Prediction: DeepSeek V4 Flash-scale real-time robot vision models coming within weeks
zhaoran_wang · x · 2026-09-26
Zhaoran Wang predicts "big models are too slow for robotics" will age badly: within weeks, expect many DeepSeek V4 Flash-scale JEVs—real-time via distillation and surprisingly close to Astra. People underestimate how fast prefill can get, he argues.
More from Embodied
- Trossen dual robot arms strike a match fully autonomously, unveils 2026 Physical AI lineup — YuXiang_IRVL · 2026-09-26
- Scoble: robot revolution is here, humanoids 2-7 years out and a funding wave is coming — Scobleizer · 2026-09-26
- NSF FRR robotics meeting workshop: four talks on skill learning and physical intelligence — YuXiang_IRVL · 2026-09-26
- Déjà View, a NeurIPS Oral: one looped transformer block matches 3D reconstruction models 8-10x its size — ZGojcic · 2026-09-26
- Places Library debuts: 100 high-fidelity real-world 3D environments for embodied AI — yshan2u · 2026-09-26
- microagi x ElevenLabs: Voice is the most human interface for living with robots — animesh_garg · 2026-09-26