{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QSJ375FM5TOARRSRQELOHTRTXB","short_pith_number":"pith:QSJ375FM","schema_version":"1.0","canonical_sha256":"8493bff4acecdc08c6518116e3ce33b841880000422ccc2606d100716fe993bc","source":{"kind":"arxiv","id":"2412.07689","version":5},"attestation_state":"computed","paper":{"title":"RoboTron-Drive: All-in-One Large Multimodal Model for Autonomous Driving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM","cs.RO"],"primary_cat":"cs.CV","authors_text":"Baihui Xiao, Chengjian Feng, Feng Yan, Lin Ma, Xiaodan Liang, Yujie Zhong, Zequn Jie, Zhijian Huang","submitted_at":"2024-12-10T17:27:32Z","abstract_excerpt":"Large Multimodal Models (LMMs) have demonstrated exceptional comprehension and interpretation capabilities in Autonomous Driving (AD) by incorporating large language models. Despite the advancements, current data-driven AD approaches tend to concentrate on a single dataset and specific tasks, neglecting their overall capabilities and ability to generalize. To bridge these gaps, we propose RoboTron-Drive, a general large multimodal model designed to process diverse data inputs, such as images and multi-view videos, while performing a broad spectrum of AD tasks, including perception, prediction,"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2412.07689","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-10T17:27:32Z","cross_cats_sorted":["cs.MM","cs.RO"],"title_canon_sha256":"2b70daf61731454a3ad55373c520d284a01cd67959ebc023580b5005ac34ecb6","abstract_canon_sha256":"4c055d9d1d5c92bc3ba7738ed78d1c4bcabc7bff3d0c4126b466172532677ff8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:49:48.733618Z","signature_b64":"xP4aeuRCb4ipBZr4KRJHpNHkqn10Au68RVYT71zsTwOfZOnbml8XczKLhx2qi/5F8rzM2q5A5knRIHbnddy2BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8493bff4acecdc08c6518116e3ce33b841880000422ccc2606d100716fe993bc","last_reissued_at":"2026-07-05T11:49:48.733090Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:49:48.733090Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RoboTron-Drive: All-in-One Large Multimodal Model for Autonomous Driving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM","cs.RO"],"primary_cat":"cs.CV","authors_text":"Baihui Xiao, Chengjian Feng, Feng Yan, Lin Ma, Xiaodan Liang, Yujie Zhong, Zequn Jie, Zhijian Huang","submitted_at":"2024-12-10T17:27:32Z","abstract_excerpt":"Large Multimodal Models (LMMs) have demonstrated exceptional comprehension and interpretation capabilities in Autonomous Driving (AD) by incorporating large language models. Despite the advancements, current data-driven AD approaches tend to concentrate on a single dataset and specific tasks, neglecting their overall capabilities and ability to generalize. To bridge these gaps, we propose RoboTron-Drive, a general large multimodal model designed to process diverse data inputs, such as images and multi-view videos, while performing a broad spectrum of AD tasks, including perception, prediction,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.07689","kind":"arxiv","version":5},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2412.07689/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2412.07689","created_at":"2026-07-05T11:49:48.733149+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.07689v5","created_at":"2026-07-05T11:49:48.733149+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.07689","created_at":"2026-07-05T11:49:48.733149+00:00"},{"alias_kind":"pith_short_12","alias_value":"QSJ375FM5TOA","created_at":"2026-07-05T11:49:48.733149+00:00"},{"alias_kind":"pith_short_16","alias_value":"QSJ375FM5TOARRSR","created_at":"2026-07-05T11:49:48.733149+00:00"},{"alias_kind":"pith_short_8","alias_value":"QSJ375FM","created_at":"2026-07-05T11:49:48.733149+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":13,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.18483","citing_title":"Steadily moving semi-infinite fracture in plane poroelasticity","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27660","citing_title":"MVPruner: Dynamic Token Pruning for Accelerating Multi-view Vision-Language Models in Autonomous Driving","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00283","citing_title":"What's Hidden Matters: Identifying Planning-Critical Occluded Agents using Vision-Language Models","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01624","citing_title":"What to Test Next: Interpretable Coverage Gap Discovery in Driving VLMs","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27660","citing_title":"MVPruner: Dynamic Token Pruning for Accelerating Multi-view Vision-Language Models in Autonomous Driving","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18074","citing_title":"4DLidarOpen: An Open 4D FMCW Lidar Dataset for Motion-Aware Autonomous Driving","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2509.01944","citing_title":"AutoDrive-R$^2$: Incentivizing Reasoning and Self-Reflection Capacity for VLA Model in Autonomous Driving","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2604.00813","citing_title":"DVGT-2: Vision-Geometry-Action Model for Autonomous Driving at Scale","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10564","citing_title":"DeepSight: Long-Horizon World Modeling via Latent States Prediction for End-to-End Autonomous Driving","ref_index":192,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22260","citing_title":"Towards Safe Mobility: A Unified Transportation Foundation Model enabled by Open-Ended Vision-Language Dataset","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19145","citing_title":"ST-Prune: Training-Free Spatio-Temporal Token Pruning for Vision-Language Models in Autonomous Driving","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18484","citing_title":"XEmbodied: A Foundation Model with Enhanced Geometric and Physical Cues for Large-Scale Embodied Environments","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22851","citing_title":"EgoDyn-Bench: Evaluating Ego-Motion Understanding in Vision-Centric Foundation Models for Autonomous Driving","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QSJ375FM5TOARRSRQELOHTRTXB","json":"https://pith.science/pith/QSJ375FM5TOARRSRQELOHTRTXB.json","graph_json":"https://pith.science/api/pith-number/QSJ375FM5TOARRSRQELOHTRTXB/graph.json","events_json":"https://pith.science/api/pith-number/QSJ375FM5TOARRSRQELOHTRTXB/events.json","paper":"https://pith.science/paper/QSJ375FM"},"agent_actions":{"view_html":"https://pith.science/pith/QSJ375FM5TOARRSRQELOHTRTXB","download_json":"https://pith.science/pith/QSJ375FM5TOARRSRQELOHTRTXB.json","view_paper":"https://pith.science/paper/QSJ375FM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.07689&json=true","fetch_graph":"https://pith.science/api/pith-number/QSJ375FM5TOARRSRQELOHTRTXB/graph.json","fetch_events":"https://pith.science/api/pith-number/QSJ375FM5TOARRSRQELOHTRTXB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QSJ375FM5TOARRSRQELOHTRTXB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QSJ375FM5TOARRSRQELOHTRTXB/action/storage_attestation","attest_author":"https://pith.science/pith/QSJ375FM5TOARRSRQELOHTRTXB/action/author_attestation","sign_citation":"https://pith.science/pith/QSJ375FM5TOARRSRQELOHTRTXB/action/citation_signature","submit_replication":"https://pith.science/pith/QSJ375FM5TOARRSRQELOHTRTXB/action/replication_record"}},"created_at":"2026-07-05T11:49:48.733149+00:00","updated_at":"2026-07-05T11:49:48.733149+00:00"}