{"as_of":"2026-08-09T00:20:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:d3b131bca3fea2ff79888770b39821188f6969ae216e3340fbf5d9ddc10b6cc5","coverage":[{"denominator":76,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":76,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T19:53:04.394610Z","state":"measured"},{"denominator":76,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":76,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2507.04599/citation-record","integrity":"/paper/2507.04599/integrity","json":"/paper/2507.04599/citation-record.json","paper":"/paper/2507.04599"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:53:01.034762Z","title":"Cross-image attention for zero- shot appearance transfer","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.04599","last_updated":"2025-07-24T09:12:08Z","snapshot_observed_at":"2026-08-06T19:41:54.718857Z","submitted_at":"2025-07-07T01:31:01Z","title":"QR-LoRA: Efficient and Disentangled Fine-tuning via QR Decomposition for Customized Generation","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-06T19:53:01.034762Z"},"links":{"citing_paper":"/paper/2507.04599"},"observation_digest":"sha256:08aa0af9688db7234f8f3c270f37a8b5b1b594544b1f125daacd29689fb6606a","observation_id":"a541bfcb-7c50-4443-968e-3307e22c0b3e","resolution":{"observed_at":"2026-08-06T19:53:01.034762Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:53:05.741793Z","title":"Emerg- ing properties in self-supervised vision transformers","venue":null,"work_id":"b5973af6-3ee9-4e97-b1f1-6242a447ce80","year":2021},"citing_paper":{"arxiv_id":"2507.04599","last_updated":"2025-07-24T09:12:08Z","snapshot_observed_at":"2026-08-06T19:41:54.718857Z","submitted_at":"2025-07-07T01:31:01Z","title":"QR-LoRA: Efficient and Disentangled Fine-tuning via QR Decomposition for Customized Generation","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-06T19:53:01.087916Z"},"links":{"citing_paper":"/paper/2507.04599"},"observation_digest":"sha256:e68b3a70cbfc03440f4600d3cec963c5fb9c594077dd8aceb8aedb0850edf8cc","observation_id":"e8d11688-1995-4805-9d8e-c1394eb894f4","resolution":{"observed_at":"2026-08-06T19:53:05.747100Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2304.03373","last_updated":"2023-11-29T10:21:48Z","snapshot_observed_at":"2026-08-06T15:13:18.487979Z","submitted_at":"2023-04-06T21:00:00Z","title":"Training-Free Layout Control with Cross-Attention Guidance","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.03373","snapshot_observed_at":"2026-08-06T19:53:01.160385Z","title":"Training-free layout control with cross-attention guidance","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.04599","last_updated":"2025-07-24T09:12:08Z","snapshot_observed_at":"2026-08-06T19:41:54.718857Z","submitted_at":"2025-07-07T01:31:01Z","title":"QR-LoRA: Efficient and Disentangled Fine-tuning via QR Decomposition for Customized Generation","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-06T19:53:01.160385Z"},"links":{"cited_paper":"/paper/2304.03373","citing_paper":"/paper/2507.04599"},"observation_digest":"sha256:e832d2b92771a10255597f837a92ebb84a72f43fb8ca39410a1f569d53640e3b","observation_id":"9c31251b-d2aa-412a-bdf0-8d9010fd679a","resolution":{"observed_at":"2026-08-06T19:53:01.160385Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:53:05.723675Z","title":"The approximation of one ma- trix by another of lower rank","venue":null,"work_id":"e6e9733e-767b-4818-9e15-a7c291bf1550","year":null},"citing_paper":{"arxiv_id":"2507.04599","last_updated":"2025-07-24T09:12:08Z","snapshot_observed_at":"2026-08-06T19:41:54.718857Z","submitted_at":"2025-07-07T01:31:01Z","title":"QR-LoRA: Efficient and Disentangled Fine-tuning via QR Decomposition for Customized Generation","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-06T19:53:01.233316Z"},"links":{"citing_paper":"/paper/2507.04599"},"observation_digest":"sha256:e2e33ed405739ba02db722d075562f4d9b72841430ce53f0880c812fe0746d8f","observation_id":"e05015f5-d6d7-4390-ac28-76b393d03458","resolution":{"observed_at":"2026-08-06T19:53:05.728827Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:53:05.703875Z","title":"Diffusion self-guidance for control- lable image generation","venue":null,"work_id":"b18bbbe1-fd48-4d12-8b95-167e42c41c2e","year":2023},"citing_paper":{"arxiv_id":"2507.04599","last_updated":"2025-07-24T09:12:08Z","snapshot_observed_at":"2026-08-06T19:41:54.718857Z","submitted_at":"2025-07-07T01:31:01Z","title":"QR-LoRA: Efficient and Disentangled Fine-tuning via QR Decomposition for Customized Generation","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-06T19:53:01.336253Z"},"links":{"citing_paper":"/paper/2507.04599"},"observation_digest":"sha256:aa80c9cc528b4f6baf600f11b69a90b4a232e7b42c6c4da83e1f163e2011ac00","observation_id":"572e40bf-e39b-487b-b863-5dbc66722755","resolution":{"observed_at":"2026-08-06T19:53:05.711279Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:53:05.686622Z","title":"Scaling recti- fied flow transformers for high-resolution image synthesis","venue":null,"work_id":"a8f5cadb-4a4d-4b38-8c7b-71de2aaa094b","year":2024},"citing_paper":{"arxiv_id":"2507.04599","last_updated":"2025-07-24T09:12:08Z","snapshot_observed_at":"2026-08-06T19:41:54.718857Z","submitted_at":"2025-07-07T01:31:01Z","title":"QR-LoRA: Efficient and Disentangled Fine-tuning via QR Decomposition for Customized Generation","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-06T19:53:01.440114Z"},"links":{"citing_paper":"/paper/2507.04599"},"observation_digest":"sha256:476bde3a219e65210ce8b286393b83e9046c5df5004478af31e46a078f3ab808","observation_id":"fce48e39-cd5f-4ea8-ba49-2f77625fd912","resolution":{"observed_at":"2026-08-06T19:53:05.691987Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:53:05.667756Z","title":"Lora-x: Bridging foundation models with training-free cross-model adaptation","venue":null,"work_id":"1e85cf98-69e1-45ba-8352-34c0d0b6e761","year":2025},"citing_paper":{"arxiv_id":"2507.04599","last_updated":"2025-07-24T09:12:08Z","snapshot_observed_at":"2026-08-06T19:41:54.718857Z","submitted_at":"2025-07-07T01:31:01Z","title":"QR-LoRA: Efficient and Disentangled Fine-tuning via QR Decomposition for Customized Generation","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-06T19:53:01.546370Z"},"links":{"citing_paper":"/paper/2507.04599"},"observation_digest":"sha256:6190fc764fb65054f62138bdfcad4dfb381902eeaa0c6b01755cd7903e45a09e","observation_id":"8435a61d-8fdc-463f-80eb-4fc07db4b984","resolution":{"observed_at":"2026-08-06T19:53:05.673295Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:53:05.649315Z","title":"Implicit style-content separation using b-lora","venue":null,"work_id":"95cba3db-de8a-4629-b819-ab61841e5d32","year":2025},"citing_paper":{"arxiv_id":"2507.04599","last_updated":"2025-07-24T09:12:08Z","snapshot_observed_at":"2026-08-06T19:41:54.718857Z","submitted_at":"2025-07-07T01:31:01Z","title":"QR-LoRA: Efficient and Disentangled Fine-tuning via QR Decomposition for Customized Generation","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-06T19:53:01.652182Z"},"links":{"citing_paper":"/paper/2507.04599"},"observation_digest":"sha256:23e65877f35dc693973e1bc49fe27b769a737d2c57d01030f3a6a23f854b6cff","observation_id":"ab06d568-9f66-4979-bf57-d8a5a9c17728","resolution":{"observed_at":"2026-08-06T19:53:05.655320Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2208.01618","last_updated":"2022-08-02T17:50:36Z","snapshot_observed_at":"2026-08-02T23:40:32.342515Z","submitted_at":"2022-08-02T17:50:36Z","title":"An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2208.01618","snapshot_observed_at":"2026-08-06T19:53:01.736688Z","title":"An image is worth one word: Personalizing text-to- image generation using textual inversion","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.04599","last_updated":"2025-07-24T09:12:08Z","snapshot_observed_at":"2026-08-06T19:41:54.718857Z","submitted_at":"2025-07-07T01:31:01Z","title":"QR-LoRA: Efficient and Disentangled Fine-tuning via QR Decomposition for Customized Generation","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-06T19:53:01.736688Z"},"links":{"cited_paper":"/paper/2208.01618","citing_paper":"/paper/2507.04599"},"observation_digest":"sha256:8dff9a4ca7bb41fa24f34aa07fa5318ae59c4fc00ea5216d4e4ab617c0ac69c6","observation_id":"992bdb3c-2323-43d6-b1a6-9f046440f492","resolution":{"observed_at":"2026-08-06T19:53:01.736688Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:53:05.633327Z","title":"Singular value de- composition and least squares