{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.26984", "kind": "paper", "url": "https://arxiv.org/abs/2606.26984"}, {"id": "gh:fudancvl/unison", "kind": "repo", "url": "https://github.com/FudanCVL/Unison"}], "authors": ["Jinyu Liu", "Xincheng Shuai", "Henghui Ding", "Yu-Gang Jiang"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.26984", "source_url": "https://arxiv.org/abs/2606.26984"}, "categories": ["General AI", "Multimodal"], "description": {"en": "Evaluates unified multimodal models on joint understanding and generation across four dimensions: internal consistency, understanding-guided generation, generation-guided understanding, and mutual enhancement, using 2,169 task samples."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.26984", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.26984", "title": "Unison"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Fudan University"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2606.26984", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2606.26984", "source_url": "https://openalex.org/W7166040635"}, "key": "claire-radar:2606.26984", "modality": null, "name": "Unison", "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_unison_ffbd3e3c", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "2fd05503dc827e45c212275a2f7b7713ec285da48615a48a4c6b8d5bf283b80b", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.26984"}, "publisher": null, "released": "2026-06-25", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.26984", "source_url": "https://arxiv.org/abs/2606.26984"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-26984", "source": "claire_radar", "source_benchmark_id": "2606.26984", "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/Unison", "githubScope": "benchmark_repo", "githubStars": 14, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2606.26984", "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", "state": "unavailable"}}, "status": "fresh"}, "capabilities": [], "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": "702c52da8df55316ee62da579bb57a5752fab832cf84ff1bbd8436c3b79ec1e0", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Evaluates unified multimodal models on joint understanding and generation across four dimensions: internal consistency, understanding-guided generation, generation-guided understanding, and mutual enhancement, using 2,169 task samples.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["exact coined title identity tied to benchmark evidence", "benchmark release stated in one sentence", "evaluation protocol evidence", "public artifact URL"], "snippet": "To bridge this gap, we introduce Unison, a comprehensive benchmark comprising 2,169 high-quality unified task samples, designed to evaluate joint understanding and generation in unified multimodal models."}, "familyId": "bmf_b3704083f1b6", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [{"evidence": [{"basis": "existing-code-link", "linkedUrl": "https://github.com/FudanCVL/Unison", "url": "https://github.com/FudanCVL/Unison"}, {"basis": "existing-metric-association", "linkedUrl": "https://github.com/FudanCVL/Unison", "url": "https://huggingface.co/papers/2606.26984"}, {"basis": "linked-from-report", "linkedUrl": "https://github.com/FudanCVL/Unison", "url": "https://arxiv.org/abs/2606.26984"}, {"basis": "linked-from-report", "linkedUrl": "https://github.com/FudanCVL/Unison.", "url": "https://arxiv.org/abs/2606.26984"}], "scope": "benchmark_repo", "url": "https://github.com/FudanCVL/Unison", "verification": "source-linked"}], "status": "linked"}, "heat": null, "id": "bm_unison_ffbd3e3c", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": "https://github.com/FudanCVL/Unison", "data": null, "hfPaper": "https://huggingface.co/papers/2606.26984", "paper": "https://arxiv.org/abs/2606.26984", "pdf": "https://arxiv.org/pdf/2606.26984", "project": null, "report": "https://arxiv.org/abs/2606.26984"}, "metrics": [], "motivation": "Unified multimodal models capable of both understanding and generation have achieved remarkable strides.", "name": "Unison", "oneLine": "Evaluates unified multimodal models on joint understanding and generation across four dimensions: internal consistency, understanding-guided generation, generation-guided understanding, and mutual enhancement, using 2,169 task samples.", "paperTitle": "Unison: Benchmarking Unified Multimodal Models via Synergistic Understanding and Generation", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.26984", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "FudanCVL", "organizationType": "academic-lab", "role": "benchmark-publisher", "sourceUrl": "https://github.com/FudanCVL/Unison"}], "ranking": {}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-06-25", "source": {"authors": ["Jinyu Liu", "Xincheng Shuai", "Henghui Ding", "Yu-Gang Jiang"], "categories": ["cs.CV"], "id": "2606.26984", "title": "Unison: Benchmarking Unified Multimodal Models via Synergistic Understanding and Generation", "type": "arxiv", "url": "https://arxiv.org/abs/2606.26984"}, "sourceUpdatedAt": "2026-06-25T12:58:54Z", "topics": ["Multimodal"], "venueAttempts": [], "whyItMatters": "Existing benchmarks assess understanding and generation in isolation, missing the synergy between them. This benchmark provides a diagnostic and human-aligned evaluation to measure and compare integrated capabilities, aiding model development."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
