{"adoption": {"forks": 255, "observed_at": "2026-08-28T04:08:07.494120+00:00", "stars": 3500}, "canonical_url": "https://ross.abutalabs.com/products/video-llava", "card": {"archived": false, "artifact_type": "library", "description": "【EMNLP 2024🔥】Video-LLaVA: Learning United Visual Representation by Alignment Before Projection", "domain": ["large-language-models", "computer-vision", "artificial-intelligence"], "enriched": true, "function": ["machine-learning", "deep-learning", "llm-inference", "video-processing", "image-processing", "nlp"], "health_score": 20, "homepage": "https://arxiv.org/pdf/2311.10122.pdf", "language": "Python", "license": "Apache-2.0", "license_family": "permissive", "maturity": "active", "member_repos": ["PKU-YuanGroup/Video-LLaVA"], "name": "PKU-YuanGroup/Video-LLaVA", "platform": ["python"], "pushed_at": "2024-12-03T02:58:46+00:00", "repo": "PKU-YuanGroup/Video-LLaVA", "stars": 3500, "tags": ["multimodal", "vision-language-model", "video-understanding", "instruction-tuning", "video-qa", "research", "video", "natural-language-processing", "gpu", "linux"], "topics": ["instruction-tuning", "large-vision-language-model", "multi-modal"], "urls": [], "use_cases": ["answer questions about videos with an llm", "video question answering model", "chat with images and videos using a vision-language model", "run multimodal llm inference on video", "fine-tune a video-language model with instruction tuning", "unified image and video understanding model"], "what_it_is": "Video-LLaVA is a large vision-language model that aligns image and video representations into a unified visual space before projection into the language model, enabling joint image and video understanding. It is an EMNLP 2024 research codebase with pretrained checkpoints, training scripts, and demo spaces.", "when_to_avoid": ["you need production-grade, commercially supported multimodal APIs", "you lack a GPU for inference or training", "you only need text-only LLM capabilities"], "when_to_choose": ["you need a single model that handles both image and video inputs", "you want an open-source research baseline for video-language alignment", "you need video question answering or captioning with an LLM"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/video-llava", "repo": "PKU-YuanGroup/Video-LLaVA", "role": "main", "score": 27}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:08:07.494120+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T18:35:48.427696+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6c3ae86af9eeff3e1bc0386829191ac300f0f108dd6a8df16eeaadab40ec2c8d", "fetched_at": "2026-08-28T04:08:07.494120+00:00", "kind": "readme", "missing": false, "url": "https://github.com/PKU-YuanGroup/Video-LLaVA"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:08:07.494120+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T18:35:48.427696+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6c3ae86af9eeff3e1bc0386829191ac300f0f108dd6a8df16eeaadab40ec2c8d", "fetched_at": "2026-08-28T04:08:07.494120+00:00", "kind": "readme", "missing": false, "url": "https://github.com/PKU-YuanGroup/Video-LLaVA"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T18:35:48.427696+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6c3ae86af9eeff3e1bc0386829191ac300f0f108dd6a8df16eeaadab40ec2c8d", "fetched_at": "2026-08-28T04:08:07.494120+00:00", "kind": "readme", "missing": false, "url": "https://github.com/PKU-YuanGroup/Video-LLaVA"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:08:07.494120+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:08:07.494120+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:08:07.494120+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T18:35:48.427696+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6c3ae86af9eeff3e1bc0386829191ac300f0f108dd6a8df16eeaadab40ec2c8d", "fetched_at": "2026-08-28T04:08:07.494120+00:00", "kind": "readme", "missing": false, "url": "https://github.com/PKU-YuanGroup/Video-LLaVA"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:08:07.494120+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:08:07.494120+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T18:35:48.427696+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6c3ae86af9eeff3e1bc0386829191ac300f0f108dd6a8df16eeaadab40ec2c8d", "fetched_at": "2026-08-28T04:08:07.494120+00:00", "kind": "readme", "missing": false, "url": "https://github.com/PKU-YuanGroup/Video-LLaVA"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:08:07.494120+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:08:07.494120+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:08:07.494120+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T18:35:48.427696+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6c3ae86af9eeff3e1bc0386829191ac300f0f108dd6a8df16eeaadab40ec2c8d", "fetched_at": "2026-08-28T04:08:07.494120+00:00", "kind": "readme", "missing": false, "url": "https://github.com/PKU-YuanGroup/Video-LLaVA"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:08:07.494120+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:08:07.494120+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T18:35:48.427696+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6c3ae86af9eeff3e1bc0386829191ac300f0f108dd6a8df16eeaadab40ec2c8d", "fetched_at": "2026-08-28T04:08:07.494120+00:00", "kind": "readme", "missing": false, "url": "https://github.com/PKU-YuanGroup/Video-LLaVA"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T18:35:48.427696+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6c3ae86af9eeff3e1bc0386829191ac300f0f108dd6a8df16eeaadab40ec2c8d", "fetched_at": "2026-08-28T04:08:07.494120+00:00", "kind": "readme", "missing": false, "url": "https://github.com/PKU-YuanGroup/Video-LLaVA"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T18:35:48.427696+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6c3ae86af9eeff3e1bc0386829191ac300f0f108dd6a8df16eeaadab40ec2c8d", "fetched_at": "2026-08-28T04:08:07.494120+00:00", "kind": "readme", "missing": false, "url": "https://github.com/PKU-YuanGroup/Video-LLaVA"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T18:35:48.427696+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6c3ae86af9eeff3e1bc0386829191ac300f0f108dd6a8df16eeaadab40ec2c8d", "fetched_at": "2026-08-28T04:08:07.494120+00:00", "kind": "readme", "missing": false, "url": "https://github.com/PKU-YuanGroup/Video-LLaVA"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 74, "rhythm": 35}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": ["no_releases"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 1045, "days_push": 638, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 27, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}