Hong-You Chen

Think Then Embed: Generative Context Improves Multimodal Embedding

Contrastive Localized Language-Image Pre-Training

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

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

SlowFast-LLaVA: A strong training-free baseline for video large language models

Lessons Learned from a Unifying Empirical Study of Parameter-Efficient Transfer Learning (PETL) in Visual Recognition

Contrastive Localized Language-Image Pre-Training