Mean-Variance Split residuals separate centered variation from mean updates to prevent collapse and enable stable training of 1000-layer Diffusion Transformers.
Manning, and Chelsea Finn
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
representative citing papers
PRPO is a paragraph-level policy optimization technique that grounds vision-language model reasoning in image content to raise deepfake detection accuracy and reasoning quality.
REINFORCE-style variants outperform PPO, DPO, and RAFT in RLHF for LLMs by removing unnecessary PPO components and adapting the simpler method to LLM alignment characteristics.
A survey deriving a unified policy gradient framework for LLM post-training methods and providing technical comparisons of PPO, GRPO, DPO variants.
citing papers explorer
-
Mean Mode Screaming: Mean--Variance Split Residuals for 1000-Layer Diffusion Transformers
Mean-Variance Split residuals separate centered variation from mean updates to prevent collapse and enable stable training of 1000-layer Diffusion Transformers.
-
PRPO: Paragraph-level Policy Optimization for Vision-Language Deepfake Detection
PRPO is a paragraph-level policy optimization technique that grounds vision-language model reasoning in image content to raise deepfake detection accuracy and reasoning quality.
-
Back to Basics: Revisiting REINFORCE Style Optimization for Learning from Human Feedback in LLMs
REINFORCE-style variants outperform PPO, DPO, and RAFT in RLHF for LLMs by removing unnecessary PPO components and adapting the simpler method to LLM alignment characteristics.
-
Reinforcement Learning for LLM Post-Training: A Survey
A survey deriving a unified policy gradient framework for LLM post-training methods and providing technical comparisons of PPO, GRPO, DPO variants.