{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:EEK5DJ5IQMWUHRC54DBVTODT3L","short_pith_number":"pith:EEK5DJ5I","schema_version":"1.0","canonical_sha256":"2115d1a7a8832d43c45de0c359b873dadfd96050cbc83f3cef0a7d1a0c5676bb","source":{"kind":"arxiv","id":"2405.19335","version":1},"attestation_state":"computed","paper":{"title":"X-VILA: Cross-Modality Alignment for Large Language Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Andrew Tao, Dan Xu, De-An Huang, Hanrong Ye, Hongxu Yin, Jan Kautz, Pavlo Molchanov, Song Han, Wei Ping, Yao Lu, Zhiding Yu","submitted_at":"2024-05-29T17:59:58Z","abstract_excerpt":"We introduce X-VILA, an omni-modality model designed to extend the capabilities of large language models (LLMs) by incorporating image, video, and audio modalities. By aligning modality-specific encoders with LLM inputs and diffusion decoders with LLM outputs, X-VILA achieves cross-modality understanding, reasoning, and generation. To facilitate this cross-modality alignment, we curate an effective interleaved any-to-any modality instruction-following dataset. Furthermore, we identify a significant problem with the current cross-modality alignment method, which results in visual information lo"},"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":"2405.19335","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-29T17:59:58Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"1a0115b8b84440618db0aacbedeafed8cbfc0ad5cc7e03caf4b9dba0773f5c01","abstract_canon_sha256":"f22539a41af7dc582f61cdb27bdd40ba3e1edd199c83117c6fbcf7da16e62926"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:24:51.259720Z","signature_b64":"aUzJKNmq+kWC3qmKxkisLzNHsCvfErte3QQltJpoS+r0N+YslyAyR89LZcG8V8Wo0MsITJQ06SEw/Ar4qQoICw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2115d1a7a8832d43c45de0c359b873dadfd96050cbc83f3cef0a7d1a0c5676bb","last_reissued_at":"2026-07-05T08:24:51.259204Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:24:51.259204Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"X-VILA: Cross-Modality Alignment for Large Language Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Andrew Tao, Dan Xu, De-An Huang, Hanrong Ye, Hongxu Yin, Jan Kautz, Pavlo Molchanov, Song Han, Wei Ping, Yao Lu, Zhiding Yu","submitted_at":"2024-05-29T17:59:58Z","abstract_excerpt":"We introduce X-VILA, an omni-modality model designed to extend the capabilities of large language models (LLMs) by incorporating image, video, and audio modalities. By aligning modality-specific encoders with LLM inputs and diffusion decoders with LLM outputs, X-VILA achieves cross-modality understanding, reasoning, and generation. To facilitate this cross-modality alignment, we curate an effective interleaved any-to-any modality instruction-following dataset. Furthermore, we identify a significant problem with the current cross-modality alignment method, which results in visual information lo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.19335","kind":"arxiv","version":1},"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/2405.19335/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":"2405.19335","created_at":"2026-07-05T08:24:51.259270+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.19335v1","created_at":"2026-07-05T08:24:51.259270+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.19335","created_at":"2026-07-05T08:24:51.259270+00:00"},{"alias_kind":"pith_short_12","alias_value":"EEK5DJ5IQMWU","created_at":"2026-07-05T08:24:51.259270+00:00"},{"alias_kind":"pith_short_16","alias_value":"EEK5DJ5IQMWUHRC5","created_at":"2026-07-05T08:24:51.259270+00:00"},{"alias_kind":"pith_short_8","alias_value":"EEK5DJ5I","created_at":"2026-07-05T08:24:51.259270+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2408.10188","citing_title":"LongVILA: Scaling Long-Context Visual Language Models for Long Videos","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2505.15809","citing_title":"MMaDA: Multimodal Large Diffusion Language Models","ref_index":103,"is_internal_anchor":false},{"citing_arxiv_id":"2408.12528","citing_title":"Show-o: One Single Transformer to Unify Multimodal Understanding and Generation","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06339","citing_title":"Evolution of Video Generative Foundations","ref_index":143,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EEK5DJ5IQMWUHRC54DBVTODT3L","json":"https://pith.science/pith/EEK5DJ5IQMWUHRC54DBVTODT3L.json","graph_json":"https://pith.science/api/pith-number/EEK5DJ5IQMWUHRC54DBVTODT3L/graph.json","events_json":"https://pith.science/api/pith-number/EEK5DJ5IQMWUHRC54DBVTODT3L/events.json","paper":"https://pith.science/paper/EEK5DJ5I"},"agent_actions":{"view_html":"https://pith.science/pith/EEK5DJ5IQMWUHRC54DBVTODT3L","download_json":"https://pith.science/pith/EEK5DJ5IQMWUHRC54DBVTODT3L.json","view_paper":"https://pith.science/paper/EEK5DJ5I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.19335&json=true","fetch_graph":"https://pith.science/api/pith-number/EEK5DJ5IQMWUHRC54DBVTODT3L/graph.json","fetch_events":"https://pith.science/api/pith-number/EEK5DJ5IQMWUHRC54DBVTODT3L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EEK5DJ5IQMWUHRC54DBVTODT3L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EEK5DJ5IQMWUHRC54DBVTODT3L/action/storage_attestation","attest_author":"https://pith.science/pith/EEK5DJ5IQMWUHRC54DBVTODT3L/action/author_attestation","sign_citation":"https://pith.science/pith/EEK5DJ5IQMWUHRC54DBVTODT3L/action/citation_signature","submit_replication":"https://pith.science/pith/EEK5DJ5IQMWUHRC54DBVTODT3L/action/replication_record"}},"created_at":"2026-07-05T08:24:51.259270+00:00","updated_at":"2026-07-05T08:24:51.259270+00:00"}