OpenVLHarness: Real World Visual Agentic Tool-Use with Multimodal Memory Paper • 2610.26860 • Published Oct 19 • 106
CommerceGen-Studio: An End-to-End Framework for Commercial-Grade Main-Image Generation Paper • 2610.20603 • Published Oct 14 • 26
OSWorld-Science: A Benchmark of Computer Use Agents for Learning and Using Scientific Software Paper • 2609.39903 • Published Sep 30 • 28
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
MonkeyOCRv2: A Visual-Text Foundation Model for Document AI Paper • 2607.11562 • Published Jul 13 • 36
RESOURCE2SKILL: Distilling Executable Agent Skills from Human-Created Multimodal Resources Paper • 2606.29538 • Published Jul 16 • 88
ClawGUI: A Unified Framework for Training, Evaluating, and Deploying GUI Agents Paper • 2604.11784 • Published Apr 13 • 94