{"as_of":"2026-08-19T08:07:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:e8eb3e913ecbd8aa97158d6b833bd6bded47b6f3e919383b0cca694e431e0ee7","coverage":[{"denominator":41,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":41,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-05T16:07:24.734639Z","state":"measured"},{"denominator":55,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":55,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-19T06:32:44.657259+00:00","state":"measured"},{"denominator":14,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":14,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-05T05:20:00.972643Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-07-04T13:39:50.260429Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2508.18966","last_updated":"2025-08-26T12:10:24Z","snapshot_observed_at":"2026-08-14T18:15:49.266112Z","submitted_at":"2025-08-26T12:10:24Z","title":"USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2508.18966","snapshot_observed_at":"2026-08-05T05:20:00.972643Z","title":"Uso: Unified style and subject-driven generation via disentangled and re- ward learning.arXiv preprint arXiv:2508.18966, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.05659","last_updated":"2025-09-06T09:29:48Z","snapshot_observed_at":"2026-08-16T09:38:58.652822Z","submitted_at":"2025-09-06T09:29:48Z","title":"EditIDv2: Editable ID Customization with Data-Lubricated ID Feature Integration for Text-to-Image Generation","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-05T05:20:00.972643Z"},"links":{"cited_paper":"/paper/2508.18966","citing_paper":"/paper/2509.05659"},"observation_digest":"sha256:550a4633c833be73cf629a2a743600e09b2efe07f6106b4b5bc8b69fc421490c","observation_id":"2bae9a30-e521-4019-a44a-b1fe7a86bbf7","resolution":{"observed_at":"2026-08-05T05:20:00.972643Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2508.18966","last_updated":"2025-08-26T12:10:24Z","snapshot_observed_at":"2026-08-14T18:15:49.266112Z","submitted_at":"2025-08-26T12:10:24Z","title":"USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2508.18966","snapshot_observed_at":"2026-08-04T06:47:09.609041Z","title":"Uso: Unified style and subject-driven generation via disentangled and re- ward learning.arXiv preprint arXiv:2508.18966, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2511.20635","last_updated":"2026-08-02T05:27:14Z","snapshot_observed_at":"2026-08-17T20:56:12.941886Z","submitted_at":"2025-11-25T18:54:16Z","title":"iMontage: Unified, Versatile, Highly Dynamic Many-to-many Image Generation","version":3},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-04T06:47:09.609041Z"},"links":{"cited_paper":"/paper/2508.18966","citing_paper":"/paper/2511.20635"},"observation_digest":"sha256:8d4014c5b9d629cbbbd7c24bf353a9e425657cd609d36da19c21b52d44c471c8","observation_id":"b453d790-b836-49af-bfa6-d49d5f7e63d5","resolution":{"observed_at":"2026-08-04T06:47:09.609041Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2508.18966","last_updated":"2025-08-26T12:10:24Z","snapshot_observed_at":"2026-08-14T18:15:49.266112Z","submitted_at":"2025-08-26T12:10:24Z","title":"USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning","version":1},"cited_work":{"arxiv_id":"2508.18966","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2508.18966","snapshot_observed_at":"2026-07-04T13:39:50.260429Z","title":"Uso: Unified style and subject-driven generation via disentangled and reward learning.arXivpreprint","venue":null,"work_id":"d7e22d09-fbcc-4ec6-ae6d-7df421c05d24","year":2025},"citing_paper":{"arxiv_id":"2512.12675","last_updated":"2026-06-09T11:29:25Z","snapshot_observed_at":"2026-08-13T03:23:47.681771Z","submitted_at":"2025-12-14T12:58:19Z","title":"Scone: Bridging Composition and Distinction in Subject-Driven Image Generation via Unified Understanding-Generation Modeling","version":2},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-05-16T22:39:32.955779Z"},"links":{"cited_paper":"/paper/2508.18966","citing_paper":"/paper/2512.12675"},"observation_digest":"sha256:9d58b125fa5374368bd9d31ac97d64469cf9514c0423aa543de8e5ad22537547","observation_id":"b23e37bb-3fe3-485a-a5ee-f839000fe832","resolution":{"observed_at":"2026-05-16T22:41:19.268627Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2508.18966","last_updated":"2025-08-26T12:10:24Z","snapshot_observed_at":"2026-08-14T18:15:49.266112Z","submitted_at":"2025-08-26T12:10:24Z","title":"USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2508.18966","snapshot_observed_at":"2026-08-03T16:37:06.916771Z","title":"Uso: Unified style and