{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QC7CIPJY3UYJKVZAZ2PBGBCP67","short_pith_number":"pith:QC7CIPJY","schema_version":"1.0","canonical_sha256":"80be243d38dd30955720ce9e13044ff7d85ddf082465710d5d51a2406fc933ba","source":{"kind":"arxiv","id":"2406.08394","version":3},"attestation_state":"computed","paper":{"title":"VisionLLM v2: An End-to-End Generalist Multimodal Large Language Model for Hundreds of Vision-Language Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiannan Wu, Jifeng Dai, Lewei Lu, Muyan Zhong, Ping Luo, Sen Xing, Tong Lu, Wenhai Wang, Xizhou Zhu, Yu Qiao, Zeqiang Lai, Zhaoyang Liu, Zhe Chen","submitted_at":"2024-06-12T16:44:50Z","abstract_excerpt":"We present VisionLLM v2, an end-to-end generalist multimodal large model (MLLM) that unifies visual perception, understanding, and generation within a single framework. Unlike traditional MLLMs limited to text output, VisionLLM v2 significantly broadens its application scope. It excels not only in conventional visual question answering (VQA) but also in open-ended, cross-domain vision tasks such as object localization, pose estimation, and image generation and editing. To this end, we propose a new information transmission mechanism termed \"super link\", as a medium to connect MLLM with task-sp"},"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":"2406.08394","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-12T16:44:50Z","cross_cats_sorted":[],"title_canon_sha256":"c583dba26866ed36769fdc8e35a528eb69c905640b482ab97f2730d55e2c22e6","abstract_canon_sha256":"3b145f9d3abebef1b72521419d65a776e1da8c0dd6aa769f06a2b1605f14210d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:55:33.600835Z","signature_b64":"jyqfyuiDtirVAAhiEoPfhX7/Vew6zGKKpkWBA7UYUNx3HAmArDA0OgDVjyg7IwRu1h/atmZxulBHOAxjxpYpAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"80be243d38dd30955720ce9e13044ff7d85ddf082465710d5d51a2406fc933ba","last_reissued_at":"2026-07-05T09:55:33.600240Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:55:33.600240Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VisionLLM v2: An End-to-End Generalist Multimodal Large Language Model for Hundreds of Vision-Language Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiannan Wu, Jifeng Dai, Lewei Lu, Muyan Zhong, Ping Luo, Sen Xing, Tong Lu, Wenhai Wang, Xizhou Zhu, Yu Qiao, Zeqiang Lai, Zhaoyang Liu, Zhe Chen","submitted_at":"2024-06-12T16:44:50Z","abstract_excerpt":"We present VisionLLM v2, an end-to-end generalist multimodal large model (MLLM) that unifies visual perception, understanding, and generation within a single framework. Unlike traditional MLLMs limited to text output, VisionLLM v2 significantly broadens its application scope. It excels not only in conventional visual question answering (VQA) but also in open-ended, cross-domain vision tasks such as object localization, pose estimation, and image generation and editing. To this end, we propose a new information transmission mechanism termed \"super link\", as a medium to connect MLLM with task-sp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.08394","kind":"arxiv","version":3},"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/2406.08394/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":"2406.08394","created_at":"2026-07-05T09:55:33.600301+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.08394v3","created_at":"2026-07-05T09:55:33.600301+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.08394","created_at":"2026-07-05T09:55:33.600301+00:00"},{"alias_kind":"pith_short_12","alias_value":"QC7CIPJY3UYJ","created_at":"2026-07-05T09:55:33.600301+00:00"},{"alias_kind":"pith_short_16","alias_value":"QC7CIPJY3UYJKVZA","created_at":"2026-07-05T09:55:33.600301+00:00"},{"alias_kind":"pith_short_8","alias_value":"QC7CIPJY","created_at":"2026-07-05T09:55:33.600301+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12195","citing_title":"InternVideo3: Agentify Foundation Models with Multimodal Contextual Reasoning","ref_index":108,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15997","citing_title":"Segmentation, Detection and Explanation: A Unified Framework for CT Appearance Reasoning","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2501.12386","citing_title":"InternVideo2.5: Empowering Video MLLMs with Long and Rich Context Modeling","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2410.23262","citing_title":"EMMA: End-to-End Multimodal Model for Autonomous Driving","ref_index":196,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10527","citing_title":"STORM: End-to-End Referring Multi-Object Tracking in Videos","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QC7CIPJY3UYJKVZAZ2PBGBCP67","json":"https://pith.science/pith/QC7CIPJY3UYJKVZAZ2PBGBCP67.json","graph_json":"https://pith.science/api/pith-number/QC7CIPJY3UYJKVZAZ2PBGBCP67/graph.json","events_json":"https://pith.science/api/pith-number/QC7CIPJY3UYJKVZAZ2PBGBCP67/events.json","paper":"https://pith.science/paper/QC7CIPJY"},"agent_actions":{"view_html":"https://pith.science/pith/QC7CIPJY3UYJKVZAZ2PBGBCP67","download_json":"https://pith.science/pith/QC7CIPJY3UYJKVZAZ2PBGBCP67.json","view_paper":"https://pith.science/paper/QC7CIPJY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.08394&json=true","fetch_graph":"https://pith.science/api/pith-number/QC7CIPJY3UYJKVZAZ2PBGBCP67/graph.json","fetch_events":"https://pith.science/api/pith-number/QC7CIPJY3UYJKVZAZ2PBGBCP67/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QC7CIPJY3UYJKVZAZ2PBGBCP67/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QC7CIPJY3UYJKVZAZ2PBGBCP67/action/storage_attestation","attest_author":"https://pith.science/pith/QC7CIPJY3UYJKVZAZ2PBGBCP67/action/author_attestation","sign_citation":"https://pith.science/pith/QC7CIPJY3UYJKVZAZ2PBGBCP67/action/citation_signature","submit_replication":"https://pith.science/pith/QC7CIPJY3UYJKVZAZ2PBGBCP67/action/replication_record"}},"created_at":"2026-07-05T09:55:33.600301+00:00","updated_at":"2026-07-05T09:55:33.600301+00:00"}