Vision-Language Models

MegaPairs: Massive Data Synthesis For Universal Multimodal Retrieval

Flowing from Words to Pixels: A Framework for Cross-Modality Evolution

LLaVA-UHD v2: an MLLM Integrating High-Resolution Feature Pyramid via Hierarchical Window Transformer

Descriptive Caption Enhancement with Visual Specialists for Multimodal Perception

GeoX: Geometric Problem Solving Through Unified Formalized Vision-Language Pre-training

Efficient Generative Modeling with Residual Vector Quantization-Based Tokens

Apollo: An Exploration of Video Understanding in Large Multimodal Models

SynerGen-VL: Towards Synergistic Image Understanding and Generation with Vision Experts and Token Folding

BiMediX2: Bio-Medical EXpert LMM for Diverse Medical Modalities