VideoSeeker: Incentivizing Instance-level Video Understanding via Native Agentic Tool Invocation Paper • 2605.16079 • Published May 15 • 29
Running on Zero MCP Featured 2.05k Qwen-Image-Edit-2511-LoRAs-Fast 🎃 2.05k Demo of the Collection of Qwen Image Edit LoRAs
Running on Zero MCP 240 Qwen Image Edit 2509 LoRAs Fast âš¡ 240 Demo of the Collection of Qwen Image Editing LoRAs
MMSkills: Towards Multimodal Skills for General Visual Agents Paper • 2605.13527 • Published May 14 • 122