{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:X4WHOAFJ6YU7U2BL6BLOTOY3NH","short_pith_number":"pith:X4WHOAFJ","schema_version":"1.0","canonical_sha256":"bf2c7700a9f629fa682bf056e9bb1b69e509fbc70cf269d2fadec0bb5d2f3fbe","source":{"kind":"arxiv","id":"2305.11175","version":2},"attestation_state":"computed","paper":{"title":"VisionLLM: Large Language Model is also an Open-Ended Decoder for Vision-Centric Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gang Zeng, Jiannan Wu, Jie Zhou, Jifeng Dai, Ping Luo, Tong Lu, Wenhai Wang, Xiaokang Chen, Xizhou Zhu, Yu Qiao, Zhe Chen","submitted_at":"2023-05-18T17:59:42Z","abstract_excerpt":"Large language models (LLMs) have notably accelerated progress towards artificial general intelligence (AGI), with their impressive zero-shot capacity for user-tailored tasks, endowing them with immense potential across a range of applications. However, in the field of computer vision, despite the availability of numerous powerful vision foundation models (VFMs), they are still restricted to tasks in a pre-defined form, struggling to match the open-ended task capabilities of LLMs. In this work, we present an LLM-based framework for vision-centric tasks, termed VisionLLM. This framework provide"},"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":"2305.11175","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-18T17:59:42Z","cross_cats_sorted":[],"title_canon_sha256":"ed96df3bc0b22cbedea66714267b63ec226a9f722ef2ffc26a0eeca0ac89bba4","abstract_canon_sha256":"ea15ec3c934d59a95a35458c5fba9497f6ee6c6b3502a22ed3d10f850292a515"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:13:56.692625Z","signature_b64":"X4OWUZ3G409m42k1l550CFngDz6ut55wE7GV9C/fywj7E7brG9GCI0aoRi7pSW6ns3B4cvAU6ObgMilBU/DPDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bf2c7700a9f629fa682bf056e9bb1b69e509fbc70cf269d2fadec0bb5d2f3fbe","last_reissued_at":"2026-07-05T06:13:56.692130Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:13:56.692130Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VisionLLM: Large Language Model is also an Open-Ended Decoder for Vision-Centric Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gang Zeng, Jiannan Wu, Jie Zhou, Jifeng Dai, Ping Luo, Tong Lu, Wenhai Wang, Xiaokang Chen, Xizhou Zhu, Yu Qiao, Zhe Chen","submitted_at":"2023-05-18T17:59:42Z","abstract_excerpt":"Large language models (LLMs) have notably accelerated progress towards artificial general intelligence (AGI), with their impressive zero-shot capacity for user-tailored tasks, endowing them with immense potential across a range of applications. However, in the field of computer vision, despite the availability of numerous powerful vision foundation models (VFMs), they are still restricted to tasks in a pre-defined form, struggling to match the open-ended task capabilities of LLMs. In this work, we present an LLM-based framework for vision-centric tasks, termed VisionLLM. This framework provide"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.11175","kind":"arxiv","version":2},"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/2305.11175/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":"2305.11175","created_at":"2026-07-05T06:13:56.692195+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.11175v2","created_at":"2026-07-05T06:13:56.692195+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.11175","created_at":"2026-07-05T06:13:56.692195+00:00"},{"alias_kind":"pith_short_12","alias_value":"X4WHOAFJ6YU7","created_at":"2026-07-05T06:13:56.692195+00:00"},{"alias_kind":"pith_short_16","alias_value":"X4WHOAFJ6YU7U2BL","created_at":"2026-07-05T06:13:56.692195+00:00"},{"alias_kind":"pith_short_8","alias_value":"X4WHOAFJ","created_at":"2026-07-05T06:13:56.692195+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":14,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2307.06435","citing_title":"A Comprehensive Overview of Large Language Models","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2401.10935","citing_title":"SeeClick: Harnessing GUI Grounding for Advanced Visual GUI Agents","ref_index":99,"is_internal_anchor":false},{"citing_arxiv_id":"2311.07575","citing_title":"SPHINX: The Joint Mixing of Weights, Tasks, and Visual Embeddings for Multi-modal Large Language Models","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2310.09478","citing_title":"MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2403.09611","citing_title":"MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training","ref_index":115,"is_internal_anchor":false},{"citing_arxiv_id":"2306.13549","citing_title":"A Survey on Multimodal Large Language Models","ref_index":84,"is_internal_anchor":false},{"citing_arxiv_id":"2401.15947","citing_title":"MoE-LLaVA: Mixture of Experts for Large Vision-Language Models","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2310.01415","citing_title":"GPT-Driver: Learning to Drive with GPT","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03231","citing_title":"CoME-VL: Scaling Complementary Multi-Encoder Vision-Language Learning","ref_index":64,"is_internal_anchor":false},{"citing_arxiv_id":"2310.03744","citing_title":"Improved Baselines with Visual Instruction Tuning","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2306.14824","citing_title":"Kosmos-2: Grounding Multimodal Large Language Models to the World","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11789","citing_title":"LMMs Meet Object-Centric Vision: Understanding, Segmentation, Editing and Generation","ref_index":173,"is_internal_anchor":false},{"citing_arxiv_id":"2306.13394","citing_title":"MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14373","citing_title":"SatBLIP: Context Understanding and Feature Identification from Satellite Imagery with Vision-Language Learning","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/X4WHOAFJ6YU7U2BL6BLOTOY3NH","json":"https://pith.science/pith/X4WHOAFJ6YU7U2BL6BLOTOY3NH.json","graph_json":"https://pith.science/api/pith-number/X4WHOAFJ6YU7U2BL6BLOTOY3NH/graph.json","events_json":"https://pith.science/api/pith-number/X4WHOAFJ6YU7U2BL6BLOTOY3NH/events.json","paper":"https://pith.science/paper/X4WHOAFJ"},"agent_actions":{"view_html":"https://pith.science/pith/X4WHOAFJ6YU7U2BL6BLOTOY3NH","download_json":"https://pith.science/pith/X4WHOAFJ6YU7U2BL6BLOTOY3NH.json","view_paper":"https://pith.science/paper/X4WHOAFJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.11175&json=true","fetch_graph":"https://pith.science/api/pith-number/X4WHOAFJ6YU7U2BL6BLOTOY3NH/graph.json","fetch_events":"https://pith.science/api/pith-number/X4WHOAFJ6YU7U2BL6BLOTOY3NH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X4WHOAFJ6YU7U2BL6BLOTOY3NH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X4WHOAFJ6YU7U2BL6BLOTOY3NH/action/storage_attestation","attest_author":"https://pith.science/pith/X4WHOAFJ6YU7U2BL6BLOTOY3NH/action/author_attestation","sign_citation":"https://pith.science/pith/X4WHOAFJ6YU7U2BL6BLOTOY3NH/action/citation_signature","submit_replication":"https://pith.science/pith/X4WHOAFJ6YU7U2BL6BLOTOY3NH/action/replication_record"}},"created_at":"2026-07-05T06:13:56.692195+00:00","updated_at":"2026-07-05T06:13:56.692195+00:00"}