{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6W27TJOITEOZ2I5MICULDRM24X","short_pith_number":"pith:6W27TJOI","schema_version":"1.0","canonical_sha256":"f5b5f9a5c8991d9d23ac40a8b1c59ae5e79c18eb2d2969dbc5e0fc106e796ed0","source":{"kind":"arxiv","id":"2501.02430","version":2},"attestation_state":"computed","paper":{"title":"FOLDER: Accelerating Multi-modal Large Language Models with Enhanced Performance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Ju, Enzo Tartaglione, Gabriele Spadaro, Haicheng Wang, Shuai Xiao, Victor Qu\\'etu, Zhemeng Yu","submitted_at":"2025-01-05T03:28:45Z","abstract_excerpt":"Recently, Multi-modal Large Language Models (MLLMs) have shown remarkable effectiveness for multi-modal tasks due to their abilities to generate and understand cross-modal data. However, processing long sequences of visual tokens extracted from visual backbones poses a challenge for deployment in real-time applications. To address this issue, we introduce FOLDER, a simple yet effective plug-and-play module designed to reduce the length of the visual token sequence, mitigating both computational and memory demands during training and inference. Through a comprehensive analysis of the token redu"},"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":"2501.02430","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-05T03:28:45Z","cross_cats_sorted":[],"title_canon_sha256":"2f21f78f92a10cf809c564757287984b3e8f954f131e63ea9c8ddff94116786e","abstract_canon_sha256":"0eb6737d03b7eeaca473ed44b0fbac9f496b4c105c5ff314d30c08e1ba90be65"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:46:59.703525Z","signature_b64":"LBE0qNXslZGBuJmsQHEpAyPUiJS8kI9sQG+vNOtFHZjpsgQ51NblbvupGiF2p9XdaNbzN2u7bjb5Foz8/zlADA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f5b5f9a5c8991d9d23ac40a8b1c59ae5e79c18eb2d2969dbc5e0fc106e796ed0","last_reissued_at":"2026-07-05T10:46:59.703045Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:46:59.703045Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FOLDER: Accelerating Multi-modal Large Language Models with Enhanced Performance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Ju, Enzo Tartaglione, Gabriele Spadaro, Haicheng Wang, Shuai Xiao, Victor Qu\\'etu, Zhemeng Yu","submitted_at":"2025-01-05T03:28:45Z","abstract_excerpt":"Recently, Multi-modal Large Language Models (MLLMs) have shown remarkable effectiveness for multi-modal tasks due to their abilities to generate and understand cross-modal data. However, processing long sequences of visual tokens extracted from visual backbones poses a challenge for deployment in real-time applications. To address this issue, we introduce FOLDER, a simple yet effective plug-and-play module designed to reduce the length of the visual token sequence, mitigating both computational and memory demands during training and inference. Through a comprehensive analysis of the token redu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.02430","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/2501.02430/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":"2501.02430","created_at":"2026-07-05T10:46:59.703102+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.02430v2","created_at":"2026-07-05T10:46:59.703102+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.02430","created_at":"2026-07-05T10:46:59.703102+00:00"},{"alias_kind":"pith_short_12","alias_value":"6W27TJOITEOZ","created_at":"2026-07-05T10:46:59.703102+00:00"},{"alias_kind":"pith_short_16","alias_value":"6W27TJOITEOZ2I5M","created_at":"2026-07-05T10:46:59.703102+00:00"},{"alias_kind":"pith_short_8","alias_value":"6W27TJOI","created_at":"2026-07-05T10:46:59.703102+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.15621","citing_title":"LRCP: Low-Rank Compressibility Guided Visual Token Pruning for Efficient LVLMs","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11627","citing_title":"POINTS-Long: Adaptive Dual-Mode Visual Reasoning in MLLMs","ref_index":84,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6W27TJOITEOZ2I5MICULDRM24X","json":"https://pith.science/pith/6W27TJOITEOZ2I5MICULDRM24X.json","graph_json":"https://pith.science/api/pith-number/6W27TJOITEOZ2I5MICULDRM24X/graph.json","events_json":"https://pith.science/api/pith-number/6W27TJOITEOZ2I5MICULDRM24X/events.json","paper":"https://pith.science/paper/6W27TJOI"},"agent_actions":{"view_html":"https://pith.science/pith/6W27TJOITEOZ2I5MICULDRM24X","download_json":"https://pith.science/pith/6W27TJOITEOZ2I5MICULDRM24X.json","view_paper":"https://pith.science/paper/6W27TJOI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.02430&json=true","fetch_graph":"https://pith.science/api/pith-number/6W27TJOITEOZ2I5MICULDRM24X/graph.json","fetch_events":"https://pith.science/api/pith-number/6W27TJOITEOZ2I5MICULDRM24X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6W27TJOITEOZ2I5MICULDRM24X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6W27TJOITEOZ2I5MICULDRM24X/action/storage_attestation","attest_author":"https://pith.science/pith/6W27TJOITEOZ2I5MICULDRM24X/action/author_attestation","sign_citation":"https://pith.science/pith/6W27TJOITEOZ2I5MICULDRM24X/action/citation_signature","submit_replication":"https://pith.science/pith/6W27TJOITEOZ2I5MICULDRM24X/action/replication_record"}},"created_at":"2026-07-05T10:46:59.703102+00:00","updated_at":"2026-07-05T10:46:59.703102+00:00"}