{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:SGFQDOLZJKYPXLCI7MWCLXDKTI","short_pith_number":"pith:SGFQDOLZ","schema_version":"1.0","canonical_sha256":"918b01b9794ab0fbac48fb2c25dc6a9a1e327d8c64cc8fe8ff9515677f33ed06","source":{"kind":"arxiv","id":"2501.14276","version":1},"attestation_state":"computed","paper":{"title":"Global Semantic-Guided Sub-image Feature Weight Allocation in High-Resolution Large Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bin Li, Chenghang Lai, Haotian Chen, Xiangyang Xue, Xiaolei Chen, Xu Li, Yi Zheng, Yuxuan Liang","submitted_at":"2025-01-24T06:42:06Z","abstract_excerpt":"As the demand for high-resolution image processing in Large Vision-Language Models (LVLMs) grows, sub-image partitioning has become a popular approach for mitigating visual information loss associated with fixed-resolution processing. However, existing partitioning methods uniformly process sub-images, resulting in suboptimal image understanding. In this work, we reveal that the sub-images with higher semantic relevance to the entire image encapsulate richer visual information for preserving the model's visual understanding ability. Therefore, we propose the Global Semantic-guided Weight Alloc"},"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":"2501.14276","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-24T06:42:06Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0b3f48a2183dd3d34ab1c95ad408fe56ea11259cb2b8b72202c16fbb8912811f","abstract_canon_sha256":"78fc6139636560525f794c149e31db107ed478df71fb59afe1fd3e09d70d6c69"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:04:48.107346Z","signature_b64":"uBRgra5yGM4nODWbbQFi+keVAncK4hLpYADO0ZVeuqXuKBAOxt72HKvUAbYPb3WHOG8s1WtKk+5hKuqWNNrRCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"918b01b9794ab0fbac48fb2c25dc6a9a1e327d8c64cc8fe8ff9515677f33ed06","last_reissued_at":"2026-07-05T10:04:48.106955Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:04:48.106955Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Global Semantic-Guided Sub-image Feature Weight Allocation in High-Resolution Large Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bin Li, Chenghang Lai, Haotian Chen, Xiangyang Xue, Xiaolei Chen, Xu Li, Yi Zheng, Yuxuan Liang","submitted_at":"2025-01-24T06:42:06Z","abstract_excerpt":"As the demand for high-resolution image processing in Large Vision-Language Models (LVLMs) grows, sub-image partitioning has become a popular approach for mitigating visual information loss associated with fixed-resolution processing. However, existing partitioning methods uniformly process sub-images, resulting in suboptimal image understanding. In this work, we reveal that the sub-images with higher semantic relevance to the entire image encapsulate richer visual information for preserving the model's visual understanding ability. Therefore, we propose the Global Semantic-guided Weight Alloc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.14276","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/2501.14276/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":"2501.14276","created_at":"2026-07-05T10:04:48.107007+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.14276v1","created_at":"2026-07-05T10:04:48.107007+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.14276","created_at":"2026-07-05T10:04:48.107007+00:00"},{"alias_kind":"pith_short_12","alias_value":"SGFQDOLZJKYP","created_at":"2026-07-05T10:04:48.107007+00:00"},{"alias_kind":"pith_short_16","alias_value":"SGFQDOLZJKYPXLCI","created_at":"2026-07-05T10:04:48.107007+00:00"},{"alias_kind":"pith_short_8","alias_value":"SGFQDOLZ","created_at":"2026-07-05T10:04:48.107007+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.22530","citing_title":"HRVVS: A High-resolution Video Vasculature Segmentation Network via Hierarchical Autoregressive Residual Priors","ref_index":14,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SGFQDOLZJKYPXLCI7MWCLXDKTI","json":"https://pith.science/pith/SGFQDOLZJKYPXLCI7MWCLXDKTI.json","graph_json":"https://pith.science/api/pith-number/SGFQDOLZJKYPXLCI7MWCLXDKTI/graph.json","events_json":"https://pith.science/api/pith-number/SGFQDOLZJKYPXLCI7MWCLXDKTI/events.json","paper":"https://pith.science/paper/SGFQDOLZ"},"agent_actions":{"view_html":"https://pith.science/pith/SGFQDOLZJKYPXLCI7MWCLXDKTI","download_json":"https://pith.science/pith/SGFQDOLZJKYPXLCI7MWCLXDKTI.json","view_paper":"https://pith.science/paper/SGFQDOLZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.14276&json=true","fetch_graph":"https://pith.science/api/pith-number/SGFQDOLZJKYPXLCI7MWCLXDKTI/graph.json","fetch_events":"https://pith.science/api/pith-number/SGFQDOLZJKYPXLCI7MWCLXDKTI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SGFQDOLZJKYPXLCI7MWCLXDKTI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SGFQDOLZJKYPXLCI7MWCLXDKTI/action/storage_attestation","attest_author":"https://pith.science/pith/SGFQDOLZJKYPXLCI7MWCLXDKTI/action/author_attestation","sign_citation":"https://pith.science/pith/SGFQDOLZJKYPXLCI7MWCLXDKTI/action/citation_signature","submit_replication":"https://pith.science/pith/SGFQDOLZJKYPXLCI7MWCLXDKTI/action/replication_record"}},"created_at":"2026-07-05T10:04:48.107007+00:00","updated_at":"2026-07-05T10:04:48.107007+00:00"}