solutions","venue":null,"work_id":"b124fdaa-be33-48de-b1d0-97ccbd4335b5","year":1971},"citing_paper":{"arxiv_id":"2507.04599","last_updated":"2025-07-24T09:12:08Z","snapshot_observed_at":"2026-08-06T19:41:54.718857Z","submitted_at":"2025-07-07T01:31:01Z","title":"QR-LoRA: Efficient and Disentangled Fine-tuning via QR Decomposition for Customized Generation","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-06T19:53:01.839850Z"},"links":{"citing_paper":"/paper/2507.04599"},"observation_digest":"sha256:87dadec0d6f21e057dfcbba26807d9dd58e27f0b7c098c8f9815144bef1a6740","observation_id":"3e9cf544-ea7a-4140-a6dc-a7253bd908f5","resolution":{"observed_at":"2026-08-06T19:53:05.638330Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:53:05.616439Z","title":"Matrix computations johns hopkins university press","venue":null,"work_id":"70a755da-bca4-4bc8-b980-568b0383580f","year":1996},"citing_paper":{"arxiv_id":"2507.04599","last_updated":"2025-07-24T09:12:08Z","snapshot_observed_at":"2026-08-06T19:41:54.718857Z","submitted_at":"2025-07-07T01:31:01Z","title":"QR-LoRA: Efficient and Disentangled Fine-tuning via QR Decomposition for Customized Generation","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-06T19:53:01.889373Z"},"links":{"citing_paper":"/paper/2507.04599"},"observation_digest":"sha256:3aa72b201e4359ce9ad118909eabc2e6956c03624a921aced0ecb2bd9c4adaf8","observation_id":"8477a5f4-cdc1-48a6-a648-a93bc4ef4819","resolution":{"observed_at":"2026-08-06T19:53:05.622225Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:53:05.597696Z","title":"Mix-of-show: Decentralized low-rank adaptation for multi-concept customization of diffusion models","venue":null,"work_id":"61836c22-c701-4a64-a1ab-e1a36c01b94a","year":null},"citing_paper":{"arxiv_id":"2507.04599","last_updated":"2025-07-24T09:12:08Z","snapshot_observed_at":"2026-08-06T19:41:54.718857Z","submitted_at":"2025-07-07T01:31:01Z","title":"QR-LoRA: Efficient and Disentangled Fine-tuning via QR Decomposition for Customized Generation","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-06T19:53:01.969117Z"},"links":{"citing_paper":"/paper/2507.04599"},"observation_digest":"sha256:5ab99082fd7ce97b01058962038ec7ad6e8f382134c6c006ec069f744516a11e","observation_id":"9a5a833a-3973-41ba-ae4f-df68bbeecfc9","resolution":{"observed_at":"2026-08-06T19:53:05.603971Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:53:02.032411Z","title":"Svdiff: Compact param- eter space for diffusion fine-tuning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.04599","last_updated":"2025-07-24T09:12:08Z","snapshot_observed_at":"2026-08-06T19:41:54.718857Z","submitted_at":"2025-07-07T01:31:01Z","title":"QR-LoRA: Efficient and Disentangled Fine-tuning via QR Decomposition for Customized Generation","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-06T19:53:02.032411Z"},"links":{"citing_paper":"/paper/2507.04599"},"observation_digest":"sha256:2aa0c2ccad0c59506c92765aebe02bd6bdffab67e2c542a7d1a5d1afa09e471d","observation_id":"6e6d14a4-3f01-492a-9431-2e9f0f6c7633","resolution":{"observed_at":"2026-08-06T19:53:02.032411Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2208.01626","last_updated":"2022-08-02T17:55:41Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2022-08-02T17:55:41Z","title":"Prompt-to-Prompt Image Editing with Cross Attention Control","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2208.01626","snapshot_observed_at":"2026-08-06T19:53:02.136567Z","title":"Prompt-to-prompt im- age editing with cross attention control","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.04599","last_updated":"2025-07-24T09:12:08Z","snapshot_observed_at":"2026-08-06T19:41:54.718857Z","submitted_at":"2025-07-07T01:31:01Z","title":"QR-LoRA: Efficient and Disentangled Fine-tuning via QR Decomposition for Customized Generation","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-06T19:53:02.136567Z"},"links":{"cited_paper":"/paper/2208.01626","citing_paper":"/paper/2507.04599"},"observation_digest":"sha256:33cbdd58919002cf80b6d78db9044765be0d35bf36b2214f16534f2eca50b9a8","observation_id":"3f89a281-a45c-4644-b7f6-0d6b104d036c","resolution":{"observed_at":"2026-08-06T19:53:02.136567Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:53:02.201432Z","title":"Style aligned image generation via shared atten- tion","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.04599","last_updated":"2025-07-24T09:12:08Z","snapshot_observed_at":"2026-08-06T19:41:54.718857Z","submitted_at":"2025-07-07T01:31:01Z","title":"QR-LoRA: Efficient and Disentangled Fine-tuning via QR Decomposition for Customized Generation","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-06T19:53:02.201432Z"},"links":{"citing_paper":"/paper/2507.04599"},"observation_digest":"sha256:6965dd8d26e6ec869d86382c9dd6b1fe5dc73537ed43cca3a43b3e98dc5997f5","observation_id":"564ec7c0-e7eb-47c9-8bf4-40d9926f49de","resolution":{"observed_at":"2026-08-06T19:53:02.201432Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:53:02.297308Z","title":"Denoising dif- fusion probabilistic models","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.04599","last_updated":"2025-07-24T09:12:08Z","snapshot_observed_at":"2026-08-06T19:41:54.718857Z","submitted_at":"2025-07-07T01:31:01Z","title":"QR-LoRA: Efficient and Disentangled Fine-tuning via QR Decomposition for Customized Generation","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-06T19:53:02.297308Z"},"links":{"citing_paper":"/paper/2507.04599"},"observation_digest":"sha256:64d752cde3951d7f26f7eb40b9d5b53b102cf5de403474f2d55e97b23112e7d5","observation_id":"426101a5-34af-40a1-9050-881b70a40205","resolution":{"observed_at":"2026-08-06T19:53:02.297308Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2106.09685","last_updated":"2021-10-16T18:40:34Z","snapshot_observed_at":"2026-08-07T07:43:16.294957Z","submitted_at":"2021-06-17T17:37:18Z","title":"LoRA: Low-Rank Adaptation of Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.09685","snapshot_observed_at":"2026-08-06T19:53:02.400141Z","title":"Lora: Low-rank adaptation of large language models","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.04599","last_updated":"2025-07-24T09:12:08Z","snapshot_observed_at":"2026-08-06T19:41:54.718857Z","submitted_at":"2025-07-07T01:31:01Z","title":"QR-LoRA: Efficient and Disentangled Fine-tuning via QR Decomposition for Customized Generation","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-06T19:53:02.400141Z"},"links":{"cited_paper":"/paper/2106.09685","citing_paper":"/paper/2507.04599"},"observation_digest":"sha256:3d305ea1f02714c3aadb2d3fed0079a8ff7a8547d425b53d168b93cf1c787563","observation_id":"a1533005-fdf9-4ac4-a359-0cf4c7416e5b","resolution":{"observed_at":"2026-08-06T19:53:02.400141Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:53:05.547151Z","title":"Zero-shot text-guided object gen- eration with dream fields","venue":null,"work_id":"9263bc84-295b-40ba-b92c-da1c42520d4f","year":2022},"citing_paper":{"arxiv_id":"2507.04599","last_updated":"2025-07-24T09:12:08Z","snapshot_observed_at":"2026-08-06T19:41:54.718857Z","submitted_at":"2025-07-07T01:31:01Z","title":"QR-LoRA: Efficient and Disentangled Fine-tuning via QR Decomposition for Customized Generation","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-06T19:53:02.486689Z"},"links":{"citing_paper":"/paper/2507.04599"},"observation_digest":"sha256:ff334f0b880ffa909d46def01795dfea5471a07bdc62316dad0a9e5c870f95cc","observation_id":"f267968c-3bf7-4bf0-9f39-fd8ed9680a9f","resolution":{"observed_at":"2026-08-06T19:53:05.552386Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:53:05.531164Z","title":"Decor:decomposition and projection of text embeddings for text-to-image cus- tomization, 2024","venue":null,"work_id":"6cd6616f-7a4e-41bb-a840-7e78e7b36ca5","year":2024},"citing_paper":{"arxiv_id":"2507.04599","last_updated":"2025-07-24T09:12:08Z","snapshot_observed_at":"2026-08-06T19:41:54.718857Z","submitted_at":"2025-07-07T01:31:01Z","title":"QR-LoRA: Efficient and Disentangled Fine-tuning via QR Decomposition for Customized Generation","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-06T19:53:02.502214Z"},"links":{"citing_paper":"/paper/2507.04599"},"observation_digest":"sha256:6003fda24cf2e312a0378a935e0ea6ad36d6cd9e8d47e176c75fb37d698a95e6","observation_id":"a10551c6-0f6a-4771-a7e1-e3eb4818479f","resolution":{"observed_at":"2026-08-06T19:53:05.536296Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.12974","last_updated":"2024-02-21T14:04:30Z","snapshot_observed_at":"2026-08-06T01:12:23.608786Z","submitted_at":"2024-02-20T12:51:17Z","title":"Visual