{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PJLZFXCKDRZNNRYAF4LTJS5QEY","short_pith_number":"pith:PJLZFXCK","schema_version":"1.0","canonical_sha256":"7a5792dc4a1c72d6c7002f1734cbb0262025bce42dea8c48f3c8967c4355b6a4","source":{"kind":"arxiv","id":"2506.01850","version":2},"attestation_state":"computed","paper":{"title":"MoDA: Modulation Adapter for Fine-Grained Visual Grounding in Instructional MLLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"Andr\\'es Villa, Bernard Ghanem, Juan Le\\'on Alc\\'azar, SouYoung Jin, Wayner Barrios","submitted_at":"2025-06-02T16:38:50Z","abstract_excerpt":"Multimodal Large Language Models (MLLMs) have achieved remarkable success in instruction-following tasks by integrating pretrained visual encoders with large language models (LLMs). However, existing approaches often struggle with fine-grained visual grounding due to semantic entanglement in visual patch representations, where individual patches blend multiple distinct visual elements, making it difficult for models to focus on instruction-relevant details. To address this challenge, we propose MoDA (Modulation Adapter), a lightweight module that enhances visual grounding through instruction-g"},"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":"2506.01850","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-02T16:38:50Z","cross_cats_sorted":["cs.AI","cs.LG","cs.MM"],"title_canon_sha256":"ef0ee7ec53ac246407aec243613e2dd0f73f64dadce4578eb57ab3535a4ce565","abstract_canon_sha256":"600ec099a8c2becdf0e09be6f4c84c2ef450f79342355453c863ace9ce50a765"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-08T01:03:45.355894Z","signature_b64":"uzFRBChIjbE2CFEU7FJ7pJmFyV60nznyYq9uvZQED3zwWRNGiSzqtPEd4UW3K/So75pfZgyliWzsLG5+HaIpAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7a5792dc4a1c72d6c7002f1734cbb0262025bce42dea8c48f3c8967c4355b6a4","last_reissued_at":"2026-06-08T01:03:45.355041Z","signature_status":"signed_v1","first_computed_at":"2026-06-08T01:03:45.355041Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MoDA: Modulation Adapter for Fine-Grained Visual Grounding in Instructional MLLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"Andr\\'es Villa, Bernard Ghanem, Juan Le\\'on Alc\\'azar, SouYoung Jin, Wayner Barrios","submitted_at":"2025-06-02T16:38:50Z","abstract_excerpt":"Multimodal Large Language Models (MLLMs) have achieved remarkable success in instruction-following tasks by integrating pretrained visual encoders with large language models (LLMs). However, existing approaches often struggle with fine-grained visual grounding due to semantic entanglement in visual patch representations, where individual patches blend multiple distinct visual elements, making it difficult for models to focus on instruction-relevant details. To address this challenge, we propose MoDA (Modulation Adapter), a lightweight module that enhances visual grounding through instruction-g"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01850","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/2506.01850/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":"2506.01850","created_at":"2026-06-08T01:03:45.355155+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.01850v2","created_at":"2026-06-08T01:03:45.355155+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01850","created_at":"2026-06-08T01:03:45.355155+00:00"},{"alias_kind":"pith_short_12","alias_value":"PJLZFXCKDRZN","created_at":"2026-06-08T01:03:45.355155+00:00"},{"alias_kind":"pith_short_16","alias_value":"PJLZFXCKDRZNNRYA","created_at":"2026-06-08T01:03:45.355155+00:00"},{"alias_kind":"pith_short_8","alias_value":"PJLZFXCK","created_at":"2026-06-08T01:03:45.355155+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/PJLZFXCKDRZNNRYAF4LTJS5QEY","json":"https://pith.science/pith/PJLZFXCKDRZNNRYAF4LTJS5QEY.json","graph_json":"https://pith.science/api/pith-number/PJLZFXCKDRZNNRYAF4LTJS5QEY/graph.json","events_json":"https://pith.science/api/pith-number/PJLZFXCKDRZNNRYAF4LTJS5QEY/events.json","paper":"https://pith.science/paper/PJLZFXCK"},"agent_actions":{"view_html":"https://pith.science/pith/PJLZFXCKDRZNNRYAF4LTJS5QEY","download_json":"https://pith.science/pith/PJLZFXCKDRZNNRYAF4LTJS5QEY.json","view_paper":"https://pith.science/paper/PJLZFXCK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.01850&json=true","fetch_graph":"https://pith.science/api/pith-number/PJLZFXCKDRZNNRYAF4LTJS5QEY/graph.json","fetch_events":"https://pith.science/api/pith-number/PJLZFXCKDRZNNRYAF4LTJS5QEY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PJLZFXCKDRZNNRYAF4LTJS5QEY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PJLZFXCKDRZNNRYAF4LTJS5QEY/action/storage_attestation","attest_author":"https://pith.science/pith/PJLZFXCKDRZNNRYAF4LTJS5QEY/action/author_attestation","sign_citation":"https://pith.science/pith/PJLZFXCKDRZNNRYAF4LTJS5QEY/action/citation_signature","submit_replication":"https://pith.science/pith/PJLZFXCKDRZNNRYAF4LTJS5QEY/action/replication_record"}},"created_at":"2026-06-08T01:03:45.355155+00:00","updated_at":"2026-06-08T01:03:45.355155+00:00"}