Bill Freeman at CVPR: frontier robotics is moving from bounding boxes to end-to-end policies
yunta_tsai · x · 2026-08-27
MIT's Bill Freeman opened his CVPR talk with a list of "bitter lessons", stating upfront that training end-to-end beats everything else.
Commentators note traditional vision ML is effectively blind outside annotated boxes — throwing away 90% of information, an ImageNet-era approach that cannot teach nuances. As a result, most frontier robotics work is moving from boxes to end-to-end policies: teaching a model how to act matters far more than labeling boxes.
Related event: Autonomous Driving Shifts to End-to-End Vision as Bounding Boxes Fall Short(2 posts)→
More from Embodied
- Robotics Moat: Data, Hardware, and the Deployment Layer Flywheel — chris_j_paxton · 2026-08-27
- Pollen Robotics and Hugging Face release Microduck, an open-source bipedal robot — -Cubie- · 2026-08-27
- End-to-End RL Drone Policy Passes Sim2real on Multiple Hardware — yacineMTB · 2026-08-27
- Robot that looks like a Sony Walkman and can roller skate — Thom_Wolf · 2026-08-27
- Waymo, Zoox Test Drivers Injured by Robotaxi Sudden Braking — tbirdcymru · 2026-08-27
- Why LLMs Can't Count Windows: Elorian CEO on Multimodal Reasoning — bigdata · 2026-08-27