OpenWebRL: Demystifying Online Multi-turn Reinforcement Learning for Visual Web Agents Paper • 2606.02031 • Published 3 days ago • 11
CiteVQA: Benchmarking Evidence Attribution for Trustworthy Document Intelligence Paper • 2605.12882 • Published 22 days ago • 270
LuffyTheFox/Qwen3.6-35B-A3B-Uncensored-Wasserstein-GGUF Image-Text-to-Text • 35B • Updated about 8 hours ago • 466k • 94
From Context to Skills: Can Language Models Learn from Context Skillfully? Paper • 2604.27660 • Published May 3 • 166
ArtifactNet: Detecting AI-Generated Music via Forensic Residual Physics Paper • 2604.16254 • Published Apr 17 • 3