🏢 University of Science and Technology of China

Aligning image generation subtasks: Equivariant modeling boosts efficiency and generalization by leveraging natural visual signal invariance.

TokenSet: Tokenizing images as unordered sets for dynamic capacity allocation and robust generation, breaking from fixed-position latent codes.

UAE-3D: A unified latent space approach for efficient & high-quality 3D molecular generation, outperforming existing methods in accuracy and speed.

RelaCtrl: Relevance-guided control boosts diffusion transformer efficiency, cutting parameters by intelligently allocating resources.

DepthMaster tames diffusion models for faster, more accurate monocular depth estimation by aligning generative features with high-quality semantic features and adaptively balancing low and high-freque…

Molar: A novel multimodal LLM framework boosts sequential recommendation accuracy by cleverly aligning collaborative filtering with rich item representations from text and non-text data.

One-shot image to realistic, animatable talking avatar! Novel pipeline uses diffusion models and a hybrid 3DGS-mesh representation, achieving seamless generalization and precise control.