CaTok: Taming Mean Flows for One-Dimensional Causal Image Tokenization Paper β’ 2603.06449 β’ Published 28 days ago β’ 6
Thinking with Video: Video Generation as a Promising Multimodal Reasoning Paradigm Paper β’ 2511.04570 β’ Published Nov 6, 2025 β’ 242
FlashPortrait: 6x Faster Infinite Portrait Animation with Adaptive Latent Prediction Paper β’ 2512.16900 β’ Published Dec 18, 2025 β’ 11
Semantics Lead the Way: Harmonizing Semantic and Texture Modeling with Asynchronous Latent Diffusion Paper β’ 2512.04926 β’ Published Dec 4, 2025 β’ 42
Running on CPU Upgrade 10k Kolors Virtual Try-On π 10k Generate a virtual tryβon image of a person wearing a garment
StableAvatar: Infinite-Length Audio-Driven Avatar Video Generation Paper β’ 2508.08248 β’ Published Aug 11, 2025 β’ 27