DiffRhythm: Blazingly Fast and Embarrassingly Simple End-to-End Full-Length Song Generation with Latent Diffusion Paper • 2503.01183 • Published Mar 3 • 26 • 2
Diffusion-Sharpening: Fine-tuning Diffusion Models with Denoising Trajectory Sharpening Paper • 2502.12146 • Published Feb 17 • 16 • 3
Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation Paper • 2410.13848 • Published Oct 17, 2024 • 35 • 4