Showing cs.CVShow all
3 papers · 1 filter
cs.CV2026
SRA 2: Variational Autoencoder Self-Representation Alignment for Efficient Diffusion Training
Mengmeng Wang, Dengyang Jiang, Liuzhuozheng Li +6
Denoising-based diffusion transformers, despite their strong generation performance, suffer from inefficient training convergence. Existing methods addressing this issue, such as R…
cs.CV2025
RobuQ: Pushing DiTs to W1.58A2 via Robust Activation Quantization
Kaicheng Yang, Xun Zhang, Haotong Qin +4
Diffusion Transformers (DiTs) have recently emerged as a powerful backbone for image generation, demonstrating superior scalability and performance over U-Net architectures. Howeve…
cs.CV2025
Attention Debiasing for Token Pruning in Vision Language Models
Kai Zhao, Wubang Yuan, Yuchen Lin +5
Vision-language models (VLMs) typically encode substantially more visual tokens than text tokens, resulting in significant token redundancy. Pruning uninformative visual tokens is…