{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.14721", "kind": "paper", "url": "https://arxiv.org/abs/2608.14721"}], "authors": ["Shenghong Yi", "Lin Zhang", "Muzian Li", "Jiakang Yuan", "Haoyu Zhang", "Peng Ye", "Jiayuan Fan", "Huafeng Qin", "Tao Chen"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.14721", "source_url": "https://arxiv.org/abs/2608.14721"}, "categories": ["Reasoning", "Robotics & Embodied AI", "Vision & 3D"], "description": {"en": "AeroGround evaluates vision-language models on aerial-ground collaborative reasoning using a simulated dataset of ~29,000 multimodal observation groups and 2,250 QA instances covering cross-view correspondence, spatial understanding, and reasoning."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.14721", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.14721", "title": "AeroGround"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Fudan University", "Shanghai Innovation Institute", "Chinese University of Hong Kong", "Chongqing Technology and Business University"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2608.14721", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2608.14721", "source_url": "https://openalex.org/W7203681087"}, "key": "claire-radar:2608.14721", "modality": null, "name": "AeroGround", "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_aeroground_3ddedf6a", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "794309a4385ad0ea58194c9c58222f8bfacb0cc00b6ae0304c5283670db36ba7", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2608.14721"}, "publisher": null, "released": "2026-08-12", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.14721", "source_url": "https://arxiv.org/abs/2608.14721"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-14721", "source": "claire_radar", "source_benchmark_id": "2608.14721", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["Robotics & Embodied AI"], "area": "Vision & 3D", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": null, "githubScope": null, "githubStars": null, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2608.14721", "observedAt": "2026-10-04T03:02:42.754940Z", "signalStatus": {"githubStars": {"state": "not_applicable"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"checkedAt": "2026-10-04T15:31:48.030916Z", "state": "unavailable"}}, "status": "unavailable"}, "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": "ebe3a22902cb80d2177531bb1b4faed54b18b91302869e46a93fd79adfcdedfe", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "AeroGround evaluates vision-language models on aerial-ground collaborative reasoning using a simulated dataset of ~29,000 multimodal observation groups and 2,250 QA instances covering cross-view correspondence, spatial understanding, and reasoning.", "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"], "snippet": "To address this gap, we introduce AeroGround, a comprehensive benchmark for evaluating VLMs in aerial-ground collaborative reasoning."}, "familyId": "bmf_0dd007a3643a", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_aeroground_3ddedf6a", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": ["Robotics"], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2608.14721", "paper": "https://arxiv.org/abs/2608.14721", "pdf": "https://arxiv.org/pdf/2608.14721", "project": null, "report": "https://arxiv.org/abs/2608.14721"}, "metrics": [], "motivation": "Vision-language models (VLMs) have been widely employed in understanding and reasoning tasks for unmanned aerial vehicles (UAVs).", "name": "AeroGround", "oneLine": "AeroGround evaluates vision-language models on aerial-ground collaborative reasoning using a simulated dataset of ~29,000 multimodal observation groups and 2,250 QA instances covering cross-view correspondence, spatial understanding, and reasoning.", "paperTitle": "AeroGround: A Comprehensive Benchmark for Aerial-Ground Collaborative Reasoning", "primaryDomain": "Robotics & Embodied AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2608.14721", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "arXiv", "organizationType": "benchmark-organization", "role": "benchmark-publisher", "sourceUrl": "https://arxiv.org/abs/2608.14721"}], "ranking": {"90d": {"confidence": "Low", "coverage": 0.0, "growth": {"components": {"githubStars": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfDatasetDownloads": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfPaperUpvotes": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "elapsedDays": null, "historyDate": null, "rank": null, "score": null, "windowDays": 90}, "level": {"components": {"githubStars": {"normalization": "log-max", "normalized": null, "value": null}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "rank": null, "score": null}, "method": "attention-ranking-v13", "rank": null, "score": null}}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-08-12", "source": {"authors": ["Shenghong Yi", "Lin Zhang", "Muzian Li", "Jiakang Yuan", "Haoyu Zhang", "Peng Ye", "Jiayuan Fan", "Huafeng Qin", "Tao Chen"], "categories": ["cs.CV"], "id": "2608.14721", "title": "AeroGround: A Comprehensive Benchmark for Aerial-Ground Collaborative Reasoning", "type": "arxiv", "url": "https://arxiv.org/abs/2608.14721"}, "sourceUpdatedAt": "2026-08-12T07:31:15Z", "topics": ["Reasoning"], "venueAttempts": [], "whyItMatters": "Existing UAV benchmarks focus on aerial-only views; AeroGround fills the gap for aerial-ground collaboration, offering a standardized evaluation for models in real-world applications like rescue and inspection, with clear human performance comparison."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
