Sitzmann: scaling video models will bring vision algorithms to the real world
vincesitzmann · x · 2026-10-22
In a follow-up to his essay on the decline of traditional computer vision, Vincent Sitzmann says he is confident the same algorithms will work in the real world — it just requires scaling up video models. Expensive, but guaranteed to work since it is fundamentally generative modeling; remaining challenges are about learning, not classic representation problems.
More from Research
- Chatlet: Generative UI That Emerges From Group Conversations — round · 2026-10-22
- NJU's Socratic Skill Learning hits 0.801 utility, beating distillation baselines — NJU-LINK · 2026-10-22
- CulturalRiddles: 62-culture riddle benchmark trips frontier LLMs to as low as 22% accuracy — CohereLabsCommunity · 2026-10-22
- Fudan's TextRIRO enables scene text editing with self-paired real data only — Fudan-University · 2026-10-22
- AgenticRoboRL lifts a 9B robot planner from 18% to 71% on LIBERO-PRO — UCF-Ai-LLMs · 2026-10-22
- Microsoft Research's WildAWM synthesizes computer-use environments to train agents — MicrosoftResearch · 2026-10-22