subject-driven generation via disentangled and re- ward learning.arXiv preprint arXiv:2508.18966, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2512.12675","last_updated":"2026-06-09T11:29:25Z","snapshot_observed_at":"2026-08-13T03:23:47.681771Z","submitted_at":"2025-12-14T12:58:19Z","title":"Scone: Bridging Composition and Distinction in Subject-Driven Image Generation via Unified Understanding-Generation Modeling","version":3},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-03T16:37:06.916771Z"},"links":{"cited_paper":"/paper/2508.18966","citing_paper":"/paper/2512.12675"},"observation_digest":"sha256:5a7928c03d02c08e90524c6741143383c16628c9ff7267158437ce1c01270fab","observation_id":"57de51e5-ae80-45f0-897e-310726028827","resolution":{"observed_at":"2026-08-03T16:37:06.916771Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2508.18966","last_updated":"2025-08-26T12:10:24Z","snapshot_observed_at":"2026-08-14T18:15:49.266112Z","submitted_at":"2025-08-26T12:10:24Z","title":"USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning","version":1},"cited_work":{"arxiv_id":"2508.18966","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2508.18966","snapshot_observed_at":"2026-07-04T13:39:50.260429Z","title":"Uso: Unified style and subject-driven generation via disentangled and reward learning.arXivpreprint","venue":null,"work_id":"d7e22d09-fbcc-4ec6-ae6d-7df421c05d24","year":2025},"citing_paper":{"arxiv_id":"2605.10127","last_updated":"2026-05-13T05:54:11Z","snapshot_observed_at":"2026-08-15T19:21:08.670726Z","submitted_at":"2026-05-11T07:40:03Z","title":"Fashion130K: An E-commerce Fashion Dataset for Outfit Generation with Unified Multi-modal Condition","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-05-12T03:56:43.640874Z"},"links":{"cited_paper":"/paper/2508.18966","citing_paper":"/paper/2605.10127"},"observation_digest":"sha256:fe44f18ea8e709cd227015eef0cf3f3fb49922eaa6caa2a6f727236f05e8c0c9","observation_id":"ad4de808-44e1-453e-83fb-174180e5dfba","resolution":{"observed_at":"2026-05-12T06:51:27.672889Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2508.18966","last_updated":"2025-08-26T12:10:24Z","snapshot_observed_at":"2026-08-14T18:15:49.266112Z","submitted_at":"2025-08-26T12:10:24Z","title":"USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning","version":1},"cited_work":{"arxiv_id":"2508.18966","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2508.18966","snapshot_observed_at":"2026-07-04T13:39:50.260429Z","title":"Uso: Unified style and subject-driven generation via disentangled and reward learning.arXivpreprint","venue":null,"work_id":"d7e22d09-fbcc-4ec6-ae6d-7df421c05d24","year":2025},"citing_paper":{"arxiv_id":"2605.10127","last_updated":"2026-05-13T05:54:11Z","snapshot_observed_at":"2026-08-15T19:21:08.670726Z","submitted_at":"2026-05-11T07:40:03Z","title":"Fashion130K: An E-commerce Fashion Dataset for Outfit Generation with Unified Multi-modal Condition","version":2},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-05-14T21:56:10.499014Z"},"links":{"cited_paper":"/paper/2508.18966","citing_paper":"/paper/2605.10127"},"observation_digest":"sha256:27b049e13295c2216ff6bb1f8eca43afe7f9e157d26b26affee94adce0b08e48","observation_id":"7d859d78-5852-48be-8ed0-398e0075acd3","resolution":{"observed_at":"2026-05-14T21:58:03.425154Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2508.18966","last_updated":"2025-08-26T12:10:24Z","snapshot_observed_at":"2026-08-14T18:15:49.266112Z","submitted_at":"2025-08-26T12:10:24Z","title":"USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning","version":1},"cited_work":{"arxiv_id":"2508.18966","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2508.18966","snapshot_observed_at":"2026-07-04T13:39:50.260429Z","title":"Uso: Unified style and subject-driven generation via disentangled and reward learning.arXivpreprint","venue":null,"work_id":"d7e22d09-fbcc-4ec6-ae6d-7df421c05d24","year":2025},"citing_paper":{"arxiv_id":"2605.12088","last_updated":"2026-05-13T15:41:37Z","snapshot_observed_at":"2026-08-12T23:50:23.640385Z","submitted_at":"2026-05-12T13:10:05Z","title":"UniCustom: Unified Visual Conditioning for Multi-Reference Image Generation","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-05-13T05:53:21.851578Z"},"links":{"cited_paper":"/paper/2508.18966","citing_paper":"/paper/2605.12088"},"observation_digest":"sha256:c5570b72eebd80a33c9adf76189e538df40dafe284b15a2ef29e4fd59c738beb","observation_id":"0f6c8606-c901-4891-946c-1ba2440d02bc","resolution":{"observed_at":"2026-05-13T06:02:23.928121Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2508.18966","last_updated":"2025-08-26T12:10:24Z","snapshot_observed_at":"2026-08-14T18:15:49.266112Z","submitted_at":"2025-08-26T12:10:24Z","title":"USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning","version":1},"cited_work":{"arxiv_id":"2508.18966","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2508.18966","snapshot_observed_at":"2026-07-04T13:39:50.260429Z","title":"Uso: