| LLaVA-v1.5
(w/ LoRA, w/ extra data) | 99.32 | Improved Baselines with Visual Instruction Tuning | - |
| MGM-2B
(w/o LoRA, w/ extra data) | 98.75 | Mini-Gemini: Mining the Potential of Multi-modality Vision Language
Models | - |
| Bunny-v1.0-3B
(w/ LoRA, w/ extra data) | 96.02 | Efficient Multimodal Learning from Data-centric Perspective | - |
| MobileVLM-1.7B
(w/o LoRA, w/ extra data) | 97.78 | MobileVLM : A Fast, Strong and Open Vision Language Assistant for Mobile Devices | - |
| LLaVA-v1.5
(w/ LoRA, w/o extra data) | 98.58 | Improved Baselines with Visual Instruction Tuning | - |
| MobileVLM-1.7B
(w/ LoRA, w/ extra data) | 97.87 | MobileVLM : A Fast, Strong and Open Vision Language Assistant for Mobile Devices | - |
| LLaVA-v1
(w/ LoRA, w/o extra data) | 84.55 | Visual Instruction Tuning | - |
| LLaVA-Med-v1.5
(w/ LoRA, w/ extra data) | 90.4 | LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day | - |
| ColonGPT (w/ LoRA, w/o extra data) | 99.96 | Frontiers in Intelligent Colonoscopy | - |
| MiniGPT-v2
(w/ LoRA, w/o extra data) | 94.69 | MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning | - |
| LLaVA-Med-v1.0
(w/o LoRA, w/ extra data) | 97.35 | LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day | - |
| MiniGPT-v2
(w/ LoRA, w/ extra data) | 87.65 | MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning | - |
| LLaVA-Med-v1.5
(w/ LoRA, w/o extra data) | 99.3 | LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day | - |
| Bunny-v1.0-3B
(w/ LoRA, w/o extra data) | 96.61 | Efficient Multimodal Learning from Data-centric Perspective | - |
| LLaVA-Med-v1.0
(w/o LoRA, w/o extra data) | 97.74 | LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day | - |
| MGM-2B
(w/o LoRA, w/o extra data) | 98.17 | Mini-Gemini: Mining the Potential of Multi-modality Vision Language
Models | - |
| LLaVA-v1
(w/ LoRA, w/ extra data) | 86.87 | Visual Instruction Tuning | - |