Berkeley Team's Calibration Research Accepted at NeurIPS 2026 LCFM Workshop
sehoonkim418 · x · 2026-10-08
A team including @omin0127, JoongWon Shin, @minseokim0525, Kurt Keutzer, and Jae Lee will present their calibration research at the NeurIPS 2026 LCFM Workshop in Atlanta, with paper, blog, code, and calibration resources publicly available.
More from Research
- Medical AI benchmark builder: his first ECG dataset had answers printed on images — MaziyarPanahi · 2026-10-08
- OpenAI publishes hundreds of math results, including matrix multiplication algorithm with ω≤2.25 — xiaosun86 · 2026-10-08
- Learned latent dynamics roll forward from few observations to recover hopper state with uncertainty — hisspikeness · 2026-10-08
- Adding a pixel-reconstruction loss makes latents unable to decode hopper state — hisspikeness · 2026-10-08
- New theory shows SSL separates stochastic signals from nuisance via MI maximization plus distribution matching — hisspikeness · 2026-10-08
- The conundrum of latent prediction: signals themselves are stochastic, so what to keep? — hisspikeness · 2026-10-08