{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NKW5XDYOAEZDFIXIKRH3CY3DAI","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":"1a31c6d782a870bb5260a5d12d6537635c8b67e45cc55de4ba790691b4ba0941","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-28T15:52:23Z","title_canon_sha256":"e125b23fc2304d815ea5fb741dff73d09040a1c26a642dc8f12970fb18ab17e2"},"schema_version":"1.0","source":{"id":"2408.15881","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.15881","created_at":"2026-07-05T09:24:38Z"},{"alias_kind":"arxiv_version","alias_value":"2408.15881v3","created_at":"2026-07-05T09:24:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.15881","created_at":"2026-07-05T09:24:38Z"},{"alias_kind":"pith_short_12","alias_value":"NKW5XDYOAEZD","created_at":"2026-07-05T09:24:38Z"},{"alias_kind":"pith_short_16","alias_value":"NKW5XDYOAEZDFIXI","created_at":"2026-07-05T09:24:38Z"},{"alias_kind":"pith_short_8","alias_value":"NKW5XDYO","created_at":"2026-07-05T09:24:38Z"}],"graph_snapshots":[{"event_id":"sha256:9f1e7091c20b50bae37d20180d51f53948a24d0c914441db08f7bd6f0ff0d78e","target":"graph","created_at":"2026-07-05T09:24:38Z","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/2408.15881/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce LLaVA-MoD, a novel framework designed to enable the efficient training of small-scale Multimodal Language Models (s-MLLM) by distilling knowledge from large-scale MLLM (l-MLLM). Our approach tackles two fundamental challenges in MLLM distillation. First, we optimize the network structure of s-MLLM by integrating a sparse Mixture of Experts (MoE) architecture into the language model, striking a balance between computational efficiency and model expressiveness. Second, we propose a progressive knowledge transfer strategy to ensure comprehensive knowledge migration. This strategy beg","authors_text":"Bolin Li, Chenning Xu, Fangxun Shu, Guanghao Zhang, Hao Jiang, Haonan Shi, Haoyuan Li, Hongsheng Li, Lei Zhang, Le Zhuo, Long Chen, Si Liu, Siming Fu, Tao Zhong, Wanggui He, Yue Liao, Zhelun Yu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-28T15:52:23Z","title":"LLaVA-MoD: Making LLaVA Tiny via MoE Knowledge Distillation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.15881","kind":"arxiv","version":3},"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:ac38605a4030beb8b79aaead41f74691890d76a1112ad45137a58b3896ec4ed6","target":"record","created_at":"2026-07-05T09:24:38Z","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":"1a31c6d782a870bb5260a5d12d6537635c8b67e45cc55de4ba790691b4ba0941","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-28T15:52:23Z","title_canon_sha256":"e125b23fc2304d815ea5fb741dff73d09040a1c26a642dc8f12970fb18ab17e2"},"schema_version":"1.0","source":{"id":"2408.15881","kind":"arxiv","version":3}},"canonical_sha256":"6aaddb8f0e013232a2e8544fb16363021d06096a764d4e63854ee16f945486a4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6aaddb8f0e013232a2e8544fb16363021d06096a764d4e63854ee16f945486a4","first_computed_at":"2026-07-05T09:24:38.074257Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:24:38.074257Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WPqTZnUGcX6EYCORuONUb60uT9DbRQhRwu/PZ5Q08eg6QbXRN4iwgLOBlDWjuTDKArQK2CrZalgfRKx+dLHmCA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:24:38.074771Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.15881","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ac38605a4030beb8b79aaead41f74691890d76a1112ad45137a58b3896ec4ed6","sha256:9f1e7091c20b50bae37d20180d51f53948a24d0c914441db08f7bd6f0ff0d78e"],"state_sha256":"f6598b39d0b81270d1df66f1613a5fa4712adb87f88e9692a22ff4a40d51d6fe"}