Style Prompting with Swapping Self-Attention","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.12974","snapshot_observed_at":"2026-08-06T19:53:02.627171Z","title":"Visual style prompting with swapping self- attention","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.04599","last_updated":"2025-07-24T09:12:08Z","snapshot_observed_at":"2026-08-06T19:41:54.718857Z","submitted_at":"2025-07-07T01:31:01Z","title":"QR-LoRA: Efficient and Disentangled Fine-tuning via QR Decomposition for Customized Generation","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-06T19:53:02.627171Z"},"links":{"cited_paper":"/paper/2402.12974","citing_paper":"/paper/2507.04599"},"observation_digest":"sha256:55fc928e8a34ddd762f2c9e461fce45959fb6d05d5e563708c2fb95d8d2082f2","observation_id":"13acff7f-ab3d-49fd-9ae4-f213ef8ceb1b","resolution":{"observed_at":"2026-08-06T19:53:02.627171Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:53:05.512323Z","title":"Elucidating the design space of diffusion-based generative models","venue":null,"work_id":"1900d266-b96d-4fca-b6c2-6cb2e7c713f8","year":2022},"citing_paper":{"arxiv_id":"2507.04599","last_updated":"2025-07-24T09:12:08Z","snapshot_observed_at":"2026-08-06T19:41:54.718857Z","submitted_at":"2025-07-07T01:31:01Z","title":"QR-LoRA: Efficient and Disentangled Fine-tuning via QR Decomposition for Customized Generation","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-06T19:53:02.742389Z"},"links":{"citing_paper":"/paper/2507.04599"},"observation_digest":"sha256:1fb9e6d038de30bcca07dfcca3aa78a66a244407d2bd6a20d37bbe262aea6daa","observation_id":"1bf968c1-7eb0-40e9-a732-851b547bf9ae","resolution":{"observed_at":"2026-08-06T19:53:05.519430Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:53:05.493874Z","title":"Understanding diffusion objectives as the elbo with simple data augmentation","venue":null,"work_id":"4086a9bb-75e7-432e-9df2-6545896b857d","year":2024},"citing_paper":{"arxiv_id":"2507.04599","last_updated":"2025-07-24T09:12:08Z","snapshot_observed_at":"2026-08-06T19:41:54.718857Z","submitted_at":"2025-07-07T01:31:01Z","title":"QR-LoRA: Efficient and Disentangled Fine-tuning via QR Decomposition for Customized Generation","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-06T19:53:02.854011Z"},"links":{"citing_paper":"/paper/2507.04599"},"observation_digest":"sha256:232cddea0b10c9ab5f3e937086980fa243e95c0d3a8e552ba0b9f4aca321704e","observation_id":"ba698d32-55c5-4383-89f8-80b087a1400f","resolution":{"observed_at":"2026-08-06T19:53:05.499664Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1412.6980","last_updated":"2017-01-30T01:27:54Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2014-12-22T13:54:29Z","title":"Adam: A Method for Stochastic Optimization","version":9},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1412.6980","snapshot_observed_at":"2026-08-06T19:53:02.938185Z","title":"Adam: A method for stochastic opti- mization","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2507.04599","last_updated":"2025-07-24T09:12:08Z","snapshot_observed_at":"2026-08-06T19:41:54.718857Z","submitted_at":"2025-07-07T01:31:01Z","title":"QR-LoRA: Efficient and Disentangled Fine-tuning via QR Decomposition for Customized Generation","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-06T19:53:02.938185Z"},"links":{"cited_paper":"/paper/1412.6980","citing_paper":"/paper/2507.04599"},"observation_digest":"sha256:09aaa60bb563bd8bb64b86d287bd090549017cc8aef182970880c9f67986bb42","observation_id":"29b310b3-727c-4975-bf05-1cd5826e8ac7","resolution":{"observed_at":"2026-08-06T19:53:02.938185Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:53:05.472150Z","title":"Multi-concept customization of text-to-image diffusion","venue":null,"work_id":"92fe8846-a00a-46b6-a31b-9a2f4370dbff","year":2023},"citing_paper":{"arxiv_id":"2507.04599","last_updated":"2025-07-24T09:12:08Z","snapshot_observed_at":"2026-08-06T19:41:54.718857Z","submitted_at":"2025-07-07T01:31:01Z","title":"QR-LoRA: Efficient and Disentangled Fine-tuning via QR Decomposition for Customized Generation","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-06T19:53:03.022422Z"},"links":{"citing_paper":"/paper/2507.04599"},"observation_digest":"sha256:efa094b04d4d2ceddc5d759545ca6ac560fea37032745088e0830f6e0e2d668c","observation_id":"f055f284-15c2-47de-81e9-72873002de1a","resolution":{"observed_at":"2026-08-06T19:53:05.480019Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:53:05.450349Z","title":null,"venue":null,"work_id":"3063c192-dcae-4345-83bd-4993dc239479","year":2023},"citing_paper":{"arxiv_id":"2507.04599","last_updated":"2025-07-24T09:12:08Z","snapshot_observed_at":"2026-08-06T19:41:54.718857Z","submitted_at":"2025-07-07T01:31:01Z","title":"QR-LoRA: Efficient and Disentangled Fine-tuning via QR Decomposition for Customized Generation","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-06T19:53:03.109774Z"},"links":{"citing_paper":"/paper/2507.04599"},"observation_digest":"sha256:20ab6b2003139c6ef775b52d4adb5c26322ebf8d791cbda51c88049a8423c215","observation_id":"8591db9d-dfc8-4944-9209-bf3d6155825d","resolution":{"observed_at":"2026-08-06T19:53:05.458029Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:53:05.432711Z","title":"Stylestudio: Text-driven style transfer with selective control of style elements","venue":null,"work_id":"ad983c53-2b9b-4d4b-bf1c-cccf261b39da","year":2025},"citing_paper":{"arxiv_id":"2507.04599","last_updated":"2025-07-24T09:12:08Z","snapshot_observed_at":"2026-08-06T19:41:54.718857Z","submitted_at":"2025-07-07T01:31:01Z","title":"QR-LoRA: Efficient and Disentangled Fine-tuning via QR Decomposition for Customized Generation","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-06T19:53:03.202307Z"},"links":{"citing_paper":"/paper/2507.04599"},"observation_digest":"sha256:8626129cda92d748070d83673c64f3e3472dd32dca64198959ec720d7917d650","observation_id":"8d495464-3f65-4e73-b42b-0dbaebbc7cb4","resolution":{"observed_at":"2026-08-06T19:53:05.438115Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2104.08691","last_updated":"2021-09-02T17:34:41Z","snapshot_observed_at":"2026-08-06T15:24:34.790850Z","submitted_at":"2021-04-18T03:19:26Z","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2104.08691","snapshot_observed_at":"2026-08-06T19:53:03.355221Z","title":"The power of scale for parameter-efficient prompt tuning.arXiv preprint arXiv:2104.08691, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.04599","last_updated":"2025-07-24T09:12:08Z","snapshot_observed_at":"2026-08-06T19:41:54.718857Z","submitted_at":"2025-07-07T01:31:01Z","title":"QR-LoRA: Efficient and Disentangled Fine-tuning via QR Decomposition for Customized Generation","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-06T19:53:03.355221Z"},"links":{"cited_paper":"/paper/2104.08691","citing_paper":"/paper/2507.04599"},"observation_digest":"sha256:a363b02e6034e5ad785ec5ce1e90d60bbb4c56c50166ec486a2821498205dea4","observation_id":"bdbb7b66-8533-4ce1-9b88-d5c861c1860d","resolution":{"observed_at":"2026-08-06T19:53:03.355221Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:53:05.416675Z","title":"Vb-lora: Extreme parameter efficient fine-tuning with vector banks","venue":null,"work_id":"7c01b4de-82fa-4b37-99ed-018c6287fef2","year":2024},"citing_paper":{"arxiv_id":"2507.04599","last_updated":"2025-07-24T09:12:08Z","snapshot_observed_at":"2026-08-06T19:41:54.718857Z","submitted_at":"2025-07-07T01:31:01Z","title":"QR-LoRA: Efficient and Disentangled Fine-tuning via QR Decomposition for Customized Generation","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-06T19:53:03.477795Z"},"links":{"citing_paper":"/paper/2507.04599"},"observation_digest":"sha256:28c72b2005d435f68b176804202435dad2947f93b480a9f18ac5c8cb7b7a5ba7","observation_id":"387e80fc-ebb1-4d57-afca-5e6064d1511e","resolution":{"observed_at":"2026-08-06T19:53:05.421655Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2405.19597","last_updated":"2024-05-30T01:27:43Z","snapshot_observed_at":"2026-07-31T09:18:53.492996Z","submitted_at":"2024-05-30T01:27:43Z","title":"SVFT: Parameter-Efficient Fine-Tuning with Singular Vectors","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.19597","snapshot_observed_at":"2026-08-06T19:53:03.648292Z","title":"Svft: Parameter-efficient fine-tuning with singular vectors","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.04599","last_updated":"2025-07-24T09:12:08Z","snapshot_observed_at":"2026-08-06T19:41:54.718857Z","submitted_at":"2025-07-07T01:31:01Z","title":"QR-LoRA: Efficient and Disentangled Fine-tuning via QR Decomposition for Customized Generation","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-06T19:53:03.648292Z"},"links":{"cited_paper":"/paper/2405.19597","citing_paper":"/paper/2507.04599"},"observation_digest":"sha256:f062828e730017241600b7a170e31f17f18eaa9d1419d5e78a0fbaad67309769","observation_id":"7d57f4b1-d466-40c7-8e08-2a1bbdbaa835","resolution":{"observed_at":"2026-08-06T19:53:03.648292Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2210.02747","last_updated":"2023-02-08T15:46:05Z","snapshot_observed_at":"2026-08-02T18:24:58.914589Z","submitted_at":"2022-10-06T08:32:20Z","title":"Flow Matching for Generative Modeling","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2210.02747","snapshot_observed_at":"2026-08-06T19:53:03.769216Z","title":"Flow matching for generative mod- eling","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.04599","last_updated":"2025-07-24T09:12:08Z","snapshot_observed_at":"2026-08-06T19:41:54.718857Z","submitted_at":"2025-07-07T01:31:01Z","title":"QR-LoRA: Efficient and Disentangled Fine-tuning via QR Decomposition for Customized Generation","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-06T19:53:03.769216Z"},"links":{"cited_paper":"/paper/2210.02747","citing_paper":"/paper/2507.04599"},"observation_digest":"sha256:f79db96ad1293512d8c0a4147ffffaf4779713d93281081746d15c3408361b60","observation_id":"57d130d4-029d-4397-b9f1-2a9ea0c87259","resolution":{"observed_at":"2026-08-06T19:53:03.769216Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.04465","last_updated":"2025-08-19T23:47:48Z","snapshot_observed_at":"2026-07-06T20:02:26.756229Z","submitted_at":"2024-12-05T18:59:50Z","title":"UnZipLoRA: Separating Content and Style from a Single Image","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.04465","snapshot_observed_at":"2026-08-06T19:53:03.871872Z","title":"Unziplora: Separating content and style from a single image","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.04599","last_updated":"2025-07-24T09:12:08Z","snapshot_observed_at":"2026-08-06T19:41:54.718857Z","submitted_at":"2025-07-07T01:31:01Z","title":"QR-LoRA: Efficient and Disentangled Fine-tuning via QR Decomposition for Customized Generation","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-06T19:53:03.871872Z"},"links":{"cited_paper":"/paper/2412.04465","citing_paper":"/paper/2507.04599"},"observation_digest":"sha256:b8ef7c34a563717e0677a675bbd747e379c9da71d08c97c5c39e317a8dbf02c8","observation_id":"49f2578c-a30c-4809-ba48-052151abb376","resolution":{"observed_at":"2026-08-06T19:53:03.871872Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2209.03003","last_updated":"2022-09-07T08:59:55Z","snapshot_observed_at":"2026-07-06T13:49:40.974495Z","submitted_at":"2022-09-07T08:59:55Z","title":"Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2209.03003","snapshot_observed_at":"2026-08-06T19:53:04.041428Z","title":"Flow straight and fast: Learning to generate and transfer data with rectified flow","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.04599","last_updated":"2025-07-24T09:12:08Z","snapshot_observed_at":"2026-08-06T19:41:54.718857Z","submitted_at":"2025-07-07T01:31:01Z","title":"QR-LoRA: Efficient and Disentangled Fine-tuning via QR Decomposition for Customized Generation","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-06T19:53:04.041428Z"},"links":{"cited_paper":"/paper/2209.03003","citing_paper":"/paper/2507.04599"},"observation_digest":"sha256:529fb298fb857feecd76148ab00c6a660b28400634a96994002949dee0a9a761","observation_id":"7d7b612f-3bdb-457a-9725-b01f81ddc2ca","resolution":{"observed_at":"2026-08-06T19:53:04.041428Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.00361","last_updated":"2024-08-10T05:26:24Z","snapshot_observed_at":"2026-07-06T18:08:04.815730Z","submitted_at":"2024-05-01T07:33:43Z","title":"AdaMoLE: Fine-Tuning Large Language Models with Adaptive Mixture of Low-Rank Adaptation Experts","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.00361","snapshot_observed_at":"2026-08-06T19:53:04.133258Z","title":"Adamole: Fine-tuning large lan- guage models with adaptive mixture of low-rank adaptation experts","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.04599","last_updated":"2025-07-24T09:12:08Z","snapshot_observed_at":"2026-08-06T19:41:54.718857Z","submitted_at":"2025-07-07T01:31:01Z","title":"QR-LoRA: Efficient and Disentangled Fine-tuning via QR Decomposition for Customized Generation","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-06T19:53:04.133258Z"},"links":{"cited_paper":"/paper/2405.00361","citing_paper":"/paper/2507.04599"},"observation_digest":"sha256:6376b4613075f237b0eeb279d3d4059b468b2631c1eb922d82ed49c2dd5768bf","observation_id":"c844aeeb-aa71-4810-8042-a3c5000156fa","resolution":{"observed_at":"2026-08-06T19:53:04.133258Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:53:05.398060Z","title":"Tuning-free long video generation via global-local collaborative diffu- sion, 2025","venue":null,"work_id":"6ee08066-23fc-471f-b3ad-78afa25974d2","year":2025},"citing_paper":{"arxiv_id":"2507.04599","last_updated":"2025-07-24T09:12:08Z","snapshot_observed_at":"2026-08-06T19:41:54.718857Z","submitted_at":"2025-07-07T01:31:01Z","title":"QR-LoRA: Efficient and Disentangled Fine-tuning via QR Decomposition for Customized Generation","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-06T19:53:04.139838Z"},"links":{"citing_paper":"/paper/2507.04599"},"observation_digest":"sha256:ef6058d50cf6833b313de635c55b69f9518daf52bd18df0a80b2d69457d444b4","observation_id":"d11ae02c-4ed9-4db6-a01f-b884ffe236a2","resolution":{"observed_at":"2026-08-06T19:53:05.403015Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:53:05.380797Z","title":"Adams bashforth moulton solver for inversion and editing in rectified flow, 2025","venue":null,"work_id":"c38aff5c-80da-437f-b6fc-b6a7f9c392ce","year":2025},"citing_paper":{"arxiv_id":"2507.04599","last_updated":"2025-07-24T09:12:08Z","snapshot_observed_at":"2026-08-06T19:41:54.718857Z","submitted_at":"2025-07-07T01:31:01Z","title":"QR-LoRA: Efficient and Disentangled Fine-tuning via QR Decomposition for Customized Generation","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-06T19:53:04.146694Z"},"links":{"citing_paper":"/paper/2507.04599"},"observation_digest":"sha256:b49466f7d45e2361a88f2cb208665ee6aff419e1024ec4647edb5b7832f08f10","observation_id":"84c188bf-08e8-4ef1-802d-8544bbf3b596","resolution":{"observed_at":"2026-08-06T19:53:05.386129Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:53:05.363804Z","title":"Pissa: Prin- cipal singular values and singular vectors adaptation of large language models","venue":null,"work_id":"760c16ba-33fe-4e26-9d6d-b31702e26ac4","year":2024},"citing_paper":{"arxiv_id":"2507.04599","last_updated":"2025-07-24T09:12:08Z","snapshot_observed_at":"2026-08-06T19:41:54.718857Z","submitted_at":"2025-07-07T01:31:01Z","title":"QR-LoRA: Efficient and Disentangled Fine-tuning via QR Decomposition for Customized Generation","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-06T19:53:04.151901Z"},"links":{"citing_paper":"/paper/2507.04599"},"observation_digest":"sha256:c33f922f852d3d4c90f1a7adf9bc373a879f475e2f91cf31fadc2a837d3a5a6e","observation_id":"84c9ca87-3d38-4304-8731-f00d3522e515","resolution":{"observed_at":"2026-08-06T19:53:05.368654Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:53:04.157181Z","title":"Null-text inversion for editing real im- ages using guided diffusion models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.04599","last_updated":"2025-07-24T09:12:08Z","snapshot_observed_at":"2026-08-06T19:41:54.718857Z","submitted_at":"2025-07-07T01:31:01Z","title":"QR-LoRA: Efficient and Disentangled Fine-tuning via QR Decomposition for Customized Generation","version":2},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-06T19:53:04.157181Z"},"links":{"citing_paper":"/paper/2507.04599"},"observation_digest":"sha256:192cfd15bd470ebd0790a3be9dadecd91bf1273d62d64d8a3d934580f5335c63","observation_id":"6e96b33b-ce85-45fb-858b-f94b70adda6d","resolution":{"observed_at":"2026-08-06T19:53:04.157181Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:53:05.336450Z","title":"T2i-adapter: Learning adapters to dig out more controllable ability for text-to-image diffusion models","venue":null,"work_id":"02cbcc3d-2ffb-46cf-a46b-542535ea45dd","year":2024},"citing_paper":{"arxiv_id":"2507.04599","last_updated":"2025-07-24T09:12:08Z","snapshot_observed_at":"2026-08-06T19:41:54.718857Z","submitted_at":"2025-07-07T01:31:01Z","title":"QR-LoRA: Efficient and Disentangled Fine-tuning via QR Decomposition for Customized Generation","version":2},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-06T19:53:04.161905Z"},"links":{"citing_paper":"/paper/2507.04599"},"observation_digest":"sha256:916d5038d31c914f2898f5596d63d4cdc3fe6656b50a2dfd3f48804c4c85e4cb","observation_id":"2126d501-d5dc-4086-89b6-e691c680938f","resolution":{"observed_at":"2026-08-06T19:53:05.341004Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:53:05.321371Z","title":"PACE: marrying the generalization of PArameter-efficient fine-tuning with con- sistency regularization","venue":null,"work_id":"f445cf41-d47c-467a-8479-3c8450cb88c2","year":2024},"citing_paper":{"arxiv_id":"2507.04599","last_updated":"2025-07-24T09:12:08Z","snapshot_observed_at":"2026-08-06T19:41:54.718857Z","submitted_at":"2025-07-07T01:31:01Z","title":"QR-LoRA: Efficient and Disentangled Fine-tuning via QR Decomposition for Customized Generation","version":2},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-06T19:53:04.166563Z"},"links":{"citing_paper":"/paper/2507.04599"},"observation_digest":"sha256:7627f71b325add1fb92eb57f321cf9636a383a5a541c25b66947238ed7f833c8","observation_id":"07f8b18e-596a-44d4-a2a9-807ad4ec63ae","resolution":{"observed_at":"2026-08-06T19:53:05.326280Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:53:05.305674Z","title":"Improved denoising diffusion probabilistic models","venue":null,"work_id":"3bef0570-6e39-447a-bf91-6e3fb57b59cd","year":2021},"citing_paper":{"arxiv_id":"2507.04599","last_updated":"2025-07-24T09:12:08Z","snapshot_observed_at":"2026-08-06T19:41:54.718857Z","submitted_at":"2025-07-07T01:31:01Z","title":"QR-LoRA: Efficient and Disentangled Fine-tuning via QR Decomposition for Customized Generation","version":2},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-06T19:53:04.172682Z"},"links":{"citing_paper":"/paper/2507.04599"},"observation_digest":"sha256:28d447a8eead8f4e6707fa246299c43d1c2171d42182de3290fc796371fa7445","observation_id":"1de085c5-93b2-482e-b5e3-fd505c5a54e7","resolution":{"observed_at":"2026-08-06T19:53:05.310581Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:53:05.291455Z","title":"Finding and editing multi-modal neurons in pre-trained transformers","venue":null,"work_id":"dbc3c238-c4f0-44c7-91d5-4e0698ebc6ee","year":2024},"citing_paper":{"arxiv_id":"2507.04599","last_updated":"2025-07-24T09:12:08Z","snapshot_observed_at":"2026-08-06T19:41:54.718857Z","submitted_at":"2025-07-07T01:31:01Z","title":"QR-LoRA: Efficient and Disentangled Fine-tuning via QR Decomposition for Customized Generation","version":2},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-06T19:53:04.181167Z"},"links":{"citing_paper":"/paper/2507.04599"},"observation_digest":"sha256:ea7f0ffdfe733c85350228cfdbd7cdb13eec7c8abfeac9a21d84ff91f291c69a","observation_id":"64346013-1958-49a2-bdb5-117c1d57d62f","resolution":{"observed_at":"2026-08-06T19:53:05.295850Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:53:05.276003Z","title":"Scalable diffusion models with transformers","venue":null,"work_id":"cff79d78-f347-4ff7-b21c-607e7a2320ce","year":2023},"citing_paper":{"arxiv_id":"2507.04599","last_updated":"2025-07-24T09:12:08Z","snapshot_observed_at":"2026-08-06T19:41:54.718857Z","submitted_at":"2025-07-07T01:31:01Z","title":"QR-LoRA: Efficient and Disentangled Fine-tuning via QR Decomposition for Customized Generation","version":2},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-06T19:53:04.186488Z"},"links":{"citing_paper":"/paper/2507.04599"},"observation_digest":"sha256:e5e693806d43a0781036a15e76ab3ee3affcdbde552716d5de2eb41aef542795","observation_id":"13f68b8c-a210-4522-baf1-de28a536b1d3","resolution":{"observed_at":"2026-08-06T19:53:05.280892Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:53:05.259912Z","title":"Orthogonal adaptation for modular customization of diffusion models","venue":null,"work_id":"017718ba-9d64-41d2-b747-737e97b4420b","year":2024},"citing_paper":{"arxiv_id":"2507.04599","last_updated":"2025-07-24T09:12:08Z","snapshot_observed_at":"2026-08-06T19:41:54.718857Z","submitted_at":"2025-07-07T01:31:01Z","title":"QR-LoRA: Efficient and Disentangled Fine-tuning via QR Decomposition for Customized Generation","version":2},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-06T19:53:04.194314Z"},"links":{"citing_paper":"/paper/2507.04599"},"observation_digest":"sha256:1985ef0c9c11265878d71869aa8d9179f1fc50ba2a20d458fafe00daac4f85d3","observation_id":"da1bdf10-0ca7-418a-80f9-91d11595337d","resolution":{"observed_at":"2026-08-06T19:53:05.264367Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2307.01952","last_updated":"2023-07-04T23:04:57Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-07-04T23:04:57Z","title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.01952","snapshot_observed_at":"2026-08-06T19:53:04.200314Z","title":"Sdxl: Improving latent diffusion mod- els for high-resolution image synthesis","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.04599","last_updated":"2025-07-24T09:12:08Z","snapshot_observed_at":"2026-08-06T19:41:54.718857Z","submitted_at":"2025-07-07T01:31:01Z","title":"QR-LoRA: Efficient and Disentangled Fine-tuning via QR Decomposition for Customized Generation","version":2},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-06T19:53:04.200314Z"},"links":{"cited_paper":"/paper/2307.01952","citing_paper":"/paper/2507.04599"},"observation_digest":"sha256:170b85ba66a0ab96f240b6a7dfd578cecaa413d9def2905b25e94869459a6469","observation_id":"a8ee56f5-5e2e-4f13-9049-8f0f3e586e33","resolution":{"observed_at":"2026-08-06T19:53:04.200314Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:53:05.244802Z","title":"Learning transferable visual models from natural language supervi- sion","venue":null,"work_id":"f7b7ba60-f04c-47a1-84c6-d7797ad12d5b","year":2021},"citing_paper":{"arxiv_id":"2507.04599","last_updated":"2025-07-24T09:12:08Z","snapshot_observed_at":"2026-08-06T19:41:54.718857Z","submitted_at":"2025-07-07T01:31:01Z","title":"QR-LoRA: Efficient and Disentangled Fine-tuning via QR Decomposition for Customized Generation","version":2},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-06T19:53:04.207957Z"},"links":{"citing_paper":"/paper/2507.04599"},"observation_digest":"sha256:c4c7282db863267a30e94706ef95aceff404c629bbdac65376531b33738d9c8c","observation_id":"c6665d04-b0a7-4f28-b93d-d0f725d7905a","resolution":{"observed_at":"2026-08-06T19:53:05.249630Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:53:05.229563Z","title":"Dreambooth3d: Subject-driven text-to-3d generation","venue":null,"work_id":"c7d2345b-8f9f-4a96-9821-0d0a52b5f109","year":2023},"citing_paper":{"arxiv_id":"2507.04599","last_updated":"2025-07-24T09:12:08Z","snapshot_observed_at":"2026-08-06T19:41:54.718857Z","submitted_at":"2025-07-07T01:31:01Z","title":"QR-LoRA: Efficient and Disentangled Fine-tuning via QR Decomposition for Customized Generation","version":2},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-06T19:53:04.213767Z"},"links":{"citing_paper":"/paper/2507.04599"},"observation_digest":"sha256:94fcba54b2a930d371b8109487d2d7cea6b9374f322ba0a4f7fa1020ea4a32ca","observation_id":"974cfd5c-d2c4-47f8-9adc-4890e4373387","resolution":{"observed_at":"2026-08-06T19:53:05.234295Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:53:05.212956Z","title":"High-resolution image syn- thesis with latent diffusion models","venue":null,"work_id":"9f06468b-6487-4c9b-98ee-53f4ff3b97b2","year":2022},"citing_paper":{"arxiv_id":"2507.04599","last_updated":"2025-07-24T09:12:08Z","snapshot_observed_at":"2026-08-06T19:41:54.718857Z","submitted_at":"2025-07-07T01:31:01Z","title":"QR-LoRA: Efficient and Disentangled Fine-tuning via QR Decomposition for Customized Generation","version":2},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-06T19:53:04.219317Z"},"links":{"citing_paper":"/paper/2507.04599"},"observation_digest":"sha256:1f645eded404056f00f35395b065f14d0452722dfb0f555f7b3d8030d4327fd7","observation_id":"2f8d51d4-c7e2-4c11-870d-51cda2940553","resolution":{"observed_at":"2026-08-06T19:53:05.218239Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:53:05.196025Z","title":"Dreambooth: Fine tuning text-to-image diffusion models for subject-driven generation","venue":null,"work_id":"f1e6bdbc-8281-4a33-85ca-27676ad9a15c","year":2023},"citing_paper":{"arxiv_id":"2507.04599","last_updated":"2025-07-24T09:12:08Z","snapshot_observed_at":"2026-08-06T19:41:54.718857Z","submitted_at":"2025-07-07T01:31:01Z","title":"QR-LoRA: Efficient