Qingsong Xie

5

Papers

14

Total Citations

Papers (5)

PEA-Diffusion: Parameter-Efficient Adapter with Knowledge Distillation in non-English Text-to-Image Generation

MergeVQ: A Unified Framework for Visual Generation and Representation with Disentangled Token Merging and Quantization

Advancing Text-to-3D Generation with Linearized Lookahead Variational Score Distillation

SCott: Accelerating Diffusion Models with Stochastic Consistency Distillation

Instruct-ReID: A Multi-purpose Person Re-identification Task with Instructions