{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KBR4GOJO4GRHA4RFFRM5USCX2Z","short_pith_number":"pith:KBR4GOJO","schema_version":"1.0","canonical_sha256":"5063c3392ee1a27072252c59da4857d6688d03114d49134480688977e1e1190a","source":{"kind":"arxiv","id":"2408.15998","version":2},"attestation_state":"computed","paper":{"title":"Eagle: Exploring The Design Space for Multimodal LLMs with Mixture of Encoders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.RO"],"primary_cat":"cs.CV","authors_text":"Andrew Tao, Bryan Catanzaro, De-An Huang, Fuxiao Liu, Guilin Liu, Hongxu Yin, Humphrey Shi, Jan Kautz, Karan Sapra, Min Shi, Shihao Wang, Shijia Liao, Subhashree Radhakrishnan, Yaser Yacoob, Yilin Zhao, Zhiding Yu","submitted_at":"2024-08-28T17:59:31Z","abstract_excerpt":"The ability to accurately interpret complex visual information is a crucial topic of multimodal large language models (MLLMs). Recent work indicates that enhanced visual perception significantly reduces hallucinations and improves performance on resolution-sensitive tasks, such as optical character recognition and document analysis. A number of recent MLLMs achieve this goal using a mixture of vision encoders. Despite their success, there is a lack of systematic comparisons and detailed ablation studies addressing critical aspects, such as expert selection and the integration of multiple visio"},"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":"2408.15998","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-28T17:59:31Z","cross_cats_sorted":["cs.AI","cs.LG","cs.RO"],"title_canon_sha256":"52a30ce2210797f36d58f7c47a08434cb66550d30553dfe10c4630bc0d4e9577","abstract_canon_sha256":"5624f4c6734c679eb367e2723b6ef6f05e94770bf845c90bcda165eb313c6f1e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:22:03.766402Z","signature_b64":"JrM02ZZui8CQdUoH2Od3B0Eu0dN6DxPsiBZro/4UWbUISP9eZCGNKXQM4/iT9Q7TTXkc5GYi2AMs3k6AEABcDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5063c3392ee1a27072252c59da4857d6688d03114d49134480688977e1e1190a","last_reissued_at":"2026-07-05T10:22:03.765817Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:22:03.765817Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Eagle: Exploring The Design Space for Multimodal LLMs with Mixture of Encoders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.RO"],"primary_cat":"cs.CV","authors_text":"Andrew Tao, Bryan Catanzaro, De-An Huang, Fuxiao Liu, Guilin Liu, Hongxu Yin, Humphrey Shi, Jan Kautz, Karan Sapra, Min Shi, Shihao Wang, Shijia Liao, Subhashree Radhakrishnan, Yaser Yacoob, Yilin Zhao, Zhiding Yu","submitted_at":"2024-08-28T17:59:31Z","abstract_excerpt":"The ability to accurately interpret complex visual information is a crucial topic of multimodal large language models (MLLMs). Recent work indicates that enhanced visual perception significantly reduces hallucinations and improves performance on resolution-sensitive tasks, such as optical character recognition and document analysis. A number of recent MLLMs achieve this goal using a mixture of vision encoders. Despite their success, there is a lack of systematic comparisons and detailed ablation studies addressing critical aspects, such as expert selection and the integration of multiple visio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.15998","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/2408.15998/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":"2408.15998","created_at":"2026-07-05T10:22:03.765884+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.15998v2","created_at":"2026-07-05T10:22:03.765884+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.15998","created_at":"2026-07-05T10:22:03.765884+00:00"},{"alias_kind":"pith_short_12","alias_value":"KBR4GOJO4GRH","created_at":"2026-07-05T10:22:03.765884+00:00"},{"alias_kind":"pith_short_16","alias_value":"KBR4GOJO4GRHA4RF","created_at":"2026-07-05T10:22:03.765884+00:00"},{"alias_kind":"pith_short_8","alias_value":"KBR4GOJO","created_at":"2026-07-05T10:22:03.765884+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":18,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26196","citing_title":"From Structure to Synergy: A Survey of Vision-Language