4 papers
LLaVA-UHD v3: Progressive Visual Compression for Efficient Native-Resolution Encoding in MLLMs
Shichu Sun, Yichen Zhang, Haolin Song +6
Visual encoding followed by token condensing has become the standard architectural paradigm in multi-modal large language models (MLLMs). Many recent MLLMs increasingly favor globa…
ContentV: Efficient Training of Video Generation Models with Limited Compute
Wenfeng Lin, Renjie Chen, Boyuan Liu +10
Recent advances in video generation demand increasingly efficient training recipes to mitigate escalating computational costs. In this report, we present ContentV, an 8B-parameter…
Towards Self-Improvement of Diffusion Models via Group Preference Optimization
Renjie Chen, Wenfeng Lin, Yichen Zhang +5
Aligning text-to-image (T2I) diffusion models with Direct Preference Optimization (DPO) has shown notable improvements in generation quality. However, applying DPO to T2I faces two…
CascadeV: An Implementation of Wurstchen Architecture for Video Generation
Wenfeng Lin, Jiangchuan Wei, Boyuan Liu +3
Recently, with the tremendous success of diffusion models in the field of text-to-image (T2I) generation, increasing attention has been directed toward their potential in text-to-v…