Guansong Lu

8

Papers

51

Total Citations

Papers (8)

ILLUME: Illuminating Your LLMs to See, Draw, and Self-Enhance

EDEN: Enhanced Diffusion for High-quality Large-motion Video Frame Interpolation

ManiTrans: Entity-Level Text-Guided Image Manipulation via Token-Wise Semantic Alignment and Generation

DiffCloth: Diffusion Based Garment Synthesis and Manipulation via Structural Cross-modal Semantic Alignment

Towards High-Fidelity Text-Guided 3D Face Generation and Manipulation Using only Images

DiffDis: Empowering Generative Diffusion Model with Cross-Modal Discrimination Capability

Weakly and Semi Supervised Human Body Part Parsing via Pose-Guided Knowledge Transfer

Wukong: A 100 Million Large-scale Chinese Cross-modal Pre-training Benchmark