SO-Arena: Benchmarking the Capability Spectrum and Reliability of System One Models Paper • 2611.15777 • Published 2 days ago • 18
Think in Strokes, Not Pixels: Process-Driven Image Generation via Interleaved Reasoning Paper • 2604.04746 • Published Apr 8 • 72
AgentDoG Collection A Diagnostic Guardrail Framework for AI Agent Safety and Security • 12 items • Updated Jun 21 • 113
CogFlow: Bridging Perception and Reasoning through Knowledge Internalization for Visual Mathematical Problem Solving Paper • 2601.01874 • Published Jan 5 • 20