{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:W77LJ2OTCHNHBWSHPDM5DIRD3D","short_pith_number":"pith:W77LJ2OT","schema_version":"1.0","canonical_sha256":"b7feb4e9d311da70da4778d9d1a223d8e503b11f9e9cc43b8192967e24915123","source":{"kind":"arxiv","id":"2505.18413","version":1},"attestation_state":"computed","paper":{"title":"LatentLLM: Attention-Aware Joint Tensor Compression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CV"],"primary_cat":"cs.LG","authors_text":"Jing Liu, Matthew Brand, Pu (Perry) Wang, Toshiaki Koike-Akino, Xiangyu Chen, Ye Wang","submitted_at":"2025-05-23T22:39:54Z","abstract_excerpt":"Modern foundation models such as large language models (LLMs) and large multi-modal models (LMMs) require a massive amount of computational and memory resources. We propose a new framework to convert such LLMs/LMMs into a reduced-dimension latent structure. Our method extends a local activation-aware tensor decomposition to a global attention-aware joint tensor de-composition. Our framework can significantly improve the model accuracy over the existing model compression methods when reducing the latent dimension to realize computationally/memory-efficient LLMs/LLMs. We show the benefit on seve"},"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":"2505.18413","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-23T22:39:54Z","cross_cats_sorted":["cs.AI","cs.CL","cs.CV"],"title_canon_sha256":"65f7909a98e06c51997ae7b1ab11b1fedf7c478d3c4b4a1935fa39d66aa59b69","abstract_canon_sha256":"5ca0d565c90c2445ec2c066c22a53244de0229645f700202ceb10c253995fd16"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:08:46.022946Z","signature_b64":"7A//NoXC3iWS1NHmS2YPyM1CLIt+/iyc7pXX0xB2iKB/KfVw/8QYH2nXd7tQLc54g21XpBtAuHeYGy+y/b0UBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b7feb4e9d311da70da4778d9d1a223d8e503b11f9e9cc43b8192967e24915123","last_reissued_at":"2026-07-05T11:08:46.022607Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:08:46.022607Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LatentLLM: Attention-Aware Joint Tensor Compression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CV"],"primary_cat":"cs.LG","authors_text":"Jing Liu, Matthew Brand, Pu (Perry) Wang, Toshiaki Koike-Akino, Xiangyu Chen, Ye Wang","submitted_at":"2025-05-23T22:39:54Z","abstract_excerpt":"Modern foundation models such as large language models (LLMs) and large multi-modal models (LMMs) require a massive amount of computational and memory resources. We propose a new framework to convert such LLMs/LMMs into a reduced-dimension latent structure. Our method extends a local activation-aware tensor decomposition to a global attention-aware joint tensor de-composition. Our framework can significantly improve the model accuracy over the existing model compression methods when reducing the latent dimension to realize computationally/memory-efficient LLMs/LLMs. We show the benefit on seve"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.18413","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/2505.18413/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":"2505.18413","created_at":"2026-07-05T11:08:46.022663+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.18413v1","created_at":"2026-07-05T11:08:46.022663+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.18413","created_at":"2026-07-05T11:08:46.022663+00:00"},{"alias_kind":"pith_short_12","alias_value":"W77LJ2OTCHNH","created_at":"2026-07-05T11:08:46.022663+00:00"},{"alias_kind":"pith_short_16","alias_value":"W77LJ2OTCHNHBWSH","created_at":"2026-07-05T11:08:46.022663+00:00"},{"alias_kind":"pith_short_8","alias_value":"W77LJ2OT","created_at":"2026-07-05T11:08:46.022663+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/W77LJ2OTCHNHBWSHPDM5DIRD3D","json":"https://pith.science/pith/W77LJ2OTCHNHBWSHPDM5DIRD3D.json","graph_json":"https://pith.science/api/pith-number/W77LJ2OTCHNHBWSHPDM5DIRD3D/graph.json","events_json":"https://pith.science/api/pith-number/W77LJ2OTCHNHBWSHPDM5DIRD3D/events.json","paper":"https://pith.science/paper/W77LJ2OT"},"agent_actions":{"view_html":"https://pith.science/pith/W77LJ2OTCHNHBWSHPDM5DIRD3D","download_json":"https://pith.science/pith/W77LJ2OTCHNHBWSHPDM5DIRD3D.json","view_paper":"https://pith.science/paper/W77LJ2OT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.18413&json=true","fetch_graph":"https://pith.science/api/pith-number/W77LJ2OTCHNHBWSHPDM5DIRD3D/graph.json","fetch_events":"https://pith.science/api/pith-number/W77LJ2OTCHNHBWSHPDM5DIRD3D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W77LJ2OTCHNHBWSHPDM5DIRD3D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W77LJ2OTCHNHBWSHPDM5DIRD3D/action/storage_attestation","attest_author":"https://pith.science/pith/W77LJ2OTCHNHBWSHPDM5DIRD3D/action/author_attestation","sign_citation":"https://pith.science/pith/W77LJ2OTCHNHBWSHPDM5DIRD3D/action/citation_signature","submit_replication":"https://pith.science/pith/W77LJ2OTCHNHBWSHPDM5DIRD3D/action/replication_record"}},"created_at":"2026-07-05T11:08:46.022663+00:00","updated_at":"2026-07-05T11:08:46.022663+00:00"}