HRM-Text: Efficient Pretraining Beyond Scaling Paper • 2605.20613 • Published 28 days ago • 315
VideoSeeker: Incentivizing Instance-level Video Understanding via Native Agentic Tool Invocation Paper • 2605.16079 • Published May 15 • 28
Running on Zero MCP Featured 1.46k FireRed Image Edit 1.0 Fast 🌖 1.46k FireRed-Image-Edit × Qwen-Image-Edit-Rapid (Transformers)
Running on Zero MCP 186 Qwen Image Edit 2509 LoRAs Fast âš¡ 186 Demo of the Collection of Qwen Image Editing LoRAs
FashionChameleon: Towards Real-Time and Interactive Human-Garment Video Customization Paper • 2605.15824 • Published May 15 • 65
deepseek-ai/DeepSeek-V4-Flash Text Generation • 158B • Updated 9 days ago • 2.12M • • 1.51k
MolmoAct2: Action Reasoning Models for Real-world Deployment Paper • 2605.02881 • Published May 4 • 350
ClawGUI: A Unified Framework for Training, Evaluating, and Deploying GUI Agents Paper • 2604.11784 • Published Apr 13 • 143