conftrace_

post training

6 papers

Explore in graph

Co-occurring keywords · papers mentioning both

freefall (1) rlhf (1) detoxification (1) generational toxicity (1) toxic data (1) gradient (1) score-based divergence (1) physical accuracy (1) physics (1) simulated videos (1)

Papers

David and Goliath: Small One-step Model Beats Large Diffusion with Score Post-training ICML 2025 PISA Experiments: Exploring Physics Post-Training for Video Diffusion Models by Watching Stuff Drop ICML 2025 Preserving Deep Representations in One-Shot Pruning: A Hessian-Free Second-Order Optimization Framework ICLR 2025 SepLLM: Accelerate Large Language Models by Compressing One Segment into One Separator ICML 2025 When Bad Data Leads to Good Models ICML 2025 WildChat-50M: A Deep Dive Into the Role of Synthetic Data in Post-Training ICML 2025