Shigui Li's picture

3 4

Shigui Li

ShiguiLi

·

ShiguiLi

AI & ML interests

generative models, diffusion models, inference optimization

Recent Activity

upvoted a paper about 9 hours ago

TurboDiffusion: Accelerating Video Diffusion Models by 100-200 Times

upvoted a paper 9 days ago

Aesthetic Alignment Risks Assimilation: How Image Generation and Reward Models Reinforce Beauty Bias and Ideological "Censorship"

authored a paper 2 months ago

EVODiff: Entropy-aware Variance Optimized Diffusion Inference

View all activity

Organizations

upvoted a paper about 9 hours ago

TurboDiffusion: Accelerating Video Diffusion Models by 100-200 Times

Paper • 2512.16093 • Published 8 days ago • 44

upvoted a paper 9 days ago

Aesthetic Alignment Risks Assimilation: How Image Generation and Reward Models Reinforce Beauty Bias and Ideological "Censorship"

Paper • 2512.11883 • Published 17 days ago • 6

upvoted a paper 2 months ago

EVODiff: Entropy-aware Variance Optimized Diffusion Inference

Paper • 2509.26096 • Published Sep 30 • 1