CertJudge Research Showcased at ICML
sanmikoyejo · x · 2026-07-13
The shared post highlights a new work called CertJudge, themed around "who will judge the judges."
The information also mentions that this work comes from institutions like Stanford, Harvard, Hong Kong Baptist University, and was presented at the AI4Math and Deep Learning for Code workshops at ICML 2026.
Related event: CertJudge Targets Reusable Calibration for LLM Judges(3 posts)→
More from Research
- Meta FAIR's Self-Direction turns agent failures into reusable LoRA skills, +13.8pp on Terminal-Bench — karen_ullrich · 2026-10-27
- DONIC hits 86.79% on bimanual dexterous tracking, crushing prior SOTA's 9.43% — liuziwei7 · 2026-10-27
- Why don't more LLMs ship 10M-token context? A researcher asks about attention tradeoffs — agarwl_ · 2026-10-27
- PSNR below 15 dB in papers likely means the metric was misused, researcher warns — kwangmoo_yi · 2026-10-27
- Ortet's first health eval: 34 open-weight models, 50 tasks, generic rankings fall short — thegautamkamath · 2026-10-27
- Scaling-fit discrepancy: output-head FLOPs are ~65% of compute at the smallest rung, ~3% at 535B — dlwh · 2026-10-27