Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
NoiseRater: Meta-Learned Noise Valuation for Diffusion Model Training
Fang Wu, Haokai Zhao, Da Xing +17
Diffusion models have achieved remarkable success across a wide range of generative tasks, yet their training paradigm largely treats injected noise as uniformly informative. In th…
cs.LG2025
Spectraformer: A Unified Random Feature Framework for Transformer
Duke Nguyen, Du Yin, Aditya Joshi +1
Linearization of attention using various kernel approximation and kernel learning techniques has shown promise. Past methods used a subset of combinations of component functions an…