Bin Lin

5

Papers

415

Total Citations

Papers (5)

LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment

Cycle3D: High-quality and Consistent Image-to-3D Generation via Generation-Reconstruction Cycle

OpenS2V-Nexus: A Detailed Benchmark and Million-Scale Dataset for Subject-to-Video Generation

DreamDance: Animating Human Images by Enriching 3D Geometry Cues from 2D Poses

WF-VAE: Enhancing Video VAE by Wavelet-Driven Energy Flow for Latent Video Diffusion Model