{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:WFBFMNVWK22GUF62LDPTQJZFET","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":"771c2e4f56d62704cd6c7057ac8a23f355b39eff511a749f71791ec53f8ceb71","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-29T17:59:45Z","title_canon_sha256":"927d069b323ee79923b722a3e1f9d8a778a51bb76af233d1d43f863f1ff14bf6"},"schema_version":"1.0","source":{"id":"2504.20996","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.20996","created_at":"2026-07-05T10:55:52Z"},{"alias_kind":"arxiv_version","alias_value":"2504.20996v1","created_at":"2026-07-05T10:55:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.20996","created_at":"2026-07-05T10:55:52Z"},{"alias_kind":"pith_short_12","alias_value":"WFBFMNVWK22G","created_at":"2026-07-05T10:55:52Z"},{"alias_kind":"pith_short_16","alias_value":"WFBFMNVWK22GUF62","created_at":"2026-07-05T10:55:52Z"},{"alias_kind":"pith_short_8","alias_value":"WFBFMNVW","created_at":"2026-07-05T10:55:52Z"}],"graph_snapshots":[{"event_id":"sha256:0b07eeea3e8952177f169e05f9eac228fcc531c4f0bb9d2235b06f4cf9f02e3b","target":"graph","created_at":"2026-07-05T10:55:52Z","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/2504.20996/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose X-Fusion, a framework that extends pretrained Large Language Models (LLMs) for multimodal tasks while preserving their language capabilities. X-Fusion employs a dual-tower design with modality-specific weights, keeping the LLM's parameters frozen while integrating vision-specific information for both understanding and generation. Our experiments demonstrate that X-Fusion consistently outperforms alternative architectures on both image-to-text and text-to-image tasks. We find that incorporating understanding-focused data improves generation quality, reducing image data noise enhances","authors_text":"Abhishek Tandon, Bolei Zhou, Eli Shechtman, Krishna Kumar Singh, Sicheng Mo, Siddharth Srinivasan Iyer, Thao Nguyen, Xun Huang, Yijun Li, Yong Jae Lee, Yuchen Liu, Yuheng Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-29T17:59:45Z","title":"X-Fusion: Introducing New Modality to Frozen Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.20996","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:a0f21034f64240b24409590c786b961bb899371a9f45981c1353cb16ed56237e","target":"record","created_at":"2026-07-05T10:55:52Z","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":"771c2e4f56d62704cd6c7057ac8a23f355b39eff511a749f71791ec53f8ceb71","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-29T17:59:45Z","title_canon_sha256":"927d069b323ee79923b722a3e1f9d8a778a51bb76af233d1d43f863f1ff14bf6"},"schema_version":"1.0","source":{"id":"2504.20996","kind":"arxiv","version":1}},"canonical_sha256":"b1425636b656b46a17da58df38272524fb222ce813399d8e99c09442f7a1a447","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b1425636b656b46a17da58df38272524fb222ce813399d8e99c09442f7a1a447","first_computed_at":"2026-07-05T10:55:52.748995Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:55:52.748995Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lUbBhbypvs1AKITFgIk4VTGgyXm0hGA9SWdIl/XQRLMwtb3z8bHRdg26jO1tOpZOWYvJ6rh5aC4ZHDdDyNPQBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:55:52.749457Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.20996","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a0f21034f64240b24409590c786b961bb899371a9f45981c1353cb16ed56237e","sha256:0b07eeea3e8952177f169e05f9eac228fcc531c4f0bb9d2235b06f4cf9f02e3b"],"state_sha256":"55cc22e3ea9802147d7a0227af10d0a98bf095d57b2a333ce0bf948450b60f5c"}