NARU: A Benchmark for NARrative Evolution and Cultural Nuance Understanding in Japanese Extreme Long Video Paper • 2608.13210 • Published 13 days ago • 8 • 3
Risk Assessment Framework for Code LLMs via Leveraging Internal States Paper • 2504.14640 • Published Apr 20, 2025 • 1
Evaluating LLMs on Sequential API Call Through Automated Test Generation Paper • 2507.09481 • Published Jul 13, 2025 • 1