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.

Original post →

More from Research

Research channel →