{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:H3MNCCND22ACAIELNG44I6DLMN","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":"02d0a1cfafce674af1692f8c4c232ce2e6e13ce075e470b7e0541c50ce6a6f86","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-08T10:34:16Z","title_canon_sha256":"4f71831cc5e2eaea204c98c4c53d04a4c42dd6ccc566e2d37ddb68ba0509ccb6"},"schema_version":"1.0","source":{"id":"2311.04589","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.04589","created_at":"2026-07-05T07:30:05Z"},{"alias_kind":"arxiv_version","alias_value":"2311.04589v3","created_at":"2026-07-05T07:30:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.04589","created_at":"2026-07-05T07:30:05Z"},{"alias_kind":"pith_short_12","alias_value":"H3MNCCND22AC","created_at":"2026-07-05T07:30:05Z"},{"alias_kind":"pith_short_16","alias_value":"H3MNCCND22ACAIEL","created_at":"2026-07-05T07:30:05Z"},{"alias_kind":"pith_short_8","alias_value":"H3MNCCND","created_at":"2026-07-05T07:30:05Z"}],"graph_snapshots":[{"event_id":"sha256:b5a87be85da6cafc9667020cf82717c3451212ed83ccedff03338caa5656e0b0","target":"graph","created_at":"2026-07-05T07:30:05Z","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/2311.04589/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite Multi-modal Large Language Models (MM-LLMs) have made exciting strides recently, they are still struggling to efficiently model the interactions among multi-modal inputs and the generation in non-textual modalities. In this work, we propose TEAL (Tokenize and Embed ALl)}, an approach to treat the input from any modality as a token sequence and learn a joint embedding space for all modalities. Specifically, for the input from any modality, TEAL first discretizes it into a token sequence with the off-the-shelf tokenizer and embeds the token sequence into a joint embedding space with a le","authors_text":"Fandong Meng, Jie Zhou, Yingxue Zhang, Zhen Yang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-08T10:34:16Z","title":"TEAL: Tokenize and Embed ALL for Multi-modal Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.04589","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":"sha256:8701c4323d2769b56866b13026dfe1350213b56531d1a22732216e8b62a3f5f4","target":"record","created_at":"2026-07-05T07:30:05Z","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":"02d0a1cfafce674af1692f8c4c232ce2e6e13ce075e470b7e0541c50ce6a6f86","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-08T10:34:16Z","title_canon_sha256":"4f71831cc5e2eaea204c98c4c53d04a4c42dd6ccc566e2d37ddb68ba0509ccb6"},"schema_version":"1.0","source":{"id":"2311.04589","kind":"arxiv","version":3}},"canonical_sha256":"3ed8d109a3d68020208b69b9c4786b63566fa6995d77bfe5e1654dcc0da1508e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3ed8d109a3d68020208b69b9c4786b63566fa6995d77bfe5e1654dcc0da1508e","first_computed_at":"2026-07-05T07:30:05.844094Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:30:05.844094Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IILQ5DmJssEWQSnuBinUelHWEgozAjx9GDAEPHZuhcIf6fUSZ77gX9CgtHamA42CRinoaGtr4A8vxr97eTJ6AA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:30:05.844691Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.04589","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8701c4323d2769b56866b13026dfe1350213b56531d1a22732216e8b62a3f5f4","sha256:b5a87be85da6cafc9667020cf82717c3451212ed83ccedff03338caa5656e0b0"],"state_sha256":"a8962b5de2a190c020cb2cb18b4109b08e78f78c241c2ba8bd801dbd37cef242"}