{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3CN76X7SL7BWBRR7TNHCCCHUEH","short_pith_number":"pith:3CN76X7S","schema_version":"1.0","canonical_sha256":"d89bff5ff25fc360c63f9b4e2108f421d96c0dfb45b6eb8c1046395ef5a53ba3","source":{"kind":"arxiv","id":"2506.17608","version":1},"attestation_state":"computed","paper":{"title":"HIRE: Lightweight High-Resolution Image Feature Enrichment for Multimodal LLMs","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aradhya Neeraj Mathur, Mausoom Sarkar, Nikitha SR, Rishabh Jain, Tarun Ram Menta","submitted_at":"2025-06-21T06:13:56Z","abstract_excerpt":"The integration of high-resolution image features in modern multimodal large language models has demonstrated significant improvements in fine-grained visual understanding tasks, achieving high performance across multiple benchmarks. Since these features are obtained from large image encoders like ViT, they come with a significant increase in computational costs due to multiple calls to these encoders. In this work, we first develop an intuition for feature upsampling as a natural extension of high-resolution feature generation. Through extensive experiments and ablations, we demonstrate how a"},"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":"2506.17608","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-21T06:13:56Z","cross_cats_sorted":[],"title_canon_sha256":"709190b2114af50e4ed0ba75aa61ebaf0fa7a26fcc2eb5b1164e72dc0dbcd678","abstract_canon_sha256":"e09d89047feb40b5c98e893cf4613b6920882123662d986373d6d0623b2fd6a4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:25:20.367173Z","signature_b64":"oEXQROtSlCoqn3oss9eyBxQjS9DVezgQq8A5uDfczMqBoV2g51NKmWn+LnhBoGu+9za/AB9vmn8ZVqNWklemBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d89bff5ff25fc360c63f9b4e2108f421d96c0dfb45b6eb8c1046395ef5a53ba3","last_reissued_at":"2026-07-05T11:25:20.366702Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:25:20.366702Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HIRE: Lightweight High-Resolution Image Feature Enrichment for Multimodal LLMs","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aradhya Neeraj Mathur, Mausoom Sarkar, Nikitha SR, Rishabh Jain, Tarun Ram Menta","submitted_at":"2025-06-21T06:13:56Z","abstract_excerpt":"The integration of high-resolution image features in modern multimodal large language models has demonstrated significant improvements in fine-grained visual understanding tasks, achieving high performance across multiple benchmarks. Since these features are obtained from large image encoders like ViT, they come with a significant increase in computational costs due to multiple calls to these encoders. In this work, we first develop an intuition for feature upsampling as a natural extension of high-resolution feature generation. Through extensive experiments and ablations, we demonstrate how a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.17608","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/2506.17608/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":"2506.17608","created_at":"2026-07-05T11:25:20.366766+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.17608v1","created_at":"2026-07-05T11:25:20.366766+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.17608","created_at":"2026-07-05T11:25:20.366766+00:00"},{"alias_kind":"pith_short_12","alias_value":"3CN76X7SL7BW","created_at":"2026-07-05T11:25:20.366766+00:00"},{"alias_kind":"pith_short_16","alias_value":"3CN76X7SL7BWBRR7","created_at":"2026-07-05T11:25:20.366766+00:00"},{"alias_kind":"pith_short_8","alias_value":"3CN76X7S","created_at":"2026-07-05T11:25:20.366766+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3CN76X7SL7BWBRR7TNHCCCHUEH","json":"https://pith.science/pith/3CN76X7SL7BWBRR7TNHCCCHUEH.json","graph_json":"https://pith.science/api/pith-number/3CN76X7SL7BWBRR7TNHCCCHUEH/graph.json","events_json":"https://pith.science/api/pith-number/3CN76X7SL7BWBRR7TNHCCCHUEH/events.json","paper":"https://pith.science/paper/3CN76X7S"},"agent_actions":{"view_html":"https://pith.science/pith/3CN76X7SL7BWBRR7TNHCCCHUEH","download_json":"https://pith.science/pith/3CN76X7SL7BWBRR7TNHCCCHUEH.json","view_paper":"https://pith.science/paper/3CN76X7S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.17608&json=true","fetch_graph":"https://pith.science/api/pith-number/3CN76X7SL7BWBRR7TNHCCCHUEH/graph.json","fetch_events":"https://pith.science/api/pith-number/3CN76X7SL7BWBRR7TNHCCCHUEH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3CN76X7SL7BWBRR7TNHCCCHUEH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3CN76X7SL7BWBRR7TNHCCCHUEH/action/storage_attestation","attest_author":"https://pith.science/pith/3CN76X7SL7BWBRR7TNHCCCHUEH/action/author_attestation","sign_citation":"https://pith.science/pith/3CN76X7SL7BWBRR7TNHCCCHUEH/action/citation_signature","submit_replication":"https://pith.science/pith/3CN76X7SL7BWBRR7TNHCCCHUEH/action/replication_record"}},"created_at":"2026-07-05T11:25:20.366766+00:00","updated_at":"2026-07-05T11:25:20.366766+00:00"}