Opal auto-designs sophisticated LR schedules once reserved for DeepSeek-scale late training runs
vincesitzmann · x · 2026-10-22
The author claims Opal can automatically design highly sophisticated learning-rate schedules — the kind normally affordable only for highest-impact, super-late training runs like DeepSeek's. Now anyone can get the same (or more) sophistication.
Related event: EPFL's OPAL Puts a Coding Agent Inside the Training Loop(8 posts)→
More from Research
- Cohere Labs teases CulturalRiddles, a benchmark testing AI's grasp of cultural context — Cohere_Labs · 2026-10-22
- Microsoft Research claims proof of the 31-year-old KLS conjecture, aided by human-directed AI — LesterMackey · 2026-10-22
- SGLang ran early RL training on TPUs with Miles and TorchTitan, with promising results — ying11231 · 2026-10-22
- Rohan Paul shares full technical report of Recursive Flint — rohanpaul_ai · 2026-10-22
- Prompt Injection as Role Confusion: 60% attack success on frontier models, ICML 2026 paper — ChrisGPotts · 2026-10-22
- Benchling Post-Trains NVIDIA Nemotron 3.5 Super VL, Beating Closed Models on Lab Tasks at Low Cost — NVIDIAAI · 2026-10-22