{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.02482", "kind": "paper", "url": "https://arxiv.org/abs/2606.02482"}, {"id": "gh:peiwensun2000/x-stream", "kind": "repo", "url": "https://github.com/PeiwenSun2000/X-Stream"}, {"kind": "website", "url": "https://peiwensun2000.github.io/xstream/"}], "authors": ["Peiwen Sun", "Xudong Lu", "Huadai Liu", "Yang Bo", "Dongming Wu", "Huankang Guan", "Minghong Cai", "Jinpeng Chen", "Xintong Guo", "Shuhan Li", "Fang Liu", "Rui Liu", "Xiangyu Yue"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.02482", "source_url": "https://arxiv.org/abs/2606.02482"}, "categories": ["Autonomous Driving", "Vision & 3D", "cs.CV"], "description": {"en": "Evaluates multimodal large language models on multi-stream streaming understanding, with 4,220 QA pairs across 932 videos covering 11 subtasks in multi-window, multi-view, and multi-device scenarios, using a dual-verification construction pipeline and online inference under a fixed average video-token rate."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.02482", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.02482", "title": "X-Stream"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2606.02482", "modality": null, "name": "X-Stream", "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_x-stream_b79ec653", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "8043096caf3c65cf5a750e61029eb6ea1223f9b59b6b41eff750c8d9c5d0b020", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.02482"}, "publisher": null, "released": "2026-06-01", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.02482", "source_url": "https://arxiv.org/abs/2606.02482"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-02482", "source": "claire_radar", "source_benchmark_id": "2606.02482", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["Autonomous Driving"], "area": "Vision & 3D", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": "https://github.com/PeiwenSun2000/X-Stream", "githubScope": "benchmark_repo", "githubStars": 36, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": 31, "hfPaperUrl": "https://huggingface.co/papers/2606.02482", "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": [], "confidence": "High", "construction": "Transform Existing", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "b1ff0c2b2e664aee9dd1a89b560d911f0249840395675cd01ee014873fe5bb87", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Evaluates multimodal large language models on multi-stream streaming understanding, with 4,220 QA pairs across 932 videos covering 11 subtasks in multi-window, multi-view, and multi-device scenarios, using a dual-verification construction pipeline and online inference under a fixed average video-token rate.", "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, we introduce X-Stream, the first benchmark dedicated to multi-stream streaming understanding."}, "familyId": "bmf_229d06cf6ea7", "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/PeiwenSun2000/X-Stream", "url": "https://github.com/PeiwenSun2000/X-Stream"}, {"basis": "existing-metric-association", "linkedUrl": "https://github.com/PeiwenSun2000/X-Stream", "url": "https://huggingface.co/papers/2606.02482"}, {"basis": "linked-from-project", "linkedUrl": "https://github.com/PeiwenSun2000/X-Stream", "url": "https://peiwensun2000.github.io/xstream/"}], "scope": "benchmark_repo", "url": "https://github.com/PeiwenSun2000/X-Stream", "verification": "source-linked"}], "status": "linked"}, "heat": null, "id": "bm_x-stream_b79ec653", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": ["Automotive"], "links": {"code": "https://github.com/PeiwenSun2000/X-Stream", "data": null, "hfPaper": "https://huggingface.co/papers/2606.02482", "paper": "https://arxiv.org/abs/2606.02482", "pdf": "https://arxiv.org/pdf/2606.02482", "project": "https://peiwensun2000.github.io/xstream/", "report": "https://arxiv.org/abs/2606.02482"}, "metrics": [], "motivation": "While video streaming understanding has made significant strides, real-world applications, such as live sports broadcasting, autonomous driving, and multi-screen collaboration, inherently demand continuous, multi-stream interactions.", "name": "X-Stream", "oneLine": "Evaluates multimodal large language models on multi-stream streaming understanding, with 4,220 QA pairs across 932 videos covering 11 subtasks in multi-window, multi-view, and multi-device scenarios, using a dual-verification construction pipeline and online inference under a fixed average video-token rate.", "paperTitle": "X-Stream: Exploring MLLMs as Multiplexers for Multi-Stream Understanding", "primaryDomain": "Autonomous Driving", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.02482", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "MMLab, CUHK", "organizationType": "academic-lab", "role": "benchmark-publisher", "sourceUrl": "https://github.com/PeiwenSun2000/X-Stream"}, {"name": "Huawei Inc.", "organizationType": "company-research-lab", "role": "benchmark-publisher", "sourceUrl": "https://github.com/PeiwenSun2000/X-Stream"}], "ranking": {}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-06-01", "source": {"authors": ["Peiwen Sun", "Xudong Lu", "Huadai Liu", "Yang Bo", "Dongming Wu", "Huankang Guan", "Minghong Cai", "Jinpeng Chen", "Xintong Guo", "Shuhan Li", "Fang Liu", "Rui Liu", "Xiangyu Yue"], "categories": ["cs.CV"], "id": "2606.02482", "title": "X-Stream: Exploring MLLMs as Multiplexers for Multi-Stream Understanding", "type": "arxiv", "url": "https://arxiv.org/abs/2606.02482"}, "sourceUpdatedAt": "2026-06-29T07:37:14Z", "topics": ["cs.CV"], "venueAttempts": [], "whyItMatters": "Existing benchmarks focus on single-stream video understanding, leaving a gap for evaluating concurrent video streams common in live sports, autonomous driving, and multi-screen applications. This benchmark provides a practical evaluation protocol for multi-stream reasoning and exposes limitations in current models."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
