osunlp/UGround-V1-2B

Image-Text-to-Text • Updated 5 days ago • 376 • 5

Note Based on Qwen2-VL-2B-Instruct

osunlp/UGround-V1-7B

Image-Text-to-Text • Updated 5 days ago • 416 • 2

Note Based on Qwen2-VL-7B-Instruct

osunlp/UGround-V1-72B

Image-Text-to-Text • Updated about 3 hours ago

Note Based on Qwen2-VL-72B-Instruct. Full training without LoRA.

osunlp/UGround-V1-72B-Preview

Image-Text-to-Text • Updated 3 days ago • 276

Note Based on Qwen2-VL-72B-Instruct. Trained with LoRA.

osunlp/UGround

Image-Text-to-Text • Updated 5 days ago • 6.67k • 19

Note The initial model. Based on the modified LLaVA arch (CLIP + Vicuna-7B) describe in the paper

Note Low-cost, scalable and effective data synthesis pipeline for GUI visaul grounding; SOTA GUI visual grounding model UGround; purely vision-only (modular) GUI agent framework SeeAct-V; first time demonstrating SOTA performance of vision-only GUI agents.

Note Paused. Will open a new one for Qwen2-VL-based UGround

Note Paused. Trying to figure out how to accelerate the inference. And will open a new one for UGround-V1.1