2 papers
cs.CV2026
MAVIS: Multi-Agent Video Retrieval via Structured Video Understanding
Jie Zhang, Qilang Ye, Hao Zhou +2
The dominant paradigm in video retrieval relies on embedding-based full-corpus scanning, which suffers from inherent computational inefficiency and the semantic asymmetry between i…
cs.AI2025
Truncated Proximal Policy Optimization
Tiantian Fan, Lingjun Liu, Yu Yue +20
Recently, test-time scaling Large Language Models (LLMs) have demonstrated exceptional reasoning capabilities across scientific and professional tasks by generating long chains-of-…