Weekly Models Roundup: Meta's MoE-ViE, Robot Foundation Model τ0-VLA, 4DAnyone, and WithEveryone
TheTuringPost · x · 2026-08-26
Highlights of new models this week:
- MoE-ViE: Meta's sparse mixture-of-experts vision encoder for efficient image and video understanding.
- τ0-VLA: A robot foundation model by AgiBot Finch that "thinks" through possible outcomes before acting.
- 4DAnyone: Developed by Ant Group and Zhejiang University, turns a single casual video into an animatable 4D human.
- WithEveryone: An image model specialized in generating group scenes.
Related event: This Week's New Models: Meta Vision Encoder and Robot Foundation Models(2 posts)→
More from Embodied
- Airbound raises Series A to build a world without roads — paulfinneyx · 2026-08-26
- Chang Robotics: 'The factory is the robot' — selling automation culture, not machines — MatthewChang · 2026-08-26
- ChangRobotics Teases New Site: The Factory is the Robot — MatthewChang · 2026-08-26
- Robotics Founder: The Factory Is the Robot, Rejecting RaaS Hype — MatthewChang · 2026-08-26
- Angel investor predicts Optimus will hit 1B units in a decade — Distinct-Question-16 · 2026-08-26
- Scott Walter Breaks Down the Best Humanoid Robot Design for 2026 — Scobleizer · 2026-08-26