Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs
摘要和介绍
5 docs tagged with "LLM"
View all tagsGPT4RoI-Instruction Tuning Large Language Model on Region-of-Interest
论文名称：GPT4RoI: Instruction Tuning Large Language Model on Region-of-Interest
LLaVA
论文名称：Visual Instruction Tuning
Shikra-Unleashing Multimodal LLM’s Referential Dialogue Magic
论文名称：Shikra: Unleashing Multimodal LLM’s Referential Dialogue Magic
VisionLLM
论文名称：VisionLLM: Large Language Model is also an Open-Ended Decoder for Vision-Centric Tasks