RL Workshop: Training from World Signals Instead of RLHF
shaneguML · x · 2026-07-06
Shane Gu outlines his workshop's goals: 1) advancing reinforcement learning based on grounded world signals (such as efficiency, safety, and economic outcomes) to move beyond noisy RLHF; and 2) bridging academia and industry. Speakers like MillionInt and Brian Zhan are invited to share the latest trends in RL startups across Silicon Valley and beyond.
More from Research
- Researchers identify "Forking": train loss falls while validation loss turns up — ZimingLiu11 · 2026-10-26
- Google DeepMind pilots world's first double-blind evaluations for frontier models — scychan_brains · 2026-10-26
- Rewriting scaling law study: optimal synthetic data share rises from 10% to 32% with compute — heghbalz · 2026-10-26
- FLASH: GPU-native deformable sim learns cloth folding in minutes on one RTX 5090 — ChongZzZhang · 2026-10-26
- LEMON: zero-shot LLM misbehavior monitor flags hallucinations from attention maps — yoavartzi · 2026-10-26
- Behind the EMNLP keynote: LMs as simulated learners to generate child language acquisition hypotheses — najoungkim · 2026-10-26