Score centering cancels RL training-inference drift via a bias term
finbarrtimbers · x · 2026-10-25
Score centering resolves the training/inference mismatch in RL by subtracting a bias term that cancels out the drift between the training and inference engines.
More from Research
- "Do LLMs Feel?" paper maps localized emotion circuits inside LLMs — mikeflache · 2026-10-25
- Researchers push back on hype that AI papers done in 2–3 days make peer review obsolete — ChongZzZhang · 2026-10-25
- EC2-Bench: edge-cloud collaboration hits 73% of cloud-only agent performance at 15% of the cost — zibuyu9 · 2026-10-25
- Paper: additive "score centering" term stabilizes LLM RL under training-inference mismatch — finbarrtimbers · 2026-10-25
- TensorFold's experimental Living Weights writes new facts into local model weights — GabGarrett · 2026-10-25
- Researcher argues AI tooling should filter junk papers so scientists focus on work worth their time — hugo_larochelle · 2026-10-25