{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.07643", "kind": "paper", "url": "https://arxiv.org/abs/2606.07643"}, {"kind": "repo", "url": "https://github.com/FudanCVL/AVI-Bench/blob/main/LICENSE"}, {"kind": "website", "url": "https://fudancvl.github.io/AVI-Bench/"}], "authors": ["Yaoting Wang", "Ziyi Zhang", "Wenming Tu", "Shaoxuan Xu", "Wenjie Du", "Cheng Liang", "Weijun Wang", "Yuanchao Li", "Guangyao Li", "Hao Fei", "Yuanchun Li", "Henghui Ding", "Yunxin Liu"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.07643", "source_url": "https://arxiv.org/abs/2606.07643"}, "categories": ["General AI", "Multimodal", "Reasoning"], "description": {"en": "AVI-Bench evaluates omni-multimodal LLMs on audio-visual tasks across perception, understanding, and reasoning stages, with an extension probing primitive audio-visual sensation using unfamiliar low-semantic stimuli."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.07643", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.07643", "title": "AVI-Bench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2606.07643", "modality": null, "name": "AVI-Bench", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"confidence": "High", "crawl_bundle": "claire_radar_2026-10-14", "crawled_at": "2026-10-14T09:44:51Z", "data_status": "primary-source-indexed", "display_eligible": "unknown", "origin_record_id": "bm_avi-bench_16159c13", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "7d37b9b5b6b3dd16cbbec2661df004387c0a6dde5833159a63c2185a568f0b17", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.07643"}, "publisher": null, "released": "2026-06-01", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.07643", "source_url": "https://arxiv.org/abs/2606.07643"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-07643", "source": "claire_radar", "source_benchmark_id": "2606.07643", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Multimodal", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": "https://github.com/FudanCVL/AVI-Bench", "githubScope": "hosting_repo", "githubStars": 18, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": 0, "hfPaperUrl": "https://huggingface.co/papers/2606.07643", "observedAt": "2026-10-04T15:31:48.030916Z", "signalStatus": {"githubStars": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"checkedAt": "2026-10-04T15:31:48.030916Z", "lastSuccessfulDate": "2026-09-30", "state": "stale"}}, "status": "fresh"}, "capabilities": ["Reasoning"], "confidence": "High", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "01ad0a58264e4b4cff6b1e56d3583d66a3ad3c244f024bc0848fa314a3887ea3", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "AVI-Bench evaluates omni-multimodal LLMs on audio-visual tasks across perception, understanding, and reasoning stages, with an extension probing primitive audio-visual sensation using unfamiliar low-semantic stimuli.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["coined title prefix ending in Bench or Benchmark", "benchmark release stated in one sentence", "evaluation protocol evidence", "public artifact URL"], "snippet": "We introduce AVI-Bench, a cognitively inspired benchmark that evaluates Omni-MLLMs across three stages, perception, understanding, and reasoning, through cross-modal tasks requiring joint audio-visual interpretation."}, "familyId": "bmf_b71e730eed92", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [{"evidence": [{"basis": "linked-from-project", "linkedUrl": "https://github.com/FudanCVL/AVI-Bench", "url": "https://fudancvl.github.io/AVI-Bench/"}, {"basis": "linked-from-project", "linkedUrl": "https://github.com/FudanCVL/AVI-Bench/blob/main/LICENSE", "url": "https://fudancvl.github.io/AVI-Bench/"}, {"basis": "linked-from-project", "linkedUrl": "https://github.com/FudanCVL/AVI-Bench/blob/main/DATA_USE_POLICY.md", "url": "https://fudancvl.github.io/AVI-Bench/"}], "scope": "benchmark_repo", "url": "https://github.com/FudanCVL/AVI-Bench", "verification": "source-linked"}], "status": "linked"}, "heat": null, "id": "bm_avi-bench_16159c13", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": "https://github.com/FudanCVL/AVI-Bench/blob/main/LICENSE", "data": null, "hfPaper": "https://huggingface.co/papers/2606.07643", "paper": "https://arxiv.org/abs/2606.07643", "pdf": "https://arxiv.org/pdf/2606.07643", "project": "https://fudancvl.github.io/AVI-Bench/", "report": "https://arxiv.org/abs/2606.07643"}, "metrics": [], "motivation": "Recent advances in Omni-Multimodal Large Language Models (Omni-MLLMs) have enabled strong integration of vision, audio, and language.", "name": "AVI-Bench", "oneLine": "AVI-Bench evaluates omni-multimodal LLMs on audio-visual tasks across perception, understanding, and reasoning stages, with an extension probing primitive audio-visual sensation using unfamiliar low-semantic stimuli.", "paperTitle": "AVI-Bench: Toward Human-like Audio-Visual Intelligence of Omni-MLLMs", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.07643", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-06-01", "source": {"authors": ["Yaoting Wang", "Ziyi Zhang", "Wenming Tu", "Shaoxuan Xu", "Wenjie Du", "Cheng Liang", "Weijun Wang", "Yuanchao Li", "Guangyao Li", "Hao Fei", "Yuanchun Li", "Henghui Ding", "Yunxin Liu"], "categories": ["cs.CV", "cs.AI", "cs.SD", "eess.AS"], "id": "2606.07643", "title": "AVI-Bench: Toward Human-like Audio-Visual Intelligence of Omni-MLLMs", "type": "arxiv", "url": "https://arxiv.org/abs/2606.07643"}, "sourceUpdatedAt": "2026-06-01T19:12:09Z", "topics": ["Reasoning"], "venueAttempts": [], "whyItMatters": "Provides a structured way to measure joint audio-visual capabilities in multimodal models, which is currently under-evaluated."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
