5 papers
Enhancing Text-to-Image Diffusion Transformer via Split-Text Conditioning
Yu Zhang, Jialei Zhou, Xinchen Li +6
Current text-to-image diffusion generation typically employs complete-text conditioning. Due to the intricate syntax, diffusion transformers (DiTs) inherently suffer from a compreh…
Markovian Scale Prediction: A New Era of Visual Autoregressive Generation
Yu Zhang, Jingyi Liu, Yiwei Shi +4
Visual AutoRegressive modeling (VAR) based on next-scale prediction has revitalized autoregressive visual generation. Although its full-context dependency, i.e., modeling all previ…
Swordsman: Entropy-Driven Adaptive Block Partition for Efficient Diffusion Language Models
Yu Zhang, Xinchen Li, Jialei Zhou +6
Block-wise decoding effectively improves the inference speed and quality in diffusion language models (DLMs) by combining inter-block sequential denoising and intra-block parallel…
Adaptive Visual Autoregressive Acceleration via Dual-Linkage Entropy Analysis
Yu Zhang, Jingyi Liu, Feng Liu +5
Visual AutoRegressive modeling (VAR) suffers from substantial computational cost due to the massive token count involved. Failing to account for the continuous evolution of modelin…
NeuroClips: Towards High-fidelity and Smooth fMRI-to-Video Reconstruction
Zixuan Gong, Guangyin Bao, Qi Zhang +9
Reconstruction of static visual stimuli from non-invasion brain activity fMRI achieves great success, owning to advanced deep learning models such as CLIP and Stable Diffusion. How…