news

Mar 10, 2026 Serving as a reviewer for ICML 2026.
Feb 24, 2026 Completed reviews for Visual Intelligence.
Feb 04, 2026 Released LCUDiff on arXiv for faithful human body restoration with upgraded 16-channel latent diffusion.
Sep 26, 2025 Paper accepted at NeurIPS 2025: HAODiff: Human-Aware One-Step Diffusion via Dual-Prompt Guidance.
Aug 10, 2025 Released SODiff, a semantic-oriented one-step diffusion model for JPEG compression artifacts removal.
May 26, 2025 Released HAODiff for human-aware restoration under mixed degradation and motion blur.
Feb 28, 2025 Paper accepted at CVPR 2025: OSDFace: One-Step Diffusion Model for Face Restoration.