Novel Claim or Déjà Vu? Rethinking "Contamination-Free'' Dynamic Evaluation for Multimodal Automated Fact-Checking Paper • 2607.23514 • Published 4 days ago • 13
Beyond NL2Code: A Structured Survey of Multimodal Code Intelligence Paper • 2606.15932 • Published Jun 16 • 38
WBench: A Comprehensive Multi-turn Benchmark for Interactive Video World Model Evaluation Paper • 2605.25874 • Published May 25 • 106