Astra shows any 3D/4D prior can be distilled into VLMs, a new embodied AI paradigm
mariyaivasileva · x · 2026-09-21
Jitendra Malik highlights that 3D/4D reconstruction — from multi-view geometry to VGGT and SAM 3D — is directly relevant to robotics, arguing that learning-era robotics papers ignoring 3D structure waste valuable signal. Commentators note Astra's key takeaway: virtually any 3D/4D prior can be distilled into VLMs, a potential new paradigm for embodied AI built on a real2sim2real tradition.
More from Embodied
- Human vs Robot Fight at San Francisco's REK Event Hit 'Completely Different', Says Attendee — BLUECOW009 · 2026-09-21
- DIY robot U-BOT's maiden voyage: stuck on a tiny stick, grass proves tougher than expected — _Stocko_ · 2026-09-21
- First-ever Human vs Terminator robot fight pits Frankie LaPenna against a bot — BLUECOW009 · 2026-09-21
- Legless autonomous food robot sparks debate: fixed-purpose machines land before humanoid cooks — mrjonfinger · 2026-09-21
- Closed-loop spatial understanding from just two wrist cameras, no gripper feedback — ChongZzZhang · 2026-09-21
- Andrew Chen: strong LLMs are far from running on phones, on-device AI faces bandwidth, heat and model-size hurdles — andrewchen · 2026-09-21