2 citations · 2 across the 4 of their papers we have counts for
4 papers
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…
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…
Causal Graph in Language Model Rediscovers Cortical Hierarchy in Human Narrative Processing
Zhengqi He, Taro Toyoizumi
Understanding how humans process natural language has long been a vital research direction. The field of natural language processing (NLP) has recently experienced a surge in the d…
The Fast Linear Accelerator Modeling Engine for FRIB Online Model Service
Z. He, J. Bengtsson, M. Davidsaver +3
Commissioning of a large accelerator facility like FRIB needs support from an online beam dynamics model. Considering the new physics challenges of FRIB such as modeling of non-axi…