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
- Lighthouse extends Obsidian welding foundation model to run on any robotic platform — bennash · 2026-11-11
- Sipeed's MaixStation Dock PCB returns, 14-layer SOM still in fab — AIFlow_ML · 2026-11-11
- NAE EU-US Frontiers of Engineering symposium explores AI-driven materials, robotics, neuromorphic computing — ProfBuehlerMIT · 2026-11-11
- Paper link for FLEX: robots generalize language corrections into preferences — JafarNajafov · 2026-11-11
- MIT and NYU's FLEX lets robots generalize a single spoken correction into broad preferences — JafarNajafov · 2026-11-11
- AI lets robotics research thrive in labs with no robotics experts — 4310sy · 2026-11-11