Lingzhi Zhang

5

Papers

55

Total Citations

Papers (5)

Amodal Completion via Progressive Mixed Context Diffusion

FINECAPTION: Compositional Image Captioning Focusing on Wherever You Want at Any Granularity

Refer to Any Segmentation Mask Group With Vision-Language Prompts

Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformers

Brush2Prompt: Contextual Prompt Generator for Object Inpainting