{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:WL3J6PMRY44PG355LTYMMTX7WD","short_pith_number":"pith:WL3J6PMR","schema_version":"1.0","canonical_sha256":"b2f69f3d91c738f36fbd5cf0c64effb0d5ec03fb7dc31311b032f8557d9ee293","source":{"kind":"arxiv","id":"2607.01658","version":1},"attestation_state":"computed","paper":{"title":"Teaching Vision-Language-Action Models What to See and Where to Look","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baochang Zhang, Bo Zhang, Canyu Chen, Chunyang Liu, Juan Zhang, Kehua Sheng, Linlin Yang, Xianbin Cao, Yan Wang, Yizhi Wang, Yuguang Yang, Zhewen Tan, Zichao Feng","submitted_at":"2026-07-02T03:34:32Z","abstract_excerpt":"Vision-Language-Action (VLA) models have emerged as a promising paradigm for end-to-end autonomous driving. However, existing VLAs' training relies heavily on text-centric visual question answering and chain-of-thought reasoning data, which emphasizes linguistic reasoning rather than action-grounded planning. As a result, the learned representations capture semantic knowledge but lack spatial dependencies crucial for reliable trajectory prediction. We propose DriveTeach-VLA, a framework that explicitly teaches VLAs what to see and where to look. Driving-aware Vision Distillation (DVD) injects "},"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":"2607.01658","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-02T03:34:32Z","cross_cats_sorted":[],"title_canon_sha256":"4cec3af5f169d3e670bb007d1110a426175dffff91848dfcc78b68536cd162cb","abstract_canon_sha256":"044729682193aae3642ebca35f7dd7dbd39a5c31569ca7c3f81fad0a2f275192"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-03T01:17:25.855626Z","signature_b64":"rAlfNs8ZdlWroXkDhvz5SitzfG1+lKi2al/bE3CrN23R6EXeybQTmQsL+NlYf/HgoAO15wiuN/Ahja6u18iYDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b2f69f3d91c738f36fbd5cf0c64effb0d5ec03fb7dc31311b032f8557d9ee293","last_reissued_at":"2026-07-03T01:17:25.855105Z","signature_status":"signed_v1","first_computed_at":"2026-07-03T01:17:25.855105Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Teaching Vision-Language-Action Models What to See and Where to Look","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baochang Zhang, Bo Zhang, Canyu Chen, Chunyang Liu, Juan Zhang, Kehua Sheng, Linlin Yang, Xianbin Cao, Yan Wang, Yizhi Wang, Yuguang Yang, Zhewen Tan, Zichao Feng","submitted_at":"2026-07-02T03:34:32Z","abstract_excerpt":"Vision-Language-Action (VLA) models have emerged as a promising paradigm for end-to-end autonomous driving. However, existing VLAs' training relies heavily on text-centric visual question answering and chain-of-thought reasoning data, which emphasizes linguistic reasoning rather than action-grounded planning. As a result, the learned representations capture semantic knowledge but lack spatial dependencies crucial for reliable trajectory prediction. We propose DriveTeach-VLA, a framework that explicitly teaches VLAs what to see and where to look. Driving-aware Vision Distillation (DVD) injects "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.01658","kind":"arxiv","version":1},"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/2607.01658/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":"2607.01658","created_at":"2026-07-03T01:17:25.855172+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.01658v1","created_at":"2026-07-03T01:17:25.855172+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.01658","created_at":"2026-07-03T01:17:25.855172+00:00"},{"alias_kind":"pith_short_12","alias_value":"WL3J6PMRY44P","created_at":"2026-07-03T01:17:25.855172+00:00"},{"alias_kind":"pith_short_16","alias_value":"WL3J6PMRY44PG355","created_at":"2026-07-03T01:17:25.855172+00:00"},{"alias_kind":"pith_short_8","alias_value":"WL3J6PMR","created_at":"2026-07-03T01:17:25.855172+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WL3J6PMRY44PG355LTYMMTX7WD","json":"https://pith.science/pith/WL3J6PMRY44PG355LTYMMTX7WD.json","graph_json":"https://pith.science/api/pith-number/WL3J6PMRY44PG355LTYMMTX7WD/graph.json","events_json":"https://pith.science/api/pith-number/WL3J6PMRY44PG355LTYMMTX7WD/events.json","paper":"https://pith.science/paper/WL3J6PMR"},"agent_actions":{"view_html":"https://pith.science/pith/WL3J6PMRY44PG355LTYMMTX7WD","download_json":"https://pith.science/pith/WL3J6PMRY44PG355LTYMMTX7WD.json","view_paper":"https://pith.science/paper/WL3J6PMR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.01658&json=true","fetch_graph":"https://pith.science/api/pith-number/WL3J6PMRY44PG355LTYMMTX7WD/graph.json","fetch_events":"https://pith.science/api/pith-number/WL3J6PMRY44PG355LTYMMTX7WD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WL3J6PMRY44PG355LTYMMTX7WD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WL3J6PMRY44PG355LTYMMTX7WD/action/storage_attestation","attest_author":"https://pith.science/pith/WL3J6PMRY44PG355LTYMMTX7WD/action/author_attestation","sign_citation":"https://pith.science/pith/WL3J6PMRY44PG355LTYMMTX7WD/action/citation_signature","submit_replication":"https://pith.science/pith/WL3J6PMRY44PG355LTYMMTX7WD/action/replication_record"}},"created_at":"2026-07-03T01:17:25.855172+00:00","updated_at":"2026-07-03T01:17:25.855172+00:00"}