{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:SNWXRQHXSMFC5Q3I7ZQ6NH25HL","short_pith_number":"pith:SNWXRQHX","schema_version":"1.0","canonical_sha256":"936d78c0f7930a2ec368fe61e69f5d3afb5a4639ef0e54b8377f30f5dae4d64b","source":{"kind":"arxiv","id":"2604.07753","version":2},"attestation_state":"computed","paper":{"title":"Symbiotic-MoE: Unlocking the Synergy between Generation and Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Symbiotic-MoE lets generative training improve rather than degrade understanding in multimodal models through shared experts and staged optimization.","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Liefeng Bo, Miles Yang, Ping Tan, Xiangyue Liu, Zhao Zhong, Zijian Zhang","submitted_at":"2026-04-09T03:19:26Z","abstract_excerpt":"Empowering Large Multimodal Models (LMMs) with image generation often leads to catastrophic forgetting in understanding tasks due to severe gradient conflicts. While existing paradigms like Mixture-of-Transformers (MoT) mitigate this conflict through structural isolation, they fundamentally sever cross-modal synergy and suffer from capacity fragmentation. In this work, we present Symbiotic-MoE, a unified pre-training framework that resolves task interference within a native multimodal Mixture-of-Experts (MoE) Transformers architecture with zero-parameter overhead. We first identify that standa"},"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":true},"canonical_record":{"source":{"id":"2604.07753","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-04-09T03:19:26Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"bbbeb227bfdec82715f3263b3028322eae1c86f51cd9433d03095c3e13b8bd4e","abstract_canon_sha256":"3a7c974c957afe2e91fedebdfd41e359a41e6a1d67db357c3637d33c3051d304"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T01:16:29.830041Z","signature_b64":"zpljsyCJZIGDd3eyllMVljOzqZ555sUri8RFgCNxfqhYBfELDYEjVrjjubvHlxzX8cdEtFiGtxp2lJ1uFizFCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"936d78c0f7930a2ec368fe61e69f5d3afb5a4639ef0e54b8377f30f5dae4d64b","last_reissued_at":"2026-06-30T01:16:29.829478Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T01:16:29.829478Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Symbiotic-MoE: Unlocking the Synergy between Generation and Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Symbiotic-MoE lets generative training improve rather than degrade understanding in multimodal models through shared experts and staged optimization.","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Liefeng Bo, Miles Yang, Ping Tan, Xiangyue Liu, Zhao Zhong, Zijian Zhang","submitted_at":"2026-04-09T03:19:26Z","abstract_excerpt":"Empowering Large Multimodal Models (LMMs) with image generation often leads to catastrophic forgetting in understanding tasks due to severe gradient conflicts. While existing paradigms like Mixture-of-Transformers (MoT) mitigate this conflict through structural isolation, they fundamentally sever cross-modal synergy and suffer from capacity fragmentation. In this work, we present Symbiotic-MoE, a unified pre-training framework that resolves task interference within a native multimodal Mixture-of-Experts (MoE) Transformers architecture with zero-parameter overhead. We first identify that standa"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Symbiotic-MoE resolves task interference within a native multimodal Mixture-of-Experts (MoE) Transformers architecture with zero-parameter overhead... boosting inherent understanding with remarkable gains on MMLU and OCRBench.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That partitioning experts into task-specific groups with shared experts as a semantic bridge will allow generative signals to enrich understanding without routing collapse or negative interference, and that the progressive training will reliably convert early volatility into constructive feedback.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Symbiotic-MoE introduces modality-aware expert disentanglement and progressive training in a multimodal MoE to achieve synergistic generation and understanding without task interference or extra parameters.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Symbiotic-MoE lets generative training improve rather than degrade understanding in multimodal models through shared experts and staged optimization.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"4771df1dad5b86d026d520a4e9157da03f0d35744620d035958589ce1822c949"},"source":{"id":"2604.07753","kind":"arxiv","version":2},"verdict":{"id":"56e09401-c286-4092-b473-eff63ceea866","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T18:19:49.478109Z","strongest_claim":"Symbiotic-MoE resolves task interference within a native multimodal Mixture-of-Experts (MoE) Transformers architecture with zero-parameter overhead... boosting inherent understanding with remarkable gains on MMLU and OCRBench.","one_line_summary":"Symbiotic-MoE introduces modality-aware expert disentanglement and progressive training in a multimodal MoE to achieve synergistic generation and understanding without task interference or extra parameters.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That partitioning experts into task-specific groups with shared experts as a semantic bridge will allow generative signals to enrich understanding without routing collapse or negative interference, and that the progressive training will reliably convert early volatility into constructive feedback.","pith_extraction_headline":"Symbiotic-MoE lets generative training improve rather than degrade understanding in multimodal models through shared experts and staged optimization."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.07753/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":2,"snapshot_sha256":"a6e46ac44a8bc3784c9c9fd795fab92330fbb639a194e45bba224de9ba0514cf"},"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":"2604.07753","created_at":"2026-06-30T01:16:29.829557+00:00"},{"alias_kind":"arxiv_version","alias_value":"2604.07753v2","created_at":"2026-06-30T01:16:29.829557+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.07753","created_at":"2026-06-30T01:16:29.829557+00:00"},{"alias_kind":"pith_short_12","alias_value":"SNWXRQHXSMFC","created_at":"2026-06-30T01:16:29.829557+00:00"},{"alias_kind":"pith_short_16","alias_value":"SNWXRQHXSMFC5Q3I","created_at":"2026-06-30T01:16:29.829557+00:00"},{"alias_kind":"pith_short_8","alias_value":"SNWXRQHX","created_at":"2026-06-30T01:16:29.829557+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.00293","citing_title":"Rosetta: Composable Native Multimodal Pretraining","ref_index":37,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SNWXRQHXSMFC5Q3I7ZQ6NH25HL","json":"https://pith.science/pith/SNWXRQHXSMFC5Q3I7ZQ6NH25HL.json","graph_json":"https://pith.science/api/pith-number/SNWXRQHXSMFC5Q3I7ZQ6NH25HL/graph.json","events_json":"https://pith.science/api/pith-number/SNWXRQHXSMFC5Q3I7ZQ6NH25HL/events.json","paper":"https://pith.science/paper/SNWXRQHX"},"agent_actions":{"view_html":"https://pith.science/pith/SNWXRQHXSMFC5Q3I7ZQ6NH25HL","download_json":"https://pith.science/pith/SNWXRQHXSMFC5Q3I7ZQ6NH25HL.json","view_paper":"https://pith.science/paper/SNWXRQHX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2604.07753&json=true","fetch_graph":"https://pith.science/api/pith-number/SNWXRQHXSMFC5Q3I7ZQ6NH25HL/graph.json","fetch_events":"https://pith.science/api/pith-number/SNWXRQHXSMFC5Q3I7ZQ6NH25HL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SNWXRQHXSMFC5Q3I7ZQ6NH25HL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SNWXRQHXSMFC5Q3I7ZQ6NH25HL/action/storage_attestation","attest_author":"https://pith.science/pith/SNWXRQHXSMFC5Q3I7ZQ6NH25HL/action/author_attestation","sign_citation":"https://pith.science/pith/SNWXRQHXSMFC5Q3I7ZQ6NH25HL/action/citation_signature","submit_replication":"https://pith.science/pith/SNWXRQHXSMFC5Q3I7ZQ6NH25HL/action/replication_record"}},"created_at":"2026-06-30T01:16:29.829557+00:00","updated_at":"2026-06-30T01:16:29.829557+00:00"}