OmniVideo-100K: A Dataset for Audio-Visual Reasoning through Structured Scripts and Evidence Chains Paper • 2606.14702 • Published 18 days ago • 31
ACL-Verbatim: hallucination-free question answering for research Paper • 2605.21102 • Published May 20 • 8
AsyncTool: Evaluating the Asynchronous Function Calling Capability under Multi-Task Scenarios Paper • 2605.27995 • Published May 27 • 16
EarlyTom: Early Token Compression Completes Fast Video Understanding Paper • 2605.30010 • Published May 28 • 32