Yanghao Li

MANZANO: A Simple and Scalable Unified Multimodal Model with a Hybrid Vision Tokenizer

MM1.5: Methods, Analysis & Insights from Multimodal LLM Fine-tuning

EC-DIT: Scaling Diffusion Transformers with Adaptive Expert-Choice Routing

MMEgo: Towards Building Egocentric Multimodal LLMs for Video QA

Improve Vision Language Model Chain-of-thought Reasoning