{"adoption": {"forks": 73, "observed_at": "2026-08-28T04:03:15.964258+00:00", "stars": 1022}, "canonical_url": "https://ross.abutalabs.com/products/r1-omni", "card": {"archived": false, "artifact_type": "library", "description": null, "domain": ["artificial-intelligence", "large-language-models", "machine-learning"], "enriched": true, "function": ["machine-learning", "deep-learning", "llm-training", "speech-recognition", "video-processing", "nlp"], "health_score": 28, "homepage": null, "language": "Python", "license": null, "license_family": "other", "maturity": "experimental", "member_repos": ["HumanMLLM/R1-Omni"], "name": "HumanMLLM/R1-Omni", "platform": ["python"], "pushed_at": "2025-03-24T03:54:33+00:00", "repo": "HumanMLLM/R1-Omni", "stars": 1022, "tags": ["emotion-recognition", "multimodal", "reinforcement-learning", "rlvr", "omni-model", "research", "audio", "video", "gpu", "linux"], "topics": [], "urls": [], "use_cases": ["recognize emotions from video with audio and visual cues", "train a multimodal LLM with reinforcement learning and verifiable rewards", "get explainable reasoning for emotion recognition predictions", "fine-tune an omni-modal model on emotion datasets like MAFW and DFEW", "evaluate emotion recognition generalization on out-of-distribution data", "run inference with a 0.5B multimodal emotion model"], "what_it_is": "R1-Omni is a research project applying Reinforcement Learning with Verifiable Reward (RLVR) to an omni-multimodal large language model for explainable emotion recognition from video and audio. It releases model weights (HumanOmni-0.5B variants) and training/inference code built on the HumanOmni base model.", "when_to_avoid": ["you need a production-ready, well-documented pipeline (setup and reproduction docs are incomplete)", "you need single-modality (video-only or audio-only) inference, which is not yet supported", "you require a permissive license - no license is specified"], "when_to_choose": ["you need multimodal (audio+visual) emotion recognition with interpretable reasoning", "you want to experiment with RLVR training on multimodal LLMs", "you need open model weights for emotion recognition research"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/r1-omni", "repo": "HumanMLLM/R1-Omni", "role": "main", "score": 26}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:03:15.964258+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T07:08:41.423944+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a01f68f19aa2795e534973e6a1261834b3d8d9fe30411258ea6181b6c5efe5d6", "fetched_at": "2026-08-28T04:03:15.964258+00:00", "kind": "readme", "missing": false, "url": "https://github.com/HumanMLLM/R1-Omni"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:03:15.964258+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T07:08:41.423944+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a01f68f19aa2795e534973e6a1261834b3d8d9fe30411258ea6181b6c5efe5d6", "fetched_at": "2026-08-28T04:03:15.964258+00:00", "kind": "readme", "missing": false, "url": "https://github.com/HumanMLLM/R1-Omni"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T07:08:41.423944+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a01f68f19aa2795e534973e6a1261834b3d8d9fe30411258ea6181b6c5efe5d6", "fetched_at": "2026-08-28T04:03:15.964258+00:00", "kind": "readme", "missing": false, "url": "https://github.com/HumanMLLM/R1-Omni"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:03:15.964258+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:03:15.964258+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:03:15.964258+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T07:08:41.423944+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a01f68f19aa2795e534973e6a1261834b3d8d9fe30411258ea6181b6c5efe5d6", "fetched_at": "2026-08-28T04:03:15.964258+00:00", "kind": "readme", "missing": false, "url": "https://github.com/HumanMLLM/R1-Omni"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:03:15.964258+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:03:15.964258+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T07:08:41.423944+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a01f68f19aa2795e534973e6a1261834b3d8d9fe30411258ea6181b6c5efe5d6", "fetched_at": "2026-08-28T04:03:15.964258+00:00", "kind": "readme", "missing": false, "url": "https://github.com/HumanMLLM/R1-Omni"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:03:15.964258+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:03:15.964258+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:03:15.964258+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T07:08:41.423944+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a01f68f19aa2795e534973e6a1261834b3d8d9fe30411258ea6181b6c5efe5d6", "fetched_at": "2026-08-28T04:03:15.964258+00:00", "kind": "readme", "missing": false, "url": "https://github.com/HumanMLLM/R1-Omni"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:03:15.964258+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:03:15.964258+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T07:08:41.423944+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a01f68f19aa2795e534973e6a1261834b3d8d9fe30411258ea6181b6c5efe5d6", "fetched_at": "2026-08-28T04:03:15.964258+00:00", "kind": "readme", "missing": false, "url": "https://github.com/HumanMLLM/R1-Omni"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T07:08:41.423944+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a01f68f19aa2795e534973e6a1261834b3d8d9fe30411258ea6181b6c5efe5d6", "fetched_at": "2026-08-28T04:03:15.964258+00:00", "kind": "readme", "missing": false, "url": "https://github.com/HumanMLLM/R1-Omni"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T07:08:41.423944+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a01f68f19aa2795e534973e6a1261834b3d8d9fe30411258ea6181b6c5efe5d6", "fetched_at": "2026-08-28T04:03:15.964258+00:00", "kind": "readme", "missing": false, "url": "https://github.com/HumanMLLM/R1-Omni"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T07:08:41.423944+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a01f68f19aa2795e534973e6a1261834b3d8d9fe30411258ea6181b6c5efe5d6", "fetched_at": "2026-08-28T04:03:15.964258+00:00", "kind": "readme", "missing": false, "url": "https://github.com/HumanMLLM/R1-Omni"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 13, "longevity": 38, "rhythm": 35}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": ["no_releases", "no_license"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 542, "days_push": 527, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 26, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}