model learns to control specific body parts on command without fine-tuning. He adds that Qwen seems to share a map between bodies, suggesting the learned steering relationships generalize across different body forms rather than memorizing one morphology.
Related event: Study Finds Emergent "Body Maps" Inside LLMs, Sparking Debate(12 posts)→
More from Embodied
- Robopedia launches Xperience 2, a 'gold standard' Physical AI dataset — liuziwei7 · 2026-11-13
- Baidu invites riders to try its 6th-gen Apollo Go robotaxi in Beijing — Baidu_Inc · 2026-11-13
- Gemini Robotics 2.5 Debuts at CoRL 2026: Humanoid Ties a Bow Autonomously — ZoubinGhahrama1 · 2026-11-13
- LLM edits 65 embedding rows to fix robot failures, lifting held-out success 74.3% to 87.5% — 机器之心 · 2026-11-13
- Astra vs Fable 5.2 zero-shot excavator test: only visual reference, one model prevails — Scobleizer · 2026-11-13
- Waymo rider pulls up next to a Cybercab — with a human driver still in the seat — kscottz · 2026-11-13