The Trinity:Capability-Driven Recursive Self-Improvement for Multimodal Agents Paper • 2610.36077 • Published 13 days ago • 160
Learning Where to Split: Dynamic Band Splitting for Audio Source Separation Paper • 2610.14993 • Published 29 days ago • 35
SpaceCast-Bench: Evaluating Predictive Spatial Reasoning in Vision-Language Models Paper • 2610.12402 • Published Oct 8 • 9
WeVisDoc: From Coverage to Capability for Robust End-to-End Document Parsing Paper • 2609.20423 • Published Sep 17 • 18
Gaze as Evidence for Common Grounding: A Cross-Corpus Analysis of MapTask and MUNDEX Paper • 2609.18011 • Published Sep 16 • 6
OpenART: Scaling Agent Red Teaming via Open-Ended Environment Evolution Paper • 2608.00677 • Published Aug 1 • 26