← Search

Yucheng Lin

2 accepted papers

2026

RobuQ: Pushing DiTs to W1.58A2 via Robust Activation Quantization

ICML 2026poster

Diffusion Transformers (DiTs) have emerged as a powerful backbone for image generation, offering superior scalability over U-Nets. However, their practical deployment is hindered by significant computational costs. While Quantization-Aware Training (QAT) shows promise, its application to DiTs is cha…

Cited by 0SourceScholar
2026

SRA 2: Variational Autoencoder Self-Representation Alignment for Efficient Diffusion Training

CVPR 2026

Denoising-based diffusion transformers, despite their strong generation performance, suffer from inefficient training convergence. Existing methods addressing this issue, such as REPA (relying on external representation encoders) or SRA (requiring dual-model setups), inevitably incur heavy computati

Cited by 0SourceScholar