Unified style and subject-driven generation via disentangled and reward learning.arXivpreprint","venue":null,"work_id":"d7e22d09-fbcc-4ec6-ae6d-7df421c05d24","year":2025},"citing_paper":{"arxiv_id":"2605.12088","last_updated":"2026-05-13T15:41:37Z","snapshot_observed_at":"2026-08-12T23:50:23.640385Z","submitted_at":"2026-05-12T13:10:05Z","title":"UniCustom: Unified Visual Conditioning for Multi-Reference Image Generation","version":2},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-05-14T22:00:01.349754Z"},"links":{"cited_paper":"/paper/2508.18966","citing_paper":"/paper/2605.12088"},"observation_digest":"sha256:5d4aa3d34d2f32b8528310c3bfde63c2cac023e9f16c9d2ed6944f39ef73a3b6","observation_id":"d4daa348-10eb-442e-b4ea-e7eb562c1253","resolution":{"observed_at":"2026-05-14T22:03:03.331618Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2508.18966","last_updated":"2025-08-26T12:10:24Z","snapshot_observed_at":"2026-08-14T18:15:49.266112Z","submitted_at":"2025-08-26T12:10:24Z","title":"USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning","version":1},"cited_work":{"arxiv_id":"2508.18966","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2508.18966","snapshot_observed_at":"2026-07-04T13:39:50.260429Z","title":"Uso: Unified style and subject-driven generation via disentangled and reward learning.arXivpreprint","venue":null,"work_id":"d7e22d09-fbcc-4ec6-ae6d-7df421c05d24","year":2025},"citing_paper":{"arxiv_id":"2605.18678","last_updated":"2026-05-20T11:14:23Z","snapshot_observed_at":"2026-08-16T10:04:17.107660Z","submitted_at":"2026-05-18T17:18:24Z","title":"Lance: Unified Multimodal Modeling by Multi-Task Synergy","version":1},"reference_index":127,"source":"pdf_text","source_observed_at":"2026-05-20T11:46:52.658984Z"},"links":{"cited_paper":"/paper/2508.18966","citing_paper":"/paper/2605.18678"},"observation_digest":"sha256:3dd5b07e2de42dee4cc089ca91a4bb18013d9a7121bb3fb392f06518c813226e","observation_id":"c199922f-5f35-4379-af42-98756c27559e","resolution":{"observed_at":"2026-05-20T11:48:15.001844Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2508.18966","last_updated":"2025-08-26T12:10:24Z","snapshot_observed_at":"2026-08-14T18:15:49.266112Z","submitted_at":"2025-08-26T12:10:24Z","title":"USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning","version":1},"cited_work":{"arxiv_id":"2508.18966","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2508.18966","snapshot_observed_at":"2026-07-04T13:39:50.260429Z","title":"Uso: Unified style and subject-driven generation via disentangled and reward learning.arXivpreprint","venue":null,"work_id":"d7e22d09-fbcc-4ec6-ae6d-7df421c05d24","year":2025},"citing_paper":{"arxiv_id":"2605.18678","last_updated":"2026-05-20T11:14:23Z","snapshot_observed_at":"2026-08-16T10:04:17.107660Z","submitted_at":"2026-05-18T17:18:24Z","title":"Lance: Unified Multimodal Modeling by Multi-Task Synergy","version":2},"reference_index":128,"source":"pdf_text","source_observed_at":"2026-05-21T07:56:34.034047Z"},"links":{"cited_paper":"/paper/2508.18966","citing_paper":"/paper/2605.18678"},"observation_digest":"sha256:62b8bbe752c340128b1403364e8fbfdca7d89e8f9501c3f3f9c35faa79c42eb7","observation_id":"2093b86d-e477-4408-9173-9a1f84c6a850","resolution":{"observed_at":"2026-05-21T07:59:50.549240Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2508.18966","last_updated":"2025-08-26T12:10:24Z","snapshot_observed_at":"2026-08-14T18:15:49.266112Z","submitted_at":"2025-08-26T12:10:24Z","title":"USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning","version":1},"cited_work":{"arxiv_id":"2508.18966","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2508.18966","snapshot_observed_at":"2026-07-04T13:39:50.260429Z","title":"Uso: Unified style and subject-driven generation via disentangled and reward learning.arXivpreprint","venue":null,"work_id":"d7e22d09-fbcc-4ec6-ae6d-7df421c05d24","year":2025},"citing_paper":{"arxiv_id":"2606.20506","last_updated":"2026-06-18T17:24:27Z","snapshot_observed_at":"2026-08-12T23:00:25.667979Z","submitted_at":"2026-06-18T17:24:27Z","title":"FreeStyle: Free Control of Style-Content Dual-Reference Generation from Community LoRA