Zixuan Wang

10

Papers

10

Total Citations

Papers (10)

Training-free Dense-Aligned Diffusion Guidance for Modular Conditional Image Synthesis

CoPRA: Bridging Cross-domain Pretrained Sequence Models with Complex Structures for Protein-RNA Binding Affinity Prediction

FontAnimate: High Quality Few-shot Font Generation via Animating Font Transfer Process

Generate Like Experts: Multi-Stage Font Generation by Incorporating Font Transfer Process into Diffusion Models

DanceCamera3D: 3D Camera Movement Synthesis with Music and Dance

Transformers Provably Learn Sparse Token Selection While Fully-Connected Nets Cannot

LA3: Efficient Label-Aware AutoAugment

MeGA: Hybrid Mesh-Gaussian Head Avatar for High-Fidelity Rendering and Head Editing

Beyond Words: Augmenting Discriminative Richness via Diffusions in Unsupervised Prompt Learning

Analyzing Sharpness along GD Trajectory: Progressive Sharpening and Edge of Stability