videoscore2/vs2_qwen3vl_sft_27k_5e-5_2fps_960_720_8192 Image-to-Text • 770k • Updated 18 days ago • 87
videoscore2/vs2_internvl3_5_sft_27k_5e-5_2fps_960_720_8192 Any-to-Any • 695k • Updated 18 days ago • 80
videoscore2/vs2_qwen3vl_sft_27k_5e-5_2fps_960_720_8192 Image-to-Text • 770k • Updated 18 days ago • 87
videoscore2/vs2_internvl3_5_sft_27k_5e-5_2fps_960_720_8192 Any-to-Any • 695k • Updated 18 days ago • 80
TUNA: Taming Unified Visual Representations for Native Unified Multimodal Models Paper • 2512.02014 • Published 24 days ago • 67
BrowserAgent: Building Web Agents with Human-Inspired Web Browsing Actions Paper • 2510.10666 • Published Oct 12 • 27