Vidu S2: Real-Time Interactive, Editable, and Spatial Video Generation Paper • 2609.11638 • Published Sep 10 • 220
StateM: Reaching 95.3% Raw Accuracy, or a \$15 Frontier Run, on Terminal-Bench 2.1 via Harness Scaling Paper • 2608.15089 • Published Aug 15 • 104
Running 101 Qwen3.8-27B Free Endpoint 🌀 101 Generate text answers using a free OpenAI‑compatible Qwen 3.8 API
MonkeyOCRv2: A Visual-Text Foundation Model for Document AI Paper • 2607.11562 • Published Jul 13 • 36
Running on Zero MCP 273 Dream Motion Pro - Wan 2.2 🎬 273 Fast Wan 2.2 image-to-video with first/last frames
Running on Zero Agents Featured 173 Stable Audio 3 🎵 173 Text-to-audio with SA3 Medium / Small Music / Small SFX.