MergeVQ: A Unified Framework for Visual Generation and Representation with Disentangled Token Merging and Quantization Paper • 2504.00999 • Published 5 days ago • 72
ReasonFlux Series Collection A series of released reasoning models based on ReasonFlux • 5 items • Updated 7 days ago • 1
Training-free Diffusion Acceleration with Bottleneck Sampling Paper • 2503.18940 • Published 13 days ago • 12
VQGraph: Rethinking Graph Representation Space for Bridging GNNs and MLPs Paper • 2308.02117 • Published Aug 4, 2023
RealCompo: Dynamic Equilibrium between Realism and Compositionality Improves Text-to-Image Diffusion Models Paper • 2402.12908 • Published Feb 20, 2024 • 10
VideoTetris: Towards Compositional Text-to-Video Generation Paper • 2406.04277 • Published Jun 6, 2024 • 25
HermesFlow: Seamlessly Closing the Gap in Multimodal Understanding and Generation Paper • 2502.12148 • Published Feb 17 • 16
Diffusion-Sharpening: Fine-tuning Diffusion Models with Denoising Trajectory Sharpening Paper • 2502.12146 • Published Feb 17 • 16
Training-free Diffusion Acceleration with Bottleneck Sampling Paper • 2503.18940 • Published 13 days ago • 12