{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UMGUCQAAUWUQZTKX4CDXUVPTWW","short_pith_number":"pith:UMGUCQAA","schema_version":"1.0","canonical_sha256":"a30d414000a5a90ccd57e0877a55f3b5a649ebf59897163541245348f8758941","source":{"kind":"arxiv","id":"2403.13447","version":1},"attestation_state":"computed","paper":{"title":"HyperLLaVA: Dynamic Visual and Language Expert Tuning for Multimodal Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.AI","authors_text":"Fangxun Shu, Hao Jiang, Haoyuan Li, Hao Zhou, He Wanggui, Jiang Liu, Juncheng Li, Lei Zhang, Siliang Tang, Tianwei Lin, Wenqiao Zhang, Yueting Zhuang, Zheqi Lv","submitted_at":"2024-03-20T09:42:43Z","abstract_excerpt":"Recent advancements indicate that scaling up Multimodal Large Language Models (MLLMs) effectively enhances performance on downstream multimodal tasks. The prevailing MLLM paradigm, \\emph{e.g.}, LLaVA, transforms visual features into text-like tokens using a \\emph{static} vision-language mapper, thereby enabling \\emph{static} LLMs to develop the capability to comprehend visual information through visual instruction tuning. Although promising, the \\emph{static} tuning strategy~\\footnote{The static tuning refers to the trained model with static parameters.} that shares the same parameters may con"},"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":"2403.13447","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-03-20T09:42:43Z","cross_cats_sorted":["cs.CL","cs.CV"],"title_canon_sha256":"a726618b82ba81f1506d002ded788a7ead02b365a47e6d077d9b4106244cf629","abstract_canon_sha256":"370cf5e73d9e5f5b13012a222c1af78758b9b29bac98d764980a7b3a38a2c13c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:58:36.759349Z","signature_b64":"ypyAG6BNpgTvS42E+wnUd0ahXuUHn0uQhk8nzEYo7JSXZtRBMJZ7S/FtiamLxCYr7jjeqewqoANmu9M/wXIxAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a30d414000a5a90ccd57e0877a55f3b5a649ebf59897163541245348f8758941","last_reissued_at":"2026-07-05T07:58:36.758806Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:58:36.758806Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HyperLLaVA: Dynamic Visual and Language Expert Tuning for Multimodal Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.AI","authors_text":"Fangxun Shu, Hao Jiang, Haoyuan Li, Hao Zhou, He Wanggui, Jiang Liu, Juncheng Li, Lei Zhang, Siliang Tang, Tianwei Lin, Wenqiao Zhang, Yueting Zhuang, Zheqi Lv","submitted_at":"2024-03-20T09:42:43Z","abstract_excerpt":"Recent advancements indicate that scaling up Multimodal Large Language Models (MLLMs) effectively enhances performance on downstream multimodal tasks. The prevailing MLLM paradigm, \\emph{e.g.}, LLaVA, transforms visual features into text-like tokens using a \\emph{static} vision-language mapper, thereby enabling \\emph{static} LLMs to develop the capability to comprehend visual information through visual instruction tuning. Although promising, the \\emph{static} tuning strategy~\\footnote{The static tuning refers to the trained model with static parameters.} that shares the same parameters may con"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.13447","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/2403.13447/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":"2403.13447","created_at":"2026-07-05T07:58:36.758858+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.13447v1","created_at":"2026-07-05T07:58:36.758858+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.13447","created_at":"2026-07-05T07:58:36.758858+00:00"},{"alias_kind":"pith_short_12","alias_value":"UMGUCQAAUWUQ","created_at":"2026-07-05T07:58:36.758858+00:00"},{"alias_kind":"pith_short_16","alias_value":"UMGUCQAAUWUQZTKX","created_at":"2026-07-05T07:58:36.758858+00:00"},{"alias_kind":"pith_short_8","alias_value":"UMGUCQAA","created_at":"2026-07-05T07:58:36.758858+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.26102","citing_title":"InstructSAM: Segment Any Instance with Any Instructions","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30011","citing_title":"VisualThink-VLA: Visual Intermediate Reasoning for Effective and Low-Latency Vision-Language-Action Policies","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20277","citing_title":"Regulating Anatomy-Aware Rewards via Trajectory-Integral Feedback for Volumetric Computed Tomography Analysis","ref_index":70,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18621","citing_title":"CrossView Suite: Harnessing Cross-view Spatial Intelligence of MLLMs with Dataset, Model and Benchmark","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19559","citing_title":"EgoCoT-Bench: Benchmarking Grounded and Verifiable Operation-Centric Chain of Thought Reasoning for MLLMs","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2506.05831","citing_title":"HeartcareGPT: A Unified Multimodal ECG Suite for Dual Signal-Image Modeling and Understanding","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11789","citing_title":"LMMs Meet Object-Centric Vision: Understanding, Segmentation, Editing and Generation","ref_index":229,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UMGUCQAAUWUQZTKX4CDXUVPTWW","json":"https://pith.science/pith/UMGUCQAAUWUQZTKX4CDXUVPTWW.json","graph_json":"https://pith.science/api/pith-number/UMGUCQAAUWUQZTKX4CDXUVPTWW/graph.json","events_json":"https://pith.science/api/pith-number/UMGUCQAAUWUQZTKX4CDXUVPTWW/events.json","paper":"https://pith.science/paper/UMGUCQAA"},"agent_actions":{"view_html":"https://pith.science/pith/UMGUCQAAUWUQZTKX4CDXUVPTWW","download_json":"https://pith.science/pith/UMGUCQAAUWUQZTKX4CDXUVPTWW.json","view_paper":"https://pith.science/paper/UMGUCQAA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.13447&json=true","fetch_graph":"https://pith.science/api/pith-number/UMGUCQAAUWUQZTKX4CDXUVPTWW/graph.json","fetch_events":"https://pith.science/api/pith-number/UMGUCQAAUWUQZTKX4CDXUVPTWW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UMGUCQAAUWUQZTKX4CDXUVPTWW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UMGUCQAAUWUQZTKX4CDXUVPTWW/action/storage_attestation","attest_author":"https://pith.science/pith/UMGUCQAAUWUQZTKX4CDXUVPTWW/action/author_attestation","sign_citation":"https://pith.science/pith/UMGUCQAAUWUQZTKX4CDXUVPTWW/action/citation_signature","submit_replication":"https://pith.science/pith/UMGUCQAAUWUQZTKX4CDXUVPTWW/action/replication_record"}},"created_at":"2026-07-05T07:58:36.758858+00:00","updated_at":"2026-07-05T07:58:36.758858+00:00"}