Mining","version":1},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-06-26T17:59:00.685869Z"},"links":{"cited_paper":"/paper/2508.18966","citing_paper":"/paper/2606.20506"},"observation_digest":"sha256:bdb1f7a42efd2e6b8ac21e9df81eccf89b01064230b41b3cf458fe546ceaa1d0","observation_id":"d4968a7d-7e35-4448-98a7-6da073e8cae5","resolution":{"observed_at":"2026-07-04T03:29:31.033751Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2508.18966","last_updated":"2025-08-26T12:10:24Z","snapshot_observed_at":"2026-08-14T18:15:49.266112Z","submitted_at":"2025-08-26T12:10:24Z","title":"USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning","version":1},"cited_work":{"arxiv_id":"2508.18966","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2508.18966","snapshot_observed_at":"2026-07-04T13:39:50.260429Z","title":"Uso: Unified style and subject-driven generation via disentangled and reward learning.arXivpreprint","venue":null,"work_id":"d7e22d09-fbcc-4ec6-ae6d-7df421c05d24","year":2025},"citing_paper":{"arxiv_id":"2606.26947","last_updated":"2026-06-25T12:21:13Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2026-06-25T12:21:13Z","title":"Scaling Multi-Reference Image Generation with Dynamic Reward Optimization","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-06-26T05:06:12.721122Z"},"links":{"cited_paper":"/paper/2508.18966","citing_paper":"/paper/2606.26947"},"observation_digest":"sha256:fd080ddabba7dad4cd3c51b060e747ac1a2c8189c50682111663c4a9f4cd22be","observation_id":"01f8e662-e1fd-4d72-92e5-1a9c12703774","resolution":{"observed_at":"2026-07-04T13:39:50.262085Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2508.18966","last_updated":"2025-08-26T12:10:24Z","snapshot_observed_at":"2026-08-14T18:15:49.266112Z","submitted_at":"2025-08-26T12:10:24Z","title":"USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2508.18966","snapshot_observed_at":"2026-07-31T06:53:04.357097Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.24721","last_updated":"2026-08-10T10:34:46Z","snapshot_observed_at":"2026-08-17T02:57:44.006999Z","submitted_at":"2026-07-27T17:55:21Z","title":"DreamStyle3D: Efficient 3D Stylized Asset Generation via Dual-Attention Disentanglement","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-07-31T06:53:04.357097Z"},"links":{"cited_paper":"/paper/2508.18966","citing_paper":"/paper/2607.24721"},"observation_digest":"sha256:875c737ddefa8a6d8b20f9c715860ef0883256bbb20b91bb9759d677198681cf","observation_id":"f14cd92c-223e-4886-a72d-1719f00fbffc","resolution":{"observed_at":"2026-07-31T06:53:04.357097Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2508.18966","last_updated":"2025-08-26T12:10:24Z","snapshot_observed_at":"2026-08-14T18:15:49.266112Z","submitted_at":"2025-08-26T12:10:24Z","title":"USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2508.18966","snapshot_observed_at":"2026-08-04T03:46:56.800614Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.24721","last_updated":"2026-08-10T10:34:46Z","snapshot_observed_at":"2026-08-17T02:57:44.006999Z","submitted_at":"2026-07-27T17:55:21Z","title":"DreamStyle3D: Efficient 3D Stylized Asset Generation via Dual-Attention Disentanglement","version":2},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-04T03:46:56.800614Z"},"links":{"cited_paper":"/paper/2508.18966","citing_paper":"/paper/2607.24721"},"observation_digest":"sha256:a79d157ecb7e028e2e1c994fcf51026f78180670f15662ccb35e4b4d731ea30e","observation_id":"34f53ee2-6478-48b0-9edb-b0b17869d422","resolution":{"observed_at":"2026-08-04T03:46:56.800614Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2508.18966/citation-record","integrity":"/paper/2508.18966/integrity","json":"/paper/2508.18966/citation-record.json","paper":"/paper/2508.18966"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2209.14491","last_updated":"2022-11-22T02:09:38Z","snapshot_observed_at":"2026-08-16T16:28:18.979152Z","submitted_at":"2022-09-29T00:57:28Z","title":"Re-Imagen: Retrieval-Augmented Text-to-Image Generator","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2209.14491","snapshot_observed_at":"2026-08-05T16:07:24.622496Z","title":"Re-imagen: Retrieval-augmented text-to- image generator","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2508.18966","last_updated":"2025-08-26T12:10:24Z","snapshot_observed_at":"2026-08-14T18:15:49.266112Z","submitted_at":"2025-08-26T12:10:24Z","title":"USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-05T16:07:24.622496Z"},"links":{"cited_paper":"/paper/2209.14491","citing_paper":"/paper/2508.18966"},"observation_digest":"sha256:7c26c9d6bac4565ee11194b9b7bdea98ccbaf44c2dc8c37fbbb466802ad22612","observation_id":"053fcd0d-de62-47b0-916d-a605db7f6902","resolution":{"observed_at":"2026-08-05T16:07:24.622496Z","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":"2026-08-05T16:07:24.626138Z","title":"Style