{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3WFRRTJLVMHULLN35NVDJ44ZT2","short_pith_number":"pith:3WFRRTJL","schema_version":"1.0","canonical_sha256":"dd8b18cd2bab0f45adbbeb6a34f3999e8d8ac1cd10c6c33af51f628174907992","source":{"kind":"arxiv","id":"2406.08798","version":1},"attestation_state":"computed","paper":{"title":"FouRA: Fourier Low Rank Adaptation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fatih Porikli, Kartikeya Bhardwaj, Munawar Hayat, Nilesh Prasad Pandey, Rafael Esteves, Risheek Garrepalli, Shreya Kadambi, Shubhankar Borse, Sweta Priyadarshi, Viswanath Ganapathy","submitted_at":"2024-06-13T04:27:37Z","abstract_excerpt":"While Low-Rank Adaptation (LoRA) has proven beneficial for efficiently fine-tuning large models, LoRA fine-tuned text-to-image diffusion models lack diversity in the generated images, as the model tends to copy data from the observed training samples. This effect becomes more pronounced at higher values of adapter strength and for adapters with higher ranks which are fine-tuned on smaller datasets. To address these challenges, we present FouRA, a novel low-rank method that learns projections in the Fourier domain along with learning a flexible input-dependent adapter rank selection strategy. T"},"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":"2406.08798","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-13T04:27:37Z","cross_cats_sorted":[],"title_canon_sha256":"30357865eec5f1858ff36c1ee97d70c43d015165d391ee3e8b9676c56652c44d","abstract_canon_sha256":"d979be184440279aa64245268682c8ced8e80622340dc6a53977aef652aea863"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:31:23.577205Z","signature_b64":"dKNYYqrwjNjJzHsoOs3SxRcZStouyLAbadwUKYFDQ5KzOqGWLJ3En9VIDMfqMIutcGJ35KHHbTLMDwQ37VblAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dd8b18cd2bab0f45adbbeb6a34f3999e8d8ac1cd10c6c33af51f628174907992","last_reissued_at":"2026-07-05T08:31:23.576760Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:31:23.576760Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FouRA: Fourier Low Rank Adaptation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fatih Porikli, Kartikeya Bhardwaj, Munawar Hayat, Nilesh Prasad Pandey, Rafael Esteves, Risheek Garrepalli, Shreya Kadambi, Shubhankar Borse, Sweta Priyadarshi, Viswanath Ganapathy","submitted_at":"2024-06-13T04:27:37Z","abstract_excerpt":"While Low-Rank Adaptation (LoRA) has proven beneficial for efficiently fine-tuning large models, LoRA fine-tuned text-to-image diffusion models lack diversity in the generated images, as the model tends to copy data from the observed training samples. This effect becomes more pronounced at higher values of adapter strength and for adapters with higher ranks which are fine-tuned on smaller datasets. To address these challenges, we present FouRA, a novel low-rank method that learns projections in the Fourier domain along with learning a flexible input-dependent adapter rank selection strategy. T"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.08798","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/2406.08798/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":"2406.08798","created_at":"2026-07-05T08:31:23.576824+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.08798v1","created_at":"2026-07-05T08:31:23.576824+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.08798","created_at":"2026-07-05T08:31:23.576824+00:00"},{"alias_kind":"pith_short_12","alias_value":"3WFRRTJLVMHU","created_at":"2026-07-05T08:31:23.576824+00:00"},{"alias_kind":"pith_short_16","alias_value":"3WFRRTJLVMHULLN3","created_at":"2026-07-05T08:31:23.576824+00:00"},{"alias_kind":"pith_short_8","alias_value":"3WFRRTJL","created_at":"2026-07-05T08:31:23.576824+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/3WFRRTJLVMHULLN35NVDJ44ZT2","json":"https://pith.science/pith/3WFRRTJLVMHULLN35NVDJ44ZT2.json","graph_json":"https://pith.science/api/pith-number/3WFRRTJLVMHULLN35NVDJ44ZT2/graph.json","events_json":"https://pith.science/api/pith-number/3WFRRTJLVMHULLN35NVDJ44ZT2/events.json","paper":"https://pith.science/paper/3WFRRTJL"},"agent_actions":{"view_html":"https://pith.science/pith/3WFRRTJLVMHULLN35NVDJ44ZT2","download_json":"https://pith.science/pith/3WFRRTJLVMHULLN35NVDJ44ZT2.json","view_paper":"https://pith.science/paper/3WFRRTJL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.08798&json=true","fetch_graph":"https://pith.science/api/pith-number/3WFRRTJLVMHULLN35NVDJ44ZT2/graph.json","fetch_events":"https://pith.science/api/pith-number/3WFRRTJLVMHULLN35NVDJ44ZT2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3WFRRTJLVMHULLN35NVDJ44ZT2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3WFRRTJLVMHULLN35NVDJ44ZT2/action/storage_attestation","attest_author":"https://pith.science/pith/3WFRRTJLVMHULLN35NVDJ44ZT2/action/author_attestation","sign_citation":"https://pith.science/pith/3WFRRTJLVMHULLN35NVDJ44ZT2/action/citation_signature","submit_replication":"https://pith.science/pith/3WFRRTJLVMHULLN35NVDJ44ZT2/action/replication_record"}},"created_at":"2026-07-05T08:31:23.576824+00:00","updated_at":"2026-07-05T08:31:23.576824+00:00"}