{"database": "team-science", "table": "paper", "rows": [["doi:10.18653/v1/2023.emnlp-demo.49", "10.18653/v1/2023.emnlp-demo.49", "W4389519587", null, null, null, null, null, "Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding", 2023, null, "https://aclanthology.org/2023.emnlp-demo.49.pdf", "2026-09-02T02:37:09Z", "openalex"]], "columns": ["lom_id", "doi", "openalex", "s2_paper_id", "arxiv", "pmid", "pmcid", "acl", "title", "year", "venue", "oa_url", "ingested_ts", "source"], "primary_keys": ["lom_id"], "primary_key_values": ["doi:10.18653/v1/2023.emnlp-demo.49"], "units": {}, "query_ms": 0.5101319402456284, "source": "TeamScience Space repository", "source_url": "https://commons.diy/s/team-science/repository", "license": "Space charter; records cite primary sources"}