{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:P5UCNRH4LFOLBZAID57O6O2P5K","short_pith_number":"pith:P5UCNRH4","schema_version":"1.0","canonical_sha256":"7f6826c4fc595cb0e4081f7eef3b4fea84c3ec7021f1840b90bdfa1c3f4b4bd7","source":{"kind":"arxiv","id":"2501.12327","version":1},"attestation_state":"computed","paper":{"title":"VARGPT: Unified Understanding and Generation in a Visual Autoregressive Multimodal Large Language Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jinghan Ru, Liming Liang, Xianwei Zhuang, Yuexian Zou, Yufan Deng, Yuguo Yin, Yuxin Xie","submitted_at":"2025-01-21T17:50:43Z","abstract_excerpt":"We present VARGPT, a novel multimodal large language model (MLLM) that unifies visual understanding and generation within a single autoregressive framework. VARGPT employs a next-token prediction paradigm for visual understanding and a next-scale prediction paradigm for visual autoregressive generation. VARGPT innovatively extends the LLaVA architecture, achieving efficient scale-wise autoregressive visual generation within MLLMs while seamlessly accommodating mixed-modal input and output within a single model framework. Our VARGPT undergoes a three-stage unified training process on specially "},"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":"2501.12327","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-21T17:50:43Z","cross_cats_sorted":[],"title_canon_sha256":"a25fa53aa2ddc09614bbd90992a929ab0fbd32d335e4ad3d3f5eb445a933576a","abstract_canon_sha256":"797e152804b00290a0f3b82f768e1965b6583290fc2eb2dd92b47b874867644d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:03:34.652034Z","signature_b64":"0gFMWFkOxN44YthjEOC2zO8urdhIS6HqiMHbpW1rphUWN7/TIH8IPfyMkuFE9+KIiiK5jotdZSg/VqKg8nKWBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7f6826c4fc595cb0e4081f7eef3b4fea84c3ec7021f1840b90bdfa1c3f4b4bd7","last_reissued_at":"2026-07-05T10:03:34.651624Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:03:34.651624Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VARGPT: Unified Understanding and Generation in a Visual Autoregressive Multimodal Large Language Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jinghan Ru, Liming Liang, Xianwei Zhuang, Yuexian Zou, Yufan Deng, Yuguo Yin, Yuxin Xie","submitted_at":"2025-01-21T17:50:43Z","abstract_excerpt":"We present VARGPT, a novel multimodal large language model (MLLM) that unifies visual understanding and generation within a single autoregressive framework. VARGPT employs a next-token prediction paradigm for visual understanding and a next-scale prediction paradigm for visual autoregressive generation. VARGPT innovatively extends the LLaVA architecture, achieving efficient scale-wise autoregressive visual generation within MLLMs while seamlessly accommodating mixed-modal input and output within a single model framework. Our VARGPT undergoes a three-stage unified training process on specially "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.12327","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/2501.12327/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":"2501.12327","created_at":"2026-07-05T10:03:34.651693+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.12327v1","created_at":"2026-07-05T10:03:34.651693+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.12327","created_at":"2026-07-05T10:03:34.651693+00:00"},{"alias_kind":"pith_short_12","alias_value":"P5UCNRH4LFOL","created_at":"2026-07-05T10:03:34.651693+00:00"},{"alias_kind":"pith_short_16","alias_value":"P5UCNRH4LFOLBZAI","created_at":"2026-07-05T10:03:34.651693+00:00"},{"alias_kind":"pith_short_8","alias_value":"P5UCNRH4","created_at":"2026-07-05T10:03:34.651693+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.05196","citing_title":"Unified Audio Intelligence Without Regressing on Text Intelligence","ref_index":268,"is_internal_anchor":true},{"citing_arxiv_id":"2606.27376","citing_title":"Ask, Solve, Generate: Self-Evolving Unified Multimodal Understanding and Generation via Self-Consistency Rewards","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08302","citing_title":"HACK++: Towards More Effective Head-Aware Key-Value Compression for Efficient Visual Autoregressive Modeling","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00371","citing_title":"MEPA: Multi-Scale Representation Alignment for Visual Autoregressive Modeling with Mixture of Experts","ref_index":65,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18714","citing_title":"Semantic Generative Tuning for Unified Multimodal Models","ref_index":88,"is_internal_anchor":false},{"citing_arxiv_id":"2405.14093","citing_title":"A Survey on Vision-Language-Action Models for Embodied AI","ref_index":141,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18115","citing_title":"WinTok: A Win-Win Hybrid Tokenizer via Decomposing Visual Understanding and Generation with Transferable Tokens","ref_index":112,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18714","citing_title":"Semantic Generative Tuning for Unified Multimodal Models","ref_index":88,"is_internal_anchor":false},{"citing_arxiv_id":"2603.04592","citing_title":"From Static Inference to Dynamic Interaction: A Survey of Streaming Large Language Models","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2505.15809","citing_title":"MMaDA: Multimodal Large Diffusion Language Models","ref_index":59,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P5UCNRH4LFOLBZAID57O6O2P5K","json":"https://pith.science/pith/P5UCNRH4LFOLBZAID57O6O2P5K.json","graph_json":"https://pith.science/api/pith-number/P5UCNRH4LFOLBZAID57O6O2P5K/graph.json","events_json":"https://pith.science/api/pith-number/P5UCNRH4LFOLBZAID57O6O2P5K/events.json","paper":"https://pith.science/paper/P5UCNRH4"},"agent_actions":{"view_html":"https://pith.science/pith/P5UCNRH4LFOLBZAID57O6O2P5K","download_json":"https://pith.science/pith/P5UCNRH4LFOLBZAID57O6O2P5K.json","view_paper":"https://pith.science/paper/P5UCNRH4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.12327&json=true","fetch_graph":"https://pith.science/api/pith-number/P5UCNRH4LFOLBZAID57O6O2P5K/graph.json","fetch_events":"https://pith.science/api/pith-number/P5UCNRH4LFOLBZAID57O6O2P5K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P5UCNRH4LFOLBZAID57O6O2P5K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P5UCNRH4LFOLBZAID57O6O2P5K/action/storage_attestation","attest_author":"https://pith.science/pith/P5UCNRH4LFOLBZAID57O6O2P5K/action/author_attestation","sign_citation":"https://pith.science/pith/P5UCNRH4LFOLBZAID57O6O2P5K/action/citation_signature","submit_replication":"https://pith.science/pith/P5UCNRH4LFOLBZAID57O6O2P5K/action/replication_record"}},"created_at":"2026-07-05T10:03:34.651693+00:00","updated_at":"2026-07-05T10:03:34.651693+00:00"}