and Disentangled Fine-tuning via QR Decomposition for Customized Generation","version":2},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-06T19:53:04.224178Z"},"links":{"citing_paper":"/paper/2507.04599"},"observation_digest":"sha256:ee356f97d86f1f3c894186d8cf97b653e33412cfadb8c07f4d552cf9e15d4a30","observation_id":"3b149572-743d-4557-8413-4b4c748c9691","resolution":{"observed_at":"2026-08-06T19:53:05.200790Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:53:05.179868Z","title":"Ziplora: Any subject in any style by effectively merging loras","venue":null,"work_id":"9504f2bc-d347-4181-aa3e-046b637d57d5","year":2025},"citing_paper":{"arxiv_id":"2507.04599","last_updated":"2025-07-24T09:12:08Z","snapshot_observed_at":"2026-08-06T19:41:54.718857Z","submitted_at":"2025-07-07T01:31:01Z","title":"QR-LoRA: Efficient and Disentangled Fine-tuning via QR Decomposition for Customized Generation","version":2},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-06T19:53:04.228813Z"},"links":{"citing_paper":"/paper/2507.04599"},"observation_digest":"sha256:d9fc54b95e7bb2877ad584bb2527a851ade50537d47bbe2c3be14353c9365e8e","observation_id":"db660adc-2e6c-440a-8dc1-844cc6ea95e9","resolution":{"observed_at":"2026-08-06T19:53:05.184997Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:53:05.163058Z","title":"Unleashing the power of task-specific directions in parameter efficient fine-tuning","venue":null,"work_id":"dce45219-290f-486f-a518-5975b9380ffb","year":2025},"citing_paper":{"arxiv_id":"2507.04599","last_updated":"2025-07-24T09:12:08Z","snapshot_observed_at":"2026-08-06T19:41:54.718857Z","submitted_at":"2025-07-07T01:31:01Z","title":"QR-LoRA: Efficient and Disentangled Fine-tuning via QR Decomposition for Customized Generation","version":2},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-06T19:53:04.234056Z"},"links":{"citing_paper":"/paper/2507.04599"},"observation_digest":"sha256:b5acffb824593400b683f5c98f36b3c78128d309edb2117638d4a3bde8d389c1","observation_id":"0f9f0cea-3907-492f-bfda-c4c86d535afe","resolution":{"observed_at":"2026-08-06T19:53:05.167648Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:53:05.145575Z","title":"Loraclr: Contrastive adaptation for customization of diffusion models","venue":null,"work_id":"4b506b2f-2e6a-4214-9752-a32d5db0944b","year":2025},"citing_paper":{"arxiv_id":"2507.04599","last_updated":"2025-07-24T09:12:08Z","snapshot_observed_at":"2026-08-06T19:41:54.718857Z","submitted_at":"2025-07-07T01:31:01Z","title":"QR-LoRA: Efficient and Disentangled Fine-tuning via QR Decomposition for Customized Generation","version":2},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-06T19:53:04.239218Z"},"links":{"citing_paper":"/paper/2507.04599"},"observation_digest":"sha256:5dabb394b76c834185798a70ccdad85b5ce91b0b195f58e20cfffc40d801b408","observation_id":"9175b758-4485-4af7-9931-ef3fa936b744","resolution":{"observed_at":"2026-08-06T19:53:05.150550Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:53:05.129919Z","title":"Styledrop: Text-to-image synthesis of any style","venue":null,"work_id":"a1cafae1-6dc8-45ea-82a2-04d9fdc34d06","year":2024},"citing_paper":{"arxiv_id":"2507.04599","last_updated":"2025-07-24T09:12:08Z","snapshot_observed_at":"2026-08-06T19:41:54.718857Z","submitted_at":"2025-07-07T01:31:01Z","title":"QR-LoRA: Efficient and Disentangled Fine-tuning via QR Decomposition for Customized Generation","version":2},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-06T19:53:04.243998Z"},"links":{"citing_paper":"/paper/2507.04599"},"observation_digest":"sha256:aa6ce42adb6d3baf2485a764ef5f344179bc12d467453627e4d0061263764a3a","observation_id":"e0f1280e-bd5c-4334-ba62-0b4844c4c128","resolution":{"observed_at":"2026-08-06T19:53:05.134473Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:53:04.248704Z","title":"Denois- ing diffusion implicit models","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.04599","last_updated":"2025-07-24T09:12:08Z","snapshot_observed_at":"2026-08-06T19:41:54.718857Z","submitted_at":"2025-07-07T01:31:01Z","title":"QR-LoRA: Efficient and Disentangled Fine-tuning via QR Decomposition for Customized Generation","version":2},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-06T19:53:04.248704Z"},"links":{"citing_paper":"/paper/2507.04599"},"observation_digest":"sha256:a966979cce3423a5e1842d2bc7cb9786f524e1e07f64889a273aa7823ac9ecf0","observation_id":"53986774-6b4f-4efe-966d-ec03e35a639e","resolution":{"observed_at":"2026-08-06T19:53:04.248704Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:53:04.255036Z","title":"Score-based generative modeling through stochastic differential equa- tions","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.04599","last_updated":"2025-07-24T09:12:08Z","snapshot_observed_at":"2026-08-06T19:41:54.718857Z","submitted_at":"2025-07-07T01:31:01Z","title":"QR-LoRA: Efficient and Disentangled Fine-tuning via QR Decomposition for Customized Generation","version":2},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-06T19:53:04.255036Z"},"links":{"citing_paper":"/paper/2507.04599"},"observation_digest":"sha256:dee1d4c8f2631a40bcaa8893fa2ba7ef8d79b0ca9f944aa8d7d77627f7707953","observation_id":"73b48815-f31b-4497-9583-0d8d4344cad2","resolution":{"observed_at":"2026-08-06T19:53:04.255036Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:53:04.260300Z","title":"Vl-adapter: Parameter-efficient transfer learning for vision-and-language tasks","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.04599","last_updated":"2025-07-24T09:12:08Z","snapshot_observed_at":"2026-08-06T19:41:54.718857Z","submitted_at":"2025-07-07T01:31:01Z","title":"QR-LoRA: Efficient and Disentangled Fine-tuning via QR Decomposition for Customized Generation","version":2},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-06T19:53:04.260300Z"},"links":{"citing_paper":"/paper/2507.04599"},"observation_digest":"sha256:a49099e978be012457cfae965167ac3a7beb9be08a97e8f7cee16fe68297bcac","observation_id":"8f162f8e-5b3d-462d-9a43-931bda2e554d","resolution":{"observed_at":"2026-08-06T19:53:04.260300Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:53:05.082089Z","title":null,"venue":null,"work_id":"40eed42e-5707-4b57-9c9e-df21b9c6f1ba","year":2024},"citing_paper":{"arxiv_id":"2507.04599","last_updated":"2025-07-24T09:12:08Z","snapshot_observed_at":"2026-08-06T19:41:54.718857Z","submitted_at":"2025-07-07T01:31:01Z","title":"QR-LoRA: Efficient and Disentangled Fine-tuning via QR Decomposition for Customized Generation","version":2},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-06T19:53:04.266526Z"},"links":{"citing_paper":"/paper/2507.04599"},"observation_digest":"sha256:b7aaa0957faf7e4dd89750e84435031a9acee66188b31f989d778a8a8e71cf04","observation_id":"f0ab6292-f8cc-4f7d-946c-5d6cd2ca21af","resolution":{"observed_at":"2026-08-06T19:53:05.087068Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:53:05.066123Z","title":"Hydralora: An asymmetric lora architec- ture for efficient fine-tuning","venue":null,"work_id":"6d87fd1e-6b79-4d23-b8cd-0b1244057265","year":2024},"citing_paper":{"arxiv_id":"2507.04599","last_updated":"2025-07-24T09:12:08Z","snapshot_observed_at":"2026-08-06T19:41:54.718857Z","submitted_at":"2025-07-07T01:31:01Z","title":"QR-LoRA: Efficient and Disentangled Fine-tuning via QR Decomposition for Customized Generation","version":2},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-06T19:53:04.272006Z"},"links":{"citing_paper":"/paper/2507.04599"},"observation_digest":"sha256:7b28a508a33dc73be18d56bce7c29cb6a43f1e3b2f65adcf1fdd27ddeacc12f1","observation_id":"146db99d-528a-4855-a4ed-c6fe8f21d339","resolution":{"observed_at":"2026-08-06T19:53:05.071382Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:53:04.281380Z","title":"Plug-and-play diffusion features for text-driven image-to-image translation","venue":null,"work_id":null,"year":1921},"citing_paper":{"arxiv_id":"2507.04599","last_updated":"2025-07-24T09:12:08Z","snapshot_observed_at":"2026-08-06T19:41:54.718857Z","submitted_at":"2025-07-07T01:31:01Z","title":"QR-LoRA: Efficient and Disentangled Fine-tuning via QR Decomposition for Customized Generation","version":2},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-06T19:53:04.281380Z"},"links":{"citing_paper":"/paper/2507.04599"},"observation_digest":"sha256:8a08b9a7a2743cd6ea7a50d55b3c33130346772fd02178c23f96acf9b269efa7","observation_id":"c71c9468-08ed-4957-876e-783709db2442","resolution":{"observed_at":"2026-08-06T19:53:04.281380Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:53:04.288202Z","title":"Attention