2 papers
cs.CV2026
SAGE: Subspace Alignment for Classifier-Free Guidance in Mixture-of-Experts Diffusion Models
Boyu Zhang, Yangming Cheng, Ning Zhang +5
Diffusion Transformers with Mixture-of-Experts (MoE) routing are a leading recipe for scaling generative models. Classifier-Free Guidance (CFG) is essential for generation quality,…
cs.LG2026
KiT: A Foundation Model for Financial Time-Series Forecasting using DiffusionTransformers
Boyu Zhang, Haorui Li
Financial candlestick forecasting is fundamental to quantitative investment, yet it remains exceptionally challenging due to extremely low signal-to-noise ratios and vast heterogen…