Video-Arena: A Scalable Agentic Video Benchmark for Spatiotemporal Capability Paper • 2610.14158 • Published 6 days ago • 8
A Decade in a Day: Synthesizing Agent-Native Interfaces from Human-Oriented Software Evolution Paper • 2610.15765 • Published 4 days ago • 25
Just MLPs: Efficient Visual State Reconstruction for Multimodal Language Models Paper • 2609.34972 • Published 17 days ago • 30