is all you need","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2507.04599","last_updated":"2025-07-24T09:12:08Z","snapshot_observed_at":"2026-08-06T19:41:54.718857Z","submitted_at":"2025-07-07T01:31:01Z","title":"QR-LoRA: Efficient and Disentangled Fine-tuning via QR Decomposition for Customized Generation","version":2},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-06T19:53:04.288202Z"},"links":{"citing_paper":"/paper/2507.04599"},"observation_digest":"sha256:05095610e6381460f9250e00359ce8f91808849e2206e0ee55125823f13c8919","observation_id":"0d05f1b2-54aa-4cd6-a456-c8fa8697276a","resolution":{"observed_at":"2026-08-06T19:53:04.288202Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:53:05.027118Z","title":"Diffusers: State-of-the-art diffu- sion models","venue":null,"work_id":"76377f91-7472-423f-bf58-6228a729f701","year":2022},"citing_paper":{"arxiv_id":"2507.04599","last_updated":"2025-07-24T09:12:08Z","snapshot_observed_at":"2026-08-06T19:41:54.718857Z","submitted_at":"2025-07-07T01:31:01Z","title":"QR-LoRA: Efficient and Disentangled Fine-tuning via QR Decomposition for Customized Generation","version":2},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-06T19:53:04.294969Z"},"links":{"citing_paper":"/paper/2507.04599"},"observation_digest":"sha256:e19931538219492608ce4a28dd700c62d14e61dc933e98ff6ffb6af123fa1227","observation_id":"20aa414e-3004-44e5-9908-6a3ebef68df2","resolution":{"observed_at":"2026-08-06T19:53:05.031879Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2404.02733","last_updated":"2024-04-04T19:42:32Z","snapshot_observed_at":"2026-07-06T17:55:08.182604Z","submitted_at":"2024-04-03T13:34:09Z","title":"InstantStyle: Free Lunch towards Style-Preserving in Text-to-Image Generation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.02733","snapshot_observed_at":"2026-08-06T19:53:04.302164Z","title":"Instantstyle: Free lunch towards style- preserving in text-to-image generation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.04599","last_updated":"2025-07-24T09:12:08Z","snapshot_observed_at":"2026-08-06T19:41:54.718857Z","submitted_at":"2025-07-07T01:31:01Z","title":"QR-LoRA: Efficient and Disentangled Fine-tuning via QR Decomposition for Customized Generation","version":2},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-06T19:53:04.302164Z"},"links":{"cited_paper":"/paper/2404.02733","citing_paper":"/paper/2507.04599"},"observation_digest":"sha256:e04dc4b433cc7274c3cf12b5c403aa2b9d725261eefa6dcc390750524ee02e15","observation_id":"b6b6239e-f58d-4505-8cc1-687a878f19d8","resolution":{"observed_at":"2026-08-06T19:53:04.302164Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:53:04.308770Z","title":"Uncovering the disentanglement capability in text- to-image diffusion models","venue":null,"work_id":null,"year":1900},"citing_paper":{"arxiv_id":"2507.04599","last_updated":"2025-07-24T09:12:08Z","snapshot_observed_at":"2026-08-06T19:41:54.718857Z","submitted_at":"2025-07-07T01:31:01Z","title":"QR-LoRA: Efficient and Disentangled Fine-tuning via QR Decomposition for Customized Generation","version":2},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-06T19:53:04.308770Z"},"links":{"citing_paper":"/paper/2507.04599"},"observation_digest":"sha256:278b32c43a347ec3e6b41022cd36ef75b6463eee9f0f2fdf9371a21f817b14e0","observation_id":"27b46f78-86cb-4667-ae67-f325fe0352ca","resolution":{"observed_at":"2026-08-06T19:53:04.308770Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:53:04.997220Z","title":"Freeman, Fr ´edo Durand, and Song Han","venue":null,"work_id":"b2a30fd5-d78a-4488-9fbd-699da4517509","year":2024},"citing_paper":{"arxiv_id":"2507.04599","last_updated":"2025-07-24T09:12:08Z","snapshot_observed_at":"2026-08-06T19:41:54.718857Z","submitted_at":"2025-07-07T01:31:01Z","title":"QR-LoRA: Efficient and Disentangled Fine-tuning via QR Decomposition for Customized Generation","version":2},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-06T19:53:04.313850Z"},"links":{"citing_paper":"/paper/2507.04599"},"observation_digest":"sha256:7a62fc6c4a0ddc5c9b5102164d597e7e3fc9a29d909efd89fc1bc131e172a6e0","observation_id":"d85e0a8b-06ae-4eef-8453-7bb0bde40413","resolution":{"observed_at":"2026-08-06T19:53:05.003226Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2312.12148","last_updated":"2023-12-19T13:31:24Z","snapshot_observed_at":"2026-07-06T17:05:19.007669Z","submitted_at":"2023-12-19T13:31:24Z","title":"Parameter-Efficient Fine-Tuning Methods for Pretrained Language Models: A Critical Review and Assessment","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.12148","snapshot_observed_at":"2026-08-06T19:53:04.318614Z","title":"Parameter-efficient fine-tuning methods for pretrained language models: A critical review and assess- ment","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.04599","last_updated":"2025-07-24T09:12:08Z","snapshot_observed_at":"2026-08-06T19:41:54.718857Z","submitted_at":"2025-07-07T01:31:01Z","title":"QR-LoRA: Efficient and Disentangled Fine-tuning via QR Decomposition for Customized Generation","version":2},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-06T19:53:04.318614Z"},"links":{"cited_paper":"/paper/2312.12148","citing_paper":"/paper/2507.04599"},"observation_digest":"sha256:c2eab5a279f2d429c5279aa9b587ba1a7680665506fa14060b7a89189c754bdc","observation_id":"bc3982f3-a902-4b3d-a212-b6231ec366f9","resolution":{"observed_at":"2026-08-06T19:53:04.318614Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:53:04.978422Z","title":"End-to-end chinese landscape painting creation using generative adversarial networks","venue":null,"work_id":"df8d4a6e-ed49-4129-9ddc-06348e507b12","year":2021},"citing_paper":{"arxiv_id":"2507.04599","last_updated":"2025-07-24T09:12:08Z","snapshot_observed_at":"2026-08-06T19:41:54.718857Z","submitted_at":"2025-07-07T01:31:01Z","title":"QR-LoRA: Efficient and Disentangled Fine-tuning via QR Decomposition for Customized Generation","version":2},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-06T19:53:04.324326Z"},"links":{"citing_paper":"/paper/2507.04599"},"observation_digest":"sha256:f9584c2b0c9deaa40b38fc60f859ebdfa391db18c54450733692c9f333bc7016","observation_id":"55ab22dc-167e-4473-9063-39baf7e1017d","resolution":{"observed_at":"2026-08-06T19:53:04.983350Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2410.21299","last_updated":"2024-10-31T02:13:44Z","snapshot_observed_at":"2026-08-05T10:47:37.732103Z","submitted_at":"2024-10-16T07:13:09Z","title":"TV-3DG: Mastering Text-to-3D Customized Generation with Visual Prompt","version":2},"cited_work":{"arxiv_id":"2410.21299","doi":null,"metadata_source":"pith","pith_arxiv_id":"2410.21299","snapshot_observed_at":"2026-08-06T19:53:04.521125Z","title":"TV-3DG: Mastering Text-to-3D Customized Generation with Visual Prompt","venue":"cs.CV","work_id":"847084eb-0a85-43b3-a0e1-21abb6d642b0","year":2024},"citing_paper":{"arxiv_id":"2507.04599","last_updated":"2025-07-24T09:12:08Z","snapshot_observed_at":"2026-08-06T19:41:54.718857Z","submitted_at":"2025-07-07T01:31:01Z","title":"QR-LoRA: Efficient and Disentangled Fine-tuning via QR Decomposition for Customized Generation","version":2},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-06T19:53:04.330605Z"},"links":{"cited_paper":"/paper/2410.21299","citing_paper":"/paper/2507.04599"},"observation_digest":"sha256:a8f65af1162dd97339e09d50f54a52906d153b3574e252d9e59f553b2e59fa29","observation_id":"8ca12cd8-eaa5-4176-bf1f-4f222166749f","resolution":{"observed_at":"2026-08-06T19:53:04.528779Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:53:04.960552Z","title":"Zero-shot contrastive loss for text-guided diffusion image style transfer","venue":null,"work_id":"77c81cbc-7c1b-4eff-912c-91a92e488eb2","year":2023},"citing_paper":{"arxiv_id":"2507.04599","last_updated":"2025-07-24T09:12:08Z","snapshot_observed_at":"2026-08-06T19:41:54.718857Z","submitted_at":"2025-07-07T01:31:01Z","title":"QR-LoRA: Efficient and Disentangled Fine-tuning via QR Decomposition for Customized Generation","version":2},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-06T19:53:04.336284Z"},"links":{"citing_paper":"/paper/2507.04599"},"observation_digest":"sha256:5a5cf102d4f61f30c1fd197a473cb7abc6e938f2071e4995932dc87465934f20","observation_id":"49350794-6a72-4afd-a8dc-324142f487ce","resolution":{"observed_at":"2026-08-06T19:53:04.967204Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:53:04.942645Z","title":"Deconfounded video moment retrieval with causal