Showing 1–13 of 13 results
/ Date/ Name
Jun 24, 2025Video-XL-2: Towards Very Long-Video Understanding Through Task-Aware KV SparsificationSep 25, 2025RAM-NAS: Resource-aware Multiobjective Neural Architecture Search Method for Robot Vision TasksJun 26, 2025Task-Aware KV Compression For Cost-Effective Long Video UnderstandingJan 31, 2026LegalOne: A Family of Foundation Models for Reliable Legal ReasoningSep 24, 2024Making Text Embedders Few-Shot LearnersSep 22, 2024Video-XL: Extra-Long Vision Language Model for Hour-Scale Video UnderstandingSep 8, 2025Simulating Dispute Mediation with LLM-Based Agents for Legal ResearchDec 28, 2025Video-Browser: Towards Agentic Open-web Video BrowsingFeb 14, 2026DeepXiv-SDK: An Agentic Data Interface for Scientific LiteratureMar 12, 2025Memory-enhanced Retrieval Augmentation for Long Video UnderstandingAug 22, 2024Large Language Models as Foundations for Next-Gen Dense Retrieval: A Comprehensive Empirical AssessmentJun 6, 2024MLVU: Benchmarking Multi-task Long Video UnderstandingSep 30, 2025TimeScope: Towards Task-Oriented Temporal Grounding In Long Videos