Awesome Multimodal Large Language Models
A curated, continually updated list of papers, surveys, benchmarks and datasets on multimodal large language models, covering instruction tuning, in-context learning, chain-of-thought reasoning and evaluation.
This is a curated list of research on multimodal large language models, tracking surveys, papers, benchmarks and datasets as the field develops.
It links surveys of multimodal LLM evaluation and of unified multimodal understanding and generation, papers from a series of omni multimodal models, and a family of evaluation benchmarks, including a video understanding benchmark. Its paper index is organized by topic: multimodal instruction tuning, hallucination, in-context learning, chain-of-thought reasoning, LLM-aided visual reasoning, foundation models, evaluation and reinforcement learning from human feedback, alongside a matching index of datasets for pretraining, instruction tuning and evaluation.