{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.28049", "kind": "paper", "url": "https://arxiv.org/abs/2606.28049"}], "authors": ["Haotian Li", "Yida Wang", "Leyuan Wang", "Jinshan Lai", "Keyang Wang", "Zonghao Guo", "Qiang Ma", "Liuyu Xiang", "Jianwei Hu", "Zhaofeng He"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.28049", "source_url": "https://arxiv.org/abs/2606.28049"}, "categories": ["Multimodal", "Robotics & Embodied AI"], "description": {"en": "AirGroundBench evaluates multi-view spatial intelligence in multimodal large language models through UAV-UGV collaborative tasks, including 62,000 dual-view multiple-choice questions and 115 navigation episodes across 11 simulated environments."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.28049", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.28049", "title": "AirGroundBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Beijing University of Posts and Telecommunications", "University of Electronic Science and Technology of China", "Tsinghua University"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2606.28049", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2606.28049", "source_url": "https://openalex.org/W7166534173"}, "key": "claire-radar:2606.28049", "modality": null, "name": "AirGroundBench", "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_airgroundbench_74494075", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "b5213f2789328cf42ac92c80f0d8831c09f5c2b698cc95b44e8d32508485063e", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.28049"}, "publisher": null, "released": "2026-06-26", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.28049", "source_url": "https://arxiv.org/abs/2606.28049"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-28049", "source": "claire_radar", "source_benchmark_id": "2606.28049", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["Robotics & Embodied AI"], "area": "Robotics & Embodied AI", "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/2606.28049", "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": [], "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": "67a9fbeb96f546c48238838d660a8aa60cacac7fe43d51f51e9a6716b358389e", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "AirGroundBench evaluates multi-view spatial intelligence in multimodal large language models through UAV-UGV collaborative tasks, including 62,000 dual-view multiple-choice questions and 115 navigation episodes across 11 simulated environments.", "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"], "snippet": "We present AirGroundBench, a diagnostic benchmark for evaluating multi-view spatial intelligence in heterogeneous UAV-UGV collaboration."}, "familyId": "bmf_10bc9f42a87c", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_airgroundbench_74494075", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": ["Robotics"], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2606.28049", "paper": "https://arxiv.org/abs/2606.28049", "pdf": "https://arxiv.org/pdf/2606.28049", "project": null, "report": "https://arxiv.org/abs/2606.28049"}, "metrics": [], "motivation": "In recent years, multimodal large language models (MLLMs) have shown strong potential for embodied intelligence, yet their ability to maintain geometrically consistent spatial understanding across heterogeneous views remains under-evaluated.", "name": "AirGroundBench", "oneLine": "AirGroundBench evaluates multi-view spatial intelligence in multimodal large language models through UAV-UGV collaborative tasks, including 62,000 dual-view multiple-choice questions and 115 navigation episodes across 11 simulated environments.", "paperTitle": "AirGroundBench: Probing Spatial Intelligence in Multimodal Large Models under Heterogeneous Multi-View Embodied Collaboration", "primaryDomain": "Robotics & Embodied AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.28049", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "AirGroundBench Team", "organizationType": "academic-lab", "role": "benchmark-publisher", "sourceUrl": "https://arxiv.org/abs/2606.28049"}], "ranking": {}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-06-26", "source": {"authors": ["Haotian Li", "Yida Wang", "Leyuan Wang", "Jinshan Lai", "Keyang Wang", "Zonghao Guo", "Qiang Ma", "Liuyu Xiang", "Jianwei Hu", "Zhaofeng He"], "categories": ["cs.CV"], "id": "2606.28049", "title": "AirGroundBench: Probing Spatial Intelligence in Multimodal Large Models under Heterogeneous Multi-View Embodied Collaboration", "type": "arxiv", "url": "https://arxiv.org/abs/2606.28049"}, "sourceUpdatedAt": "2026-06-26T12:51:22Z", "topics": ["Multimodal"], "venueAttempts": [], "whyItMatters": "This benchmark addresses the gap in assessing geometric consistency across heterogeneous views, providing a structured evaluation for capabilities like cross-view alignment and spatial reasoning that are critical for embodied decision-making."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
