Jon Barron's CVPR 2026 Bitter Lessons talk: which research areas should (and shouldn't) use explicit 3D representations
jon_barron · x · 2026-08-31
Google researcher Jon Barron shares his talk from the CVPR 2026 "Bitter Lessons" workshop, split into parts for discussion. Part 1 opens with his dissertation results from his early years, setting up the central question: which research areas should, and probably shouldn't, rely on explicit 3D representations.
The rest of the talk dives into each area — robotics, movies, games, engineering — where the value of explicit 3D varies dramatically, a systematic take on the debate over whether 3D vision is being marginalized by scaling.
Related event: Jon Barron Releases CVPR Talk Questioning Explicit 3D Representations(10 posts)→
More from Research
- Interpretability debate: one interpretable polysemantic neuron doesn't prove all are — aran_nayebi · 2026-10-16
- Optuna creator Akiba: when 2 hyperparameters cost $20M, what's left for BO/HPO — Stefania_druga · 2026-10-16
- AI will be superhuman at science regardless, and Europe can't opt out — teortaxesTex · 2026-10-16
- SERO augments long-horizon agentic RL with executable oracle continuations — Shanghai-AI-Laboratory · 2026-10-16
- Tsinghua and Amap propose OmniVerifier-C1, a graded verifier beating binary judges — Bowei Liu · 2026-10-16
- Alibaba open-sources MAI-Gym, an all-in-one GUI agent eval and RL training platform — Tongyi-MAI · 2026-10-16