Zunnan Xu

8

Papers

59

Total Citations

Papers (8)

Densely Connected Parameter-Efficient Tuning for Referring Image Segmentation

FireEdit: Fine-grained Instruction-based Image Editing via Region-aware Vision Language Model

Audio-visual Controlled Video Diffusion with Masked Selective State Spaces Modeling for Natural Talking Head Generation

SAM-R1: Leveraging SAM for Reward Feedback in Multimodal Segmentation via Reinforcement Learning

AToM: Aligning Text-to-Motion Model at Event-Level with GPT-4Vision Reward

Chain of Generation: Multi-Modal Gesture Synthesis via Cascaded Conditional Control

Hunyuan-Portrait: Implicit Condition Control for Enhanced Portrait Animation

REPARO: Compositional 3D Assets Generation with Differentiable 3D Layout Alignment