{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:TMBRF6KZKHA5GU5VXTPCVVP7HL","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"5bc4a20fed870c3e0b635c353333fe69978eb02b76ed842006650b48e53ad853","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-16T18:31:23Z","title_canon_sha256":"d81a309edf9a571b4c3f2abd5886ba6527ae67663a7c8f1c944bbc1aba628e48"},"schema_version":"1.0","source":{"id":"2507.12566","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.12566","created_at":"2026-07-05T11:38:34Z"},{"alias_kind":"arxiv_version","alias_value":"2507.12566v1","created_at":"2026-07-05T11:38:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.12566","created_at":"2026-07-05T11:38:34Z"},{"alias_kind":"pith_short_12","alias_value":"TMBRF6KZKHA5","created_at":"2026-07-05T11:38:34Z"},{"alias_kind":"pith_short_16","alias_value":"TMBRF6KZKHA5GU5V","created_at":"2026-07-05T11:38:34Z"},{"alias_kind":"pith_short_8","alias_value":"TMBRF6KZ","created_at":"2026-07-05T11:38:34Z"}],"graph_snapshots":[{"event_id":"sha256:1c218b798d0a7978785885ebbf2f596f75f9824ca50e4f7a89c84af7c94d675d","target":"graph","created_at":"2026-07-05T11:38:34Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2507.12566/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper focuses on monolithic Multimodal Large Language Models (MLLMs), which integrate visual encoding and language decoding into a single model. Existing structures and pre-training strategies for monolithic MLLMs often suffer from unstable optimization and catastrophic forgetting. To address these challenges, our key idea is to embed a new visual parameter space into a pre-trained LLM, enabling stable learning of visual knowledge from noisy data via delta tuning. Based on this principle, we first introduce Mono-InternVL, an advanced monolithic MLLM that incorporates a set of visual exper","authors_text":"Changyao Tian, Gen Luo, Hao Li, Jifeng Dai, Weiyun Wang, Wenhai Wang, Wenhan Dou, Wenhao Li, Xizhou Zhu, Xue Yang, Yu Qiao, Zhaokai Wang","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-16T18:31:23Z","title":"Mono-InternVL-1.5: Towards Cheaper and Faster Monolithic Multimodal Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.12566","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:1991460e9ab0dcc82131f1ce280c372652ff790324af661f15436bc6723715ca","target":"record","created_at":"2026-07-05T11:38:34Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"5bc4a20fed870c3e0b635c353333fe69978eb02b76ed842006650b48e53ad853","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-16T18:31:23Z","title_canon_sha256":"d81a309edf9a571b4c3f2abd5886ba6527ae67663a7c8f1c944bbc1aba628e48"},"schema_version":"1.0","source":{"id":"2507.12566","kind":"arxiv","version":1}},"canonical_sha256":"9b0312f95951c1d353b5bcde2ad5ff3af5099b67d7a00511d3d3890cfd128f51","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9b0312f95951c1d353b5bcde2ad5ff3af5099b67d7a00511d3d3890cfd128f51","first_computed_at":"2026-07-05T11:38:34.686533Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:38:34.686533Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"83A22roSNYYc+KI50f1DbEBk81qibXar9SLA8s/26JiRqH9fV1O7c7IyYybEg2E8doTP5Jgw8xAVQ2XVe7d2AA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:38:34.687231Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.12566","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1991460e9ab0dcc82131f1ce280c372652ff790324af661f15436bc6723715ca","sha256:1c218b798d0a7978785885ebbf2f596f75f9824ca50e4f7a89c84af7c94d675d"],"state_sha256":"988669d41d692c5b781a7d7ae09958d7f98d84169f2c72a38135e66229cddb09"}