Bowen Zhang

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

Contrastive Localized Language-Image Pre-Training

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

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

Revisit Large-Scale Image-Caption Data in Pre-training Multimodal Foundation Models

MMEgo: Towards Building Egocentric Multimodal LLMs for Video QA

Contrastive Localized Language-Image Pre-Training

Improve Vision Language Model Chain-of-thought Reasoning