injection in diffusion: A training-free approach for adapting large-scale diffusion models for style transfer","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.18966","last_updated":"2025-08-26T12:10:24Z","snapshot_observed_at":"2026-08-14T18:15:49.266112Z","submitted_at":"2025-08-26T12:10:24Z","title":"USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-05T16:07:24.626138Z"},"links":{"citing_paper":"/paper/2508.18966"},"observation_digest":"sha256:e168b32a97fa682a1a3bbdc6a370e3fb2a5a337f3cd83834db2a9550067cee61","observation_id":"146939ad-10e6-4892-b183-4b5939c1a2b2","resolution":{"observed_at":"2026-08-05T16:07:24.626138Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2505.14683","last_updated":"2025-07-27T11:45:16Z","snapshot_observed_at":"2026-08-17T01:11:44.872398Z","submitted_at":"2025-05-20T17:59:30Z","title":"Emerging Properties in Unified Multimodal Pretraining","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.14683","snapshot_observed_at":"2026-08-05T16:07:24.629170Z","title":"Emerging properties in unified multimodal pretraining.arXiv preprint arXiv:2505.14683, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2508.18966","last_updated":"2025-08-26T12:10:24Z","snapshot_observed_at":"2026-08-14T18:15:49.266112Z","submitted_at":"2025-08-26T12:10:24Z","title":"USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-05T16:07:24.629170Z"},"links":{"cited_paper":"/paper/2505.14683","citing_paper":"/paper/2508.18966"},"observation_digest":"sha256:13d188f5452a29f7e0cc51535d35bf470b1088e01650b0a098ace5b89103ee22","observation_id":"cac5d7ff-bd4b-44ed-bb72-37e7c1ad33b1","resolution":{"observed_at":"2026-08-05T16:07:24.629170Z","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":"2026-08-05T16:07:24.632577Z","title":"Scaling rectified flow transformers for high-resolution image synthesis","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.18966","last_updated":"2025-08-26T12:10:24Z","snapshot_observed_at":"2026-08-14T18:15:49.266112Z","submitted_at":"2025-08-26T12:10:24Z","title":"USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-05T16:07:24.632577Z"},"links":{"citing_paper":"/paper/2508.18966"},"observation_digest":"sha256:bf6a155433072753e079dd337fcb8e52f83cf2e32520e07da1f5c7f61faa0762","observation_id":"aa0d0b9e-0b1a-4750-b1b3-0ac961c6d402","resolution":{"observed_at":"2026-08-05T16:07:24.632577Z","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":"2026-08-05T16:07:25.164891Z","title":"Implicit style-content separation using b-lora","venue":null,"work_id":"383b7831-d794-40e9-94a1-ab070362b2e4","year":2024},"citing_paper":{"arxiv_id":"2508.18966","last_updated":"2025-08-26T12:10:24Z","snapshot_observed_at":"2026-08-14T18:15:49.266112Z","submitted_at":"2025-08-26T12:10:24Z","title":"USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-05T16:07:24.635590Z"},"links":{"citing_paper":"/paper/2508.18966"},"observation_digest":"sha256:0b153c1e0ceb4244c8ab1e104b7fbcd52238124369a8f62847caeccfeac67e29","observation_id":"8502f226-b290-41b4-acdf-2d2f3e63ccde","resolution":{"observed_at":"2026-08-05T16:07:25.168086Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-05T16:07:24.638386Z","title":"An image is worth one word: Personalizing text-to-image generation using textual inversion.arXiv preprint arXiv:2208.01618, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2508.18966","last_updated":"2025-08-26T12:10:24Z","snapshot_observed_at":"2026-08-14T18:15:49.266112Z","submitted_at":"2025-08-26T12:10:24Z","title":"USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-05T16:07:24.638386Z"},"links":{"cited_paper":"/paper/2208.01618","citing_paper":"/paper/2508.18966"},"observation_digest":"sha256:daf5788ad4114b01162b8b2c4d6a40c5fc2f1b3d2a6427a2eae75cf1f5f37a5b","observation_id":"b764b2bc-0676-4f46-a51f-cc4807099491","resolution":{"observed_at":"2026-08-05T16:07:24.638386Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.01414","last_updated":"2025-02-23T13:45:34Z","snapshot_observed_at":"2026-08-16T13:38:03.860850Z","submitted_at":"2024-07-01T16:05:18Z","title":"StyleShot: A Snapshot on Any Style","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.01414","snapshot_observed_at":"2026-08-05T16:07:24.641769Z","title":"Styleshot: A snapshot on any style.arXiv preprint