Improved Visual-Spatial Reasoning via R1-Zero-Like Training Paper • 2504.00883 • Published 5 days ago • 52
MergeVQ: A Unified Framework for Visual Generation and Representation with Disentangled Token Merging and Quantization Paper • 2504.00999 • Published 5 days ago • 70
MLCM: Multistep Consistency Distillation of Latent Diffusion Model Paper • 2406.05768 • Published Jun 9, 2024 • 13