SEGA: Spectral-Energy Guided Attention for Resolution Extrapolation in Diffusion Transformers Paper • 2605.22668 • Published May 21 • 43
Bridging the Gap: Addressing Discrepancies in Diffusion Model Training for Classifier-Free Guidance Paper • 2311.00938 • Published Nov 2, 2023 • 1
On Surprising Effectiveness of Masking Updates in Adaptive Optimizers Paper • 2602.15322 • Published Feb 17 • 11
Improving Diffusion Models's Data-Corruption Resistance using Scheduled Pseudo-Huber Loss Paper • 2403.16728 • Published Mar 25, 2024 • 1
ZClip: Adaptive Spike Mitigation for LLM Pre-Training Paper • 2504.02507 • Published Apr 3, 2025 • 90