Light-Omni: Reflex over Reasoning in Agentic Video Understanding with Long-Term Memory Paper • 2607.05511 • Published Jul 6 • 23
EvoEmbedding: Evolvable Representations for Long-Context Retrieval and Agentic Memory Paper • 2606.21649 • Published Jun 19 • 35
Video-MME-v2: Towards the Next Stage in Benchmarks for Comprehensive Video Understanding Paper • 2604.05015 • Published Apr 6 • 236