HyperAIHyperAI

Command Palette

Search for a command to run...

Console

Referring Expression Generation On Coloninst

Metrics

Accuray

Results

Performance results of various models on this benchmark

Paper Title
ColonGPT (w/ LoRA, w/o extra data)99.96Frontiers in Intelligent Colonoscopy
LLaVA-v1.5 (w/ LoRA, w/ extra data)99.32Improved Baselines with Visual Instruction Tuning
LLaVA-Med-v1.5 (w/ LoRA, w/o extra data)99.3LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day
MGM-2B (w/o LoRA, w/ extra data)98.75Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models
LLaVA-v1.5 (w/ LoRA, w/o extra data)98.58Improved Baselines with Visual Instruction Tuning
MGM-2B (w/o LoRA, w/o extra data)98.17Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models
MobileVLM-1.7B (w/ LoRA, w/ extra data)97.87MobileVLM : A Fast, Strong and Open Vision Language Assistant for Mobile Devices
MobileVLM-1.7B (w/o LoRA, w/ extra data)97.78MobileVLM : A Fast, Strong and Open Vision Language Assistant for Mobile Devices
LLaVA-Med-v1.0 (w/o LoRA, w/o extra data)97.74LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day
LLaVA-Med-v1.0 (w/o LoRA, w/ extra data)97.35LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day
Bunny-v1.0-3B (w/ LoRA, w/o extra data)96.61Efficient Multimodal Learning from Data-centric Perspective
Bunny-v1.0-3B (w/ LoRA, w/ extra data)96.02Efficient Multimodal Learning from Data-centric Perspective
MiniGPT-v2 (w/ LoRA, w/o extra data)94.69MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning
LLaVA-Med-v1.5 (w/ LoRA, w/ extra data)90.4LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day
MiniGPT-v2 (w/ LoRA, w/ extra data)87.65MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning
LLaVA-v1 (w/ LoRA, w/ extra data)86.87Visual Instruction Tuning
LLaVA-v1 (w/ LoRA, w/o extra data)84.55Visual Instruction Tuning
0 of 17 row(s) selected.