Rethinking State Tracking in Recurrent Models Through Error Control Dynamics Paper • 2605.07755 • Published 4 days ago • 15
Decomposed Attention Fusion in MLLMs for Training-Free Video Reasoning Segmentation Paper • 2510.19592 • Published Oct 22, 2025 • 13
Streaming Video Question-Answering with In-context Video KV-Cache Retrieval Paper • 2503.00540 • Published Mar 1, 2025 • 3