intervention","venue":null,"work_id":"70339dd5-f936-4639-a3c8-283260615f88","year":2021},"citing_paper":{"arxiv_id":"2507.04599","last_updated":"2025-07-24T09:12:08Z","snapshot_observed_at":"2026-08-06T19:41:54.718857Z","submitted_at":"2025-07-07T01:31:01Z","title":"QR-LoRA: Efficient and Disentangled Fine-tuning via QR Decomposition for Customized Generation","version":2},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-06T19:53:04.343684Z"},"links":{"citing_paper":"/paper/2507.04599"},"observation_digest":"sha256:cc76eacbe07e613e354fc9d1bad14b088a53a7841171f5467c1bee738bbb815b","observation_id":"129c04a5-3254-440c-b4fd-59558d8f32e1","resolution":{"observed_at":"2026-08-06T19:53:04.948294Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:53:04.924570Z","title":"Video moment retrieval with cross-modal neural architecture search","venue":null,"work_id":"339dd16c-bc56-452b-8907-17958b5b9c3b","year":2022},"citing_paper":{"arxiv_id":"2507.04599","last_updated":"2025-07-24T09:12:08Z","snapshot_observed_at":"2026-08-06T19:41:54.718857Z","submitted_at":"2025-07-07T01:31:01Z","title":"QR-LoRA: Efficient and Disentangled Fine-tuning via QR Decomposition for Customized Generation","version":2},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-06T19:53:04.348796Z"},"links":{"citing_paper":"/paper/2507.04599"},"observation_digest":"sha256:ccb018e12e055f8c76ff34fb6aaec38ce5fb6f65b16fe7cd2a8dc2d88b6180fe","observation_id":"74189a8f-6404-4b30-8c01-9aa98623150f","resolution":{"observed_at":"2026-08-06T19:53:04.929877Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:53:04.906718Z","title":"Robust video question answer- ing via contrastive cross-modality representation learning","venue":null,"work_id":"0b840241-af52-4b8d-9f00-fb73d40be4c8","year":2024},"citing_paper":{"arxiv_id":"2507.04599","last_updated":"2025-07-24T09:12:08Z","snapshot_observed_at":"2026-08-06T19:41:54.718857Z","submitted_at":"2025-07-07T01:31:01Z","title":"QR-LoRA: Efficient and Disentangled Fine-tuning via QR Decomposition for Customized Generation","version":2},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-06T19:53:04.353669Z"},"links":{"citing_paper":"/paper/2507.04599"},"observation_digest":"sha256:7c2e2f078fcb9f4ded81dfedcbca7b67b29093411c3dc824d8848baf1a65b92c","observation_id":"e261ace9-2e00-484f-b234-45b19f71024a","resolution":{"observed_at":"2026-08-06T19:53:04.912945Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2408.06072","last_updated":"2025-03-26T08:33:10Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-08-12T11:47:11Z","title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.06072","snapshot_observed_at":"2026-08-06T19:53:04.358426Z","title":"Cogvideox: Text-to-video diffusion models with an expert transformer","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.04599","last_updated":"2025-07-24T09:12:08Z","snapshot_observed_at":"2026-08-06T19:41:54.718857Z","submitted_at":"2025-07-07T01:31:01Z","title":"QR-LoRA: Efficient and Disentangled Fine-tuning via QR Decomposition for Customized Generation","version":2},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-06T19:53:04.358426Z"},"links":{"cited_paper":"/paper/2408.06072","citing_paper":"/paper/2507.04599"},"observation_digest":"sha256:4ca63fb7f9a287645edda3c83fa8eb34238ff313ebba1c1069fc033b3162ef77","observation_id":"e856d3d0-c0a8-4184-820b-645e6098f318","resolution":{"observed_at":"2026-08-06T19:53:04.358426Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2308.06721","last_updated":"2023-08-13T08:34:51Z","snapshot_observed_at":"2026-07-06T16:05:39.158819Z","submitted_at":"2023-08-13T08:34:51Z","title":"IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.06721","snapshot_observed_at":"2026-08-06T19:53:04.364730Z","title":"Ip- adapter: Text compatible image prompt adapter for text-to- image diffusion models","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.04599","last_updated":"2025-07-24T09:12:08Z","snapshot_observed_at":"2026-08-06T19:41:54.718857Z","submitted_at":"2025-07-07T01:31:01Z","title":"QR-LoRA: Efficient and Disentangled Fine-tuning via QR Decomposition for Customized Generation","version":2},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-06T19:53:04.364730Z"},"links":{"cited_paper":"/paper/2308.06721","citing_paper":"/paper/2507.04599"},"observation_digest":"sha256:571e912acb9d14ffde357085c51ede35b6a875ba7ba4c3c224e1a2ab2668d2ef","observation_id":"6a425e35-7976-492b-9e46-79d66ca5e413","resolution":{"observed_at":"2026-08-06T19:53:04.364730Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:53:04.374462Z","title":"Adding conditional control to text-to-image diffusion models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.04599","last_updated":"2025-07-24T09:12:08Z","snapshot_observed_at":"2026-08-06T19:41:54.718857Z","submitted_at":"2025-07-07T01:31:01Z","title":"QR-LoRA: Efficient and Disentangled Fine-tuning via QR Decomposition for Customized Generation","version":2},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-06T19:53:04.374462Z"},"links":{"citing_paper":"/paper/2507.04599"},"observation_digest":"sha256:15da4bc232ccaa0b27c323d804a20cd2c6d559d046f1f9983452f1845bc8eacb","observation_id":"74874dd6-4f56-4f8a-84fe-c15ea45d1276","resolution":{"observed_at":"2026-08-06T19:53:04.374462Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.16843","last_updated":"2024-11-19T02:52:45Z","snapshot_observed_at":"2026-08-06T19:03:44.030685Z","submitted_at":"2024-02-26T18:59:18Z","title":"Multi-LoRA Composition for Image Generation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.16843","snapshot_observed_at":"2026-08-06T19:53:04.379364Z","title":"Multi-lora composition for image generation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.04599","last_updated":"2025-07-24T09:12:08Z","snapshot_observed_at":"2026-08-06T19:41:54.718857Z","submitted_at":"2025-07-07T01:31:01Z","title":"QR-LoRA: Efficient and Disentangled Fine-tuning via QR Decomposition for Customized Generation","version":2},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-06T19:53:04.379364Z"},"links":{"cited_paper":"/paper/2402.16843","citing_paper":"/paper/2507.04599"},"observation_digest":"sha256:a1cc7b6a2e1f4b7fa37d457f61ff2805d1c19b99df1ae6afcf777723a7b7631b","observation_id":"8c54b8e3-2952-4ea2-9b56-d0499a1fe1b7","resolution":{"observed_at":"2026-08-06T19:53:04.379364Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:53:04.875976Z","title":"Egotextvqa: Towards egocentric scene-text aware video question answering","venue":null,"work_id":"61431173-d09b-4e94-a8d8-f81814ccf086","year":2025},"citing_paper":{"arxiv_id":"2507.04599","last_updated":"2025-07-24T09:12:08Z","snapshot_observed_at":"2026-08-06T19:41:54.718857Z","submitted_at":"2025-07-07T01:31:01Z","title":"QR-LoRA: Efficient and Disentangled Fine-tuning via QR Decomposition for Customized Generation","version":2},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-06T19:53:04.389430Z"},"links":{"citing_paper":"/paper/2507.04599"},"observation_digest":"sha256:e117ea33f6d6d1b1531d18ae3863b739cdaa45b5394ca38143e845fc9c8e16ae","observation_id":"c5b8d3fa-5b21-4090-b7d1-e7b508fecf90","resolution":{"observed_at":"2026-08-06T19:53:04.881600Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:53:04.853333Z","title":"Cached multi-lora composition for multi- concept image generation","venue":null,"work_id":"3291cbb4-f66e-468c-8209-10c61554c4bd","year":2025},"citing_paper":{"arxiv_id":"2507.04599","last_updated":"2025-07-24T09:12:08Z","snapshot_observed_at":"2026-08-06T19:41:54.718857Z","submitted_at":"2025-07-07T01:31:01Z","title":"QR-LoRA: Efficient and Disentangled Fine-tuning via QR Decomposition for Customized Generation","version":2},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-06T19:53:04.394610Z"},"links":{"citing_paper":"/paper/2507.04599"},"observation_digest":"sha256:2ec8bc232425c181f9e2008a1790167bcb6314ea0bb9a2a3388328040244041e","observation_id":"7d953ae7-ae2c-455d-a2b9-e71420c22f17","resolution":{"observed_at":"2026-08-06T19:53:04.860447Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2507.04599","last_updated":"2025-07-24T09:12:08Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-06T19:41:54.718857Z","submitted_at":"2025-07-07T01:31:01Z","title":"QR-LoRA: Efficient and Disentangled Fine-tuning via QR Decomposition for Customized Generation"},"reference_resolution":{"displayed":76,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":32,"verified_exact":1,"verified_fuzzy":43},"total_outbound_references":76},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 76 of 76 outbound references and 0 inbound Pith citation observations for arXiv:2507.04599."}