Perception Paradigm Evolution in Multimodal Large Language Models","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03444","citing_title":"PRISM: Synergizing Vision Foundation Models via Self-organized Expert Specialization","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03879","citing_title":"Beyond Encoder Accumulation: Measuring Encoder Roles in Multi-Encoder VLMs","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03713","citing_title":"Investigating Adversarial Robustness of Multi-modal Large Language Models","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24675","citing_title":"VaaWIT: Visual-Aware Adaptation of Large Language Models for Multilingual Web Image Translation","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27959","citing_title":"ROVER: Routing Object-Centric Visual Evidence for Grounded Multi-Image Reasoning","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2412.04468","citing_title":"NVILA: Efficient Frontier Visual Language Models","ref_index":74,"is_internal_anchor":false},{"citing_arxiv_id":"2504.09925","citing_title":"FLARE: Fully Integration of Vision-Language Representations for Deep Cross-Modal Understanding","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2504.21850","citing_title":"Visual Compositional Tuning","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2507.16815","citing_title":"ThinkAct: Vision-Language-Action Reasoning via Reinforced Visual Latent Planning","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2501.00321","citing_title":"OCRBench v2: An Improved Benchmark for Evaluating Large Multimodal Models on Visual Text Localization and Reasoning","ref_index":151,"is_internal_anchor":false},{"citing_arxiv_id":"2603.09465","citing_title":"EvoDriveVLA: Evolving Driving VLA Models via Collaborative Perception-Planning Distillation","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11405","citing_title":"20/20 Vision Language Models: A Prescription for Better VLMs through Data Curation Alone","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03231","citing_title":"CoME-VL: Scaling Complementary Multi-Encoder Vision-Language Learning","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11405","citing_title":"20/20 Vision Language Models: A Prescription for Better VLMs through Data Curation Alone","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12966","citing_title":"Boosting Visual Instruction Tuning with Self-Supervised Guidance","ref_index":61,"is_internal_anchor":false},{"citing_arxiv_id":"2504.10479","citing_title":"InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models","ref_index":106,"is_internal_anchor":false},{"citing_arxiv_id":"2412.05271","citing_title":"Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling","ref_index":211,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KBR4GOJO4GRHA4RFFRM5USCX2Z","json":"https://pith.science/pith/KBR4GOJO4GRHA4RFFRM5USCX2Z.json","graph_json":"https://pith.science/api/pith-number/KBR4GOJO4GRHA4RFFRM5USCX2Z/graph.json","events_json":"https://pith.science/api/pith-number/KBR4GOJO4GRHA4RFFRM5USCX2Z/events.json","paper":"https://pith.science/paper/KBR4GOJO"},"agent_actions":{"view_html":"https://pith.science/pith/KBR4GOJO4GRHA4RFFRM5USCX2Z","download_json":"https://pith.science/pith/KBR4GOJO4GRHA4RFFRM5USCX2Z.json","view_paper":"https://pith.science/paper/KBR4GOJO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.15998&json=true","fetch_graph":"https://pith.science/api/pith-number/KBR4GOJO4GRHA4RFFRM5USCX2Z/graph.json","fetch_events":"https://pith.science/api/pith-number/KBR4GOJO4GRHA4RFFRM5USCX2Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KBR4GOJO4GRHA4RFFRM5USCX2Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KBR4GOJO4GRHA4RFFRM5USCX2Z/action/storage_attestation","attest_author":"https://pith.science/pith/KBR4GOJO4GRHA4RFFRM5USCX2Z/action/author_attestation","sign_citation":"https://pith.science/pith/KBR4GOJO4GRHA4RFFRM5USCX2Z/action/citation_signature","submit_replication":"https://pith.science/pith/KBR4GOJO4GRHA4RFFRM5USCX2Z/action/replication_record"}},"created_at":"2026-07-05T10:22:03.765884+00:00","updated_at":"2026-07-05T10:22:03.765884+00:00"}