It's not gradient descent: burny_tech corrects the diagnosis to RLHF mode collapse
burny_tech · x · 2026-10-16
- Responding to claims blaming "gradient descent", burnytech argues the correct diagnosis is mode collapse, which is independent of the optimizer.
- The GAN adversarial objective is far more prone to mode collapse than the diffusion objective, even though both are typically trained with AdamW.
- His suggested phrasing: "This is the least surprising graph if you understand RLHF/RLVR/RLAIF mode collapse."
More from Research
- Transforming quadruped robot runs on real hardware: per-pose RL policies in Isaac switched on morph — _Stocko_ · 2026-10-16
- KinoGen synthesizes robot loco-manipulation reference motions directly via kinematically grounded video generation — ChongZzZhang · 2026-10-16
- Science Robotics paper introduces F³, predictive event-based vision beyond optical flow — CSProfKGD · 2026-10-16
- VideoGen-Agent: An 8B Multimodal Agent Turns Video Generation Into a Tool-Use Loop — jiqizhixin · 2026-10-16
- Comprehension Audits: New Paper Proposes a Gate for AI-Written Code at Frontier Labs — ronbodkin · 2026-10-16
- Not Boring #215: Cammarata's Clean Networks Claim, Tesla's Flying Roadster, Tau Cut 73% — Not Boring (Packy McCormick) · 2026-10-16