2 papers
cs.CV2026
Memory-Efficient Training-Free Acceleration of Diffusion Transformers with BaryCache
Chengjie Lu, Tianchi Deng, Zhengqi He +3
Diffusion Transformers achieve high-fidelity image and video generation, but their iterative sampling remains expensive, for each denoising step requires large matrix operations. E…
cs.LG2026
ChebBooster: A Training-Free Approach for Efficient Diffusion Transformer Inference via Chebyshev-Inspired Extrapolation
Chengjie Lu, Tianchi Deng, Zhengqi He +2
Diffusion Transformers (DiTs) have shown strong performance in high-fidelity image generation, but their sampling process remains computationally intensive due to full model execut…