{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:4P7LGEN7BCCXNBTC3QS6Y3JTFQ","short_pith_number":"pith:4P7LGEN7","schema_version":"1.0","canonical_sha256":"e3feb311bf0885768662dc25ec6d332c35af7c4c0b01416d36254ac42f448dc5","source":{"kind":"arxiv","id":"2406.15758","version":1},"attestation_state":"computed","paper":{"title":"EDGE-LLM: Enabling Efficient Large Language Model Adaptation on Edge Devices via Layerwise Unified Compression and Adaptive Layer Tuning and Voting","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"cs.LG","authors_text":"Haoran You, Ruijie Gao, Sreenidhi Reedy Bommu, Xiaoya Zhou, Yang Katie Zhao, Yingyan Celine Lin, Yuhan Li, Zheng Wang, Zhongzhi Yu","submitted_at":"2024-06-22T06:51:47Z","abstract_excerpt":"Efficient adaption of large language models (LLMs) on edge devices is essential for applications requiring continuous and privacy-preserving adaptation and inference. However, existing tuning techniques fall short because of the high computation and memory overheads. To this end, we introduce a computation- and memory-efficient LLM tuning framework, called Edge-LLM, to facilitate affordable and effective LLM adaptation on edge devices. Specifically, Edge-LLM features three core components: (1) a layer-wise unified compression (LUC) technique to reduce the computation overhead by generating lay"},"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":"2406.15758","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-22T06:51:47Z","cross_cats_sorted":["cs.DC"],"title_canon_sha256":"37b00e41e49cc46574a57dc52fb8dc9d2736588a91f7df18f4ba12f3cc04223b","abstract_canon_sha256":"efb43869c0be18b6f19428c2ae5ef477ed06b6cc3266b50b4f188195f937f7f0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:35:49.193740Z","signature_b64":"iDJ1UtAWVEPXRYSufBYjeN+/98oTOHvOT+NOjJdM9LUz+72zMm+dafyWTlPdKJsyJSytshcY3jEyk7X65Hh7BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e3feb311bf0885768662dc25ec6d332c35af7c4c0b01416d36254ac42f448dc5","last_reissued_at":"2026-07-05T08:35:49.193263Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:35:49.193263Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EDGE-LLM: Enabling Efficient Large Language Model Adaptation on Edge Devices via Layerwise Unified Compression and Adaptive Layer Tuning and Voting","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"cs.LG","authors_text":"Haoran You, Ruijie Gao, Sreenidhi Reedy Bommu, Xiaoya Zhou, Yang Katie Zhao, Yingyan Celine Lin, Yuhan Li, Zheng Wang, Zhongzhi Yu","submitted_at":"2024-06-22T06:51:47Z","abstract_excerpt":"Efficient adaption of large language models (LLMs) on edge devices is essential for applications requiring continuous and privacy-preserving adaptation and inference. However, existing tuning techniques fall short because of the high computation and memory overheads. To this end, we introduce a computation- and memory-efficient LLM tuning framework, called Edge-LLM, to facilitate affordable and effective LLM adaptation on edge devices. Specifically, Edge-LLM features three core components: (1) a layer-wise unified compression (LUC) technique to reduce the computation overhead by generating lay"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.15758","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/2406.15758/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":"2406.15758","created_at":"2026-07-05T08:35:49.193322+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.15758v1","created_at":"2026-07-05T08:35:49.193322+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.15758","created_at":"2026-07-05T08:35:49.193322+00:00"},{"alias_kind":"pith_short_12","alias_value":"4P7LGEN7BCCX","created_at":"2026-07-05T08:35:49.193322+00:00"},{"alias_kind":"pith_short_16","alias_value":"4P7LGEN7BCCXNBTC","created_at":"2026-07-05T08:35:49.193322+00:00"},{"alias_kind":"pith_short_8","alias_value":"4P7LGEN7","created_at":"2026-07-05T08:35:49.193322+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/4P7LGEN7BCCXNBTC3QS6Y3JTFQ","json":"https://pith.science/pith/4P7LGEN7BCCXNBTC3QS6Y3JTFQ.json","graph_json":"https://pith.science/api/pith-number/4P7LGEN7BCCXNBTC3QS6Y3JTFQ/graph.json","events_json":"https://pith.science/api/pith-number/4P7LGEN7BCCXNBTC3QS6Y3JTFQ/events.json","paper":"https://pith.science/paper/4P7LGEN7"},"agent_actions":{"view_html":"https://pith.science/pith/4P7LGEN7BCCXNBTC3QS6Y3JTFQ","download_json":"https://pith.science/pith/4P7LGEN7BCCXNBTC3QS6Y3JTFQ.json","view_paper":"https://pith.science/paper/4P7LGEN7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.15758&json=true","fetch_graph":"https://pith.science/api/pith-number/4P7LGEN7BCCXNBTC3QS6Y3JTFQ/graph.json","fetch_events":"https://pith.science/api/pith-number/4P7LGEN7BCCXNBTC3QS6Y3JTFQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4P7LGEN7BCCXNBTC3QS6Y3JTFQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4P7LGEN7BCCXNBTC3QS6Y3JTFQ/action/storage_attestation","attest_author":"https://pith.science/pith/4P7LGEN7BCCXNBTC3QS6Y3JTFQ/action/author_attestation","sign_citation":"https://pith.science/pith/4P7LGEN7BCCXNBTC3QS6Y3JTFQ/action/citation_signature","submit_replication":"https://pith.science/pith/4P7LGEN7BCCXNBTC3QS6Y3JTFQ/action/replication_record"}},"created_at":"2026-07-05T08:35:49.193322+00:00","updated_at":"2026-07-05T08:35:49.193322+00:00"}