{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:G3FZ7YF6OOSIL6ZYIXLMOGHD6O","short_pith_number":"pith:G3FZ7YF6","schema_version":"1.0","canonical_sha256":"36cb9fe0be73a485fb3845d6c718e3f3b1a99860ae0a5673636404eaba007f9d","source":{"kind":"arxiv","id":"2410.08202","version":3},"attestation_state":"computed","paper":{"title":"Mono-InternVL: Pushing the Boundaries of Monolithic Multimodal Large Language Models with Endogenous Visual Pre-training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Gen Luo, Jiawen Liu, Jifeng Dai, Wenhan Dou, Xizhou Zhu, Xue Yang, Yu Qiao, Zhaokai Wang","submitted_at":"2024-10-10T17:59:22Z","abstract_excerpt":"In this paper, we focus on monolithic Multimodal Large Language Models (MLLMs) that integrate visual encoding and language decoding into a single LLM. In particular, we identify that existing pre-training strategies for monolithic MLLMs often suffer from unstable optimization or catastrophic forgetting. To address this issue, our core idea is to embed a new visual parameter space into a pre-trained LLM, thereby stably learning visual knowledge from noisy data while freezing the LLM. Based on this principle, we present Mono-InternVL, a novel monolithic MLLM that seamlessly integrates a set of v"},"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":"2410.08202","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-10T17:59:22Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"b074599496c59ba779bf2bf060c97b98b95e671f4815a8ea1b54f2e367bcc3f3","abstract_canon_sha256":"b7764f13297334c44f152765f2bf59bdfa576c1f9aef86a94ea12f33c5d3cd71"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:30:24.388472Z","signature_b64":"VuFXV0Gra0LhsVz17WQtFK/qUXlp3jcENJraQ2tmuxxRXeQjc6LFQ51I6Br6+rmT9wdgeRMm/qJSQ6RU0i5KCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"36cb9fe0be73a485fb3845d6c718e3f3b1a99860ae0a5673636404eaba007f9d","last_reissued_at":"2026-07-05T10:30:24.387582Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:30:24.387582Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mono-InternVL: Pushing the Boundaries of Monolithic Multimodal Large Language Models with Endogenous Visual Pre-training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Gen Luo, Jiawen Liu, Jifeng Dai, Wenhan Dou, Xizhou Zhu, Xue Yang, Yu Qiao, Zhaokai Wang","submitted_at":"2024-10-10T17:59:22Z","abstract_excerpt":"In this paper, we focus on monolithic Multimodal Large Language Models (MLLMs) that integrate visual encoding and language decoding into a single LLM. In particular, we identify that existing pre-training strategies for monolithic MLLMs often suffer from unstable optimization or catastrophic forgetting. To address this issue, our core idea is to embed a new visual parameter space into a pre-trained LLM, thereby stably learning visual knowledge from noisy data while freezing the LLM. Based on this principle, we present Mono-InternVL, a novel monolithic MLLM that seamlessly integrates a set of v"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.08202","kind":"arxiv","version":3},"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/2410.08202/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":"2410.08202","created_at":"2026-07-05T10:30:24.387686+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.08202v3","created_at":"2026-07-05T10:30:24.387686+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.08202","created_at":"2026-07-05T10:30:24.387686+00:00"},{"alias_kind":"pith_short_12","alias_value":"G3FZ7YF6OOSI","created_at":"2026-07-05T10:30:24.387686+00:00"},{"alias_kind":"pith_short_16","alias_value":"G3FZ7YF6OOSIL6ZY","created_at":"2026-07-05T10:30:24.387686+00:00"},{"alias_kind":"pith_short_8","alias_value":"G3FZ7YF6","created_at":"2026-07-05T10:30:24.387686+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2411.10442","citing_title":"Enhancing the Reasoning Ability of Multimodal Large Language Models via Mixed Preference Optimization","ref_index":63,"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":172,"is_internal_anchor":false},{"citing_arxiv_id":"2508.18265","citing_title":"InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency","ref_index":80,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/G3FZ7YF6OOSIL6ZYIXLMOGHD6O","json":"https://pith.science/pith/G3FZ7YF6OOSIL6ZYIXLMOGHD6O.json","graph_json":"https://pith.science/api/pith-number/G3FZ7YF6OOSIL6ZYIXLMOGHD6O/graph.json","events_json":"https://pith.science/api/pith-number/G3FZ7YF6OOSIL6ZYIXLMOGHD6O/events.json","paper":"https://pith.science/paper/G3FZ7YF6"},"agent_actions":{"view_html":"https://pith.science/pith/G3FZ7YF6OOSIL6ZYIXLMOGHD6O","download_json":"https://pith.science/pith/G3FZ7YF6OOSIL6ZYIXLMOGHD6O.json","view_paper":"https://pith.science/paper/G3FZ7YF6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.08202&json=true","fetch_graph":"https://pith.science/api/pith-number/G3FZ7YF6OOSIL6ZYIXLMOGHD6O/graph.json","fetch_events":"https://pith.science/api/pith-number/G3FZ7YF6OOSIL6ZYIXLMOGHD6O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G3FZ7YF6OOSIL6ZYIXLMOGHD6O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G3FZ7YF6OOSIL6ZYIXLMOGHD6O/action/storage_attestation","attest_author":"https://pith.science/pith/G3FZ7YF6OOSIL6ZYIXLMOGHD6O/action/author_attestation","sign_citation":"https://pith.science/pith/G3FZ7YF6OOSIL6ZYIXLMOGHD6O/action/citation_signature","submit_replication":"https://pith.science/pith/G3FZ7YF6OOSIL6ZYIXLMOGHD6O/action/replication_record"}},"created_at":"2026-07-05T10:30:24.387686+00:00","updated_at":"2026-07-05T10:30:24.387686+00:00"}