LiteASR: Efficient Automatic Speech Recognition with Low-Rank Approximation Paper โข 2502.20583 โข Published Feb 27 โข 13
LlamaV-o1: Rethinking Step-by-step Visual Reasoning in LLMs Paper โข 2501.06186 โข Published Jan 10 โข 66
StoryMaker: Towards Holistic Consistent Characters in Text-to-image Generation Paper โข 2409.12576 โข Published Sep 19, 2024 โข 16