Automatic Creative Selection with Cross-Modal Matching

OpenELM: An Efficient Language Model Family with Open-source Training and Inference Framework

ReALM: Reference Resolution As Language Modeling

MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training

Guiding Instruction-based Image Editing via Multimodal Large Language Models

Ferret: Refer and Ground Anything Anywhere at Any Granularity

LLM in a flash: Efficient Large Language Model Inference with Limited Memory