arXiv:2407.01414, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.18966","last_updated":"2025-08-26T12:10:24Z","snapshot_observed_at":"2026-08-14T18:15:49.266112Z","submitted_at":"2025-08-26T12:10:24Z","title":"USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-05T16:07:24.641769Z"},"links":{"cited_paper":"/paper/2407.01414","citing_paper":"/paper/2508.18966"},"observation_digest":"sha256:564d221b60a38719565bec96f814a85cce47f0e4c2be63193ce0498ac52860e9","observation_id":"53caa1f1-ed43-4583-9ebc-95068f3f3791","resolution":{"observed_at":"2026-08-05T16:07:24.641769Z","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":"2026-08-17T18:04:53.578114Z","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":"2026-08-05T16:07:24.644627Z","title":"Lora: Low-rank adaptation of large language models.arXiv preprint arXiv:2106.09685, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2508.18966","last_updated":"2025-08-26T12:10:24Z","snapshot_observed_at":"2026-08-14T18:15:49.266112Z","submitted_at":"2025-08-26T12:10:24Z","title":"USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-05T16:07:24.644627Z"},"links":{"cited_paper":"/paper/2106.09685","citing_paper":"/paper/2508.18966"},"observation_digest":"sha256:3eca8d0edf442be58568d27350df3e17aa2c51901af68266c67b5e39b8942ee5","observation_id":"9900a882-fd17-468c-8124-56df99c1957e","resolution":{"observed_at":"2026-08-05T16:07:24.644627Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.23775","last_updated":"2024-11-05T06:41:27Z","snapshot_observed_at":"2026-08-17T23:31:59.305347Z","submitted_at":"2024-10-31T09:45:00Z","title":"In-Context LoRA for Diffusion Transformers","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.23775","snapshot_observed_at":"2026-08-05T16:07:24.647533Z","title":"In-context lora for diffusion transformers.arXiv preprint arXiv:2410.23775, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.18966","last_updated":"2025-08-26T12:10:24Z","snapshot_observed_at":"2026-08-14T18:15:49.266112Z","submitted_at":"2025-08-26T12:10:24Z","title":"USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-05T16:07:24.647533Z"},"links":{"cited_paper":"/paper/2410.23775","citing_paper":"/paper/2508.18966"},"observation_digest":"sha256:0297e5217cadb5aaa2688d5c167b4bcfe8f519c7df86f25f5ba9056fe9a97236","observation_id":"16c1e1df-944e-4dd9-bed4-f60cb9e1ded4","resolution":{"observed_at":"2026-08-05T16:07:24.647533Z","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":"2026-08-05T16:07:25.156280Z","title":"Realcustom: narrowing real text word for real-time open-domain text-to-image customization","venue":null,"work_id":"78cd2db1-9201-433a-bd87-437806bb4c30","year":2024},"citing_paper":{"arxiv_id":"2508.18966","last_updated":"2025-08-26T12:10:24Z","snapshot_observed_at":"2026-08-14T18:15:49.266112Z","submitted_at":"2025-08-26T12:10:24Z","title":"USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-05T16:07:24.650398Z"},"links":{"citing_paper":"/paper/2508.18966"},"observation_digest":"sha256:14dc1ff8c2ff7ff581deca333b5c32162346a9aad92f24eb0959613ef40be15b","observation_id":"5027f8ff-d35b-495a-bd9d-219738de35db","resolution":{"observed_at":"2026-08-05T16:07:25.159561Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-05T16:07:24.653086Z","title":"Arbitrary style transfer in real-time with adaptive instance normalization","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2508.18966","last_updated":"2025-08-26T12:10:24Z","snapshot_observed_at":"2026-08-14T18:15:49.266112Z","submitted_at":"2025-08-26T12:10:24Z","title":"USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-05T16:07:24.653086Z"},"links":{"citing_paper":"/paper/2508.18966"},"observation_digest":"sha256:4991c45423f22b0cfe3be2e20546540af6531aabb83fd0cbceabbe1754256788","observation_id":"c2e0acfd-0748-44df-97db-a65da35872ac","resolution":{"observed_at":"2026-08-05T16:07:24.653086Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.12974","last_updated":"2024-02-21T14:04:30Z","snapshot_observed_at":"2026-08-16T14:16:58.486297Z","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":"2026-08-05T16:07:24.655619Z","title":"Visual style prompting with swapping self-attention","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.18966","last_updated":"2025-08-26T12:10:24Z","snapshot_observed_at":"2026-08-14T18:15:49.266112Z","submitted_at":"2025-08-26T12:10:24Z","title":"USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-05T16:07:24.655619Z"},"links":{"cited_paper":"/paper/2402.12974","citing_paper":"/paper/2508.18966"},"observation_digest":"sha256:c4e640ee675080f02f98b79e32db1c4685ae281190ab5e64c14099ef918af8ff","observation_id":"3c39c659-d8f7-488b-a300-34739d2a7963","resolution":{"observed_at":"2026-08-05T16:07:24.655619Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.16418","last_updated":"2025-07-29T01:42:34Z","snapshot_observed_at":"2026-08-16T12:48:10.512851Z","submitted_at":"2025-03-20T17:59:34Z","title":"InfiniteYou: Flexible Photo Recrafting While Preserving Your Identity","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.16418","snapshot_observed_at":"2026-08-05T16:07:24.658469Z","title":"Infiniteyou: Flexible photo recrafting while preserving your identity.arXiv preprint arXiv:2503.16418, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2508.18966","last_updated":"2025-08-26T12:10:24Z","snapshot_observed_at":"2026-08-14T18:15:49.266112Z","submitted_at":"2025-08-26T12:10:24Z","title":"USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-05T16:07:24.658469Z"},"links":{"cited_paper":"/paper/2503.16418","citing_paper":"/paper/2508.18966"},"observation_digest":"sha256:95d708f9997a74389db6ee3c1e209b8269f892fe960c18ba4b86de8269ff37e2","observation_id":"60a6d8e9-92a7-4a64-a5f8-c28179ce2de8","resolution":{"observed_at":"2026-08-05T16:07:24.658469Z","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":"2026-08-05T16:07:24.661146Z","title":"Flux: Official inference repository for flux.1 models, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.18966","last_updated":"2025-08-26T12:10:24Z","snapshot_observed_at":"2026-08-14T18:15:49.266112Z","submitted_at":"2025-08-26T12:10:24Z","title":"USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-05T16:07:24.661146Z"},"links":{"citing_paper":"/paper/2508.18966"},"observation_digest":"sha256:6a2ce2c93f4a4028eaa1160215f9ff7b27e050573a60b55f73cd97719269060a","observation_id":"e7b04878-e630-431d-b924-5a6a8092eaab","resolution":{"observed_at":"2026-08-05T16:07:24.661146Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2506.15742","last_updated":"2025-06-24T05:31:03Z","snapshot_observed_at":"2026-08-14T01:48:52.921086Z","submitted_at":"2025-06-17T20:18:23Z","title":"FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.15742","snapshot_observed_at":"2026-08-05T16:07:24.663792Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2508.18966","last_updated":"2025-08-26T12:10:24Z","snapshot_observed_at":"2026-08-14T18:15:49.266112Z","submitted_at":"2025-08-26T12:10:24Z","title":"USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-05T16:07:24.663792Z"},"links":{"cited_paper":"/paper/2506.15742","citing_paper":"/paper/2508.18966"},"observation_digest":"sha256:016baef1f956930b61492eb31d437087447f773729d8d3c7740edd2c3ba16240","observation_id":"7ae95b26-2355-484f-bcf5-6ab4da9c122f","resolution":{"observed_at":"2026-08-05T16:07:24.663792Z","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":"2026-08-05T16:07:24.666586Z","title":"Stylestudio: Text-driven style transfer with selective control of style elements","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2508.18966","last_updated":"2025-08-26T12:10:24Z","snapshot_observed_at":"2026-08-14T18:15:49.266112Z","submitted_at":"2025-08-26T12:10:24Z","title":"USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-05T16:07:24.666586Z"},"links":{"citing_paper":"/paper/2508.18966"},"observation_digest":"sha256:894f10c489ff6ae6a14e2bc33c8f7e8ed722626ff53c5c76f25609110ceb0265","observation_id":"9cc647c7-a885-4534-b113-0fb7b5036a94","resolution":{"observed_at":"2026-08-05T16:07:24.666586Z","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":"2026-08-05T16:07:25.133954Z","title":"Blip-diffusion: Pre-trained subject representation for controllable text-to-image generation and editing.Advancesin Neural Information Processing Systems, 36:30146–30166, 2023","venue":null,"work_id":"a0c0d650-6370-4d4e-879a-04a2ec01d5bc","year":2023},"citing_paper":{"arxiv_id":"2508.18966","last_updated":"2025-08-26T12:10:24Z","snapshot_observed_at":"2026-08-14T18:15:49.266112Z","submitted_at":"2025-08-26T12:10:24Z","title":"USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-05T16:07:24.669116Z"},"links":{"citing_paper":"/paper/2508.18966"},"observation_digest":"sha256:ea460a02c45bc52602c8f0bb11d0bdf59e2de77f9ea4d5a52a35e73de82d0fa9","observation_id":"67884539-b12c-4c88-a8ed-4506d23b4040","resolution":{"observed_at":"2026-08-05T16:07:25.137453Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2503.10406","last_updated":"2025-07-20T08:44:35Z","snapshot_observed_at":"2026-08-18T05:49:59.336266Z","submitted_at":"2025-03-13T14:31:52Z","title":"RealGeneral: Unifying Visual Generation via Temporal In-Context Learning with Video Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.10406","snapshot_observed_at":"2026-08-05T16:07:24.671855Z","title":"Realgeneral: Unifying visual generation via temporal in-context learning with video models.arXiv preprint arXiv:2503.10406, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2508.18966","last_updated":"2025-08-26T12:10:24Z","snapshot_observed_at":"2026-08-14T18:15:49.266112Z","submitted_at":"2025-08-26T12:10:24Z","title":"USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-05T16:07:24.671855Z"},"links":{"cited_paper":"/paper/2503.10406","citing_paper":"/paper/2508.18966"},"observation_digest":"sha256:a362c10fbb3a88211a8b352f0b964d8300c33729a3c33b5e085ee8129f90fd05","observation_id":"4a4a020f-ba17-4b79-a6b0-b7c45ab3c53a","resolution":{"observed_at":"2026-08-05T16:07:24.671855Z","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":"2026-08-05T16:07:24.674807Z","title":"Realcustom++: Representing images as real-word for real-time customization.arXiv preprint arXiv:2408.09744, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.18966","last_updated":"2025-08-26T12:10:24Z","snapshot_observed_at":"2026-08-14T18:15:49.266112Z","submitted_at":"2025-08-26T12:10:24Z","title":"USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-05T16:07:24.674807Z"},"links":{"citing_paper":"/paper/2508.18966"},"observation_digest":"sha256:45a41375f43b9f160ed1fa7157378aab0e2cba6bc9fb9309ab6e9e3fc8ddd508","observation_id":"05b6b423-5388-4a5b-a8a1-347d26ef34d8","resolution":{"observed_at":"2026-08-05T16:07:24.674807Z","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":"2026-08-05T16:07:24.677294Z","title":"Dreamo: A unified framework for image customization.arXiv preprint arXiv:2504.16915, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2508.18966","last_updated":"2025-08-26T12:10:24Z","snapshot_observed_at":"2026-08-14T18:15:49.266112Z","submitted_at":"2025-08-26T12:10:24Z","title":"USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-05T16:07:24.677294Z"},"links":{"citing_paper":"/paper/2508.18966"},"observation_digest":"sha256:3d6140a1f512dda98b8de06c5f3dc4892fc60fcf3dbff499589b54e890f18bfa","observation_id":"519fa052-f033-4e3f-8224-0bbae670b014","resolution":{"observed_at":"2026-08-05T16:07:24.677294Z","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":"2026-08-05T16:07:25.124937Z","title":"SDXL: Improving latent diffusion models for high-resolution image synthesis","venue":null,"work_id":"5f6990f1-3eba-495f-965e-0f42c6a01223","year":2024},"citing_paper":{"arxiv_id":"2508.18966","last_updated":"2025-08-26T12:10:24Z","snapshot_observed_at":"2026-08-14T18:15:49.266112Z","submitted_at":"2025-08-26T12:10:24Z","title":"USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-05T16:07:24.679882Z"},"links":{"citing_paper":"/paper/2508.18966"},"observation_digest":"sha256:8a3a8ff18066d1bc1ef2e8473d2db1b6012f1ee82a19fd6a87b668b81cdf391d","observation_id":"f48189fd-172e-4f3e-a354-81cb301dc3d4","resolution":{"observed_at":"2026-08-05T16:07:25.128253Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2401.13974","last_updated":"2024-01-25T06:18:20Z","snapshot_observed_at":"2026-08-18T17:18:11.881569Z","submitted_at":"2024-01-25T06:18:20Z","title":"BootPIG: Bootstrapping Zero-shot Personalized Image Generation Capabilities in Pretrained Diffusion Models","version":1},"cited_work":{"arxiv_id":"2401.13974","doi":null,"metadata_source":"pith","pith_arxiv_id":"2401.13974","snapshot_observed_at":"2026-08-05T16:07:24.845089Z","title":"BootPIG: Bootstrapping Zero-shot Personalized Image Generation Capabilities in Pretrained Diffusion Models","venue":"cs.CV","work_id":"4b87b46e-a0f4-43c5-b3f0-6c4b23cd96e9","year":2024},"citing_paper":{"arxiv_id":"2508.18966","last_updated":"2025-08-26T12:10:24Z","snapshot_observed_at":"2026-08-14T18:15:49.266112Z","submitted_at":"2025-08-26T12:10:24Z","title":"USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-05T16:07:24.682387Z"},"links":{"cited_paper":"/paper/2401.13974","citing_paper":"/paper/2508.18966"},"observation_digest":"sha256:5a0e0f7d09cf3acd5b0a6755ccda8bb45fe7fa4f2a728eca0e2aa99b01fbed0e","observation_id":"b489951c-11de-4b91-bb91-b2de6e970432","resolution":{"observed_at":"2026-08-05T16:07:24.848310Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-05T16:07:24.685128Z","title":"Deadiff: An efficient stylization diffusion model with disentangled representations","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.18966","last_updated":"2025-08-26T12:10:24Z","snapshot_observed_at":"2026-08-14T18:15:49.266112Z","submitted_at":"2025-08-26T12:10:24Z","title":"USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-05T16:07:24.685128Z"},"links":{"citing_paper":"/paper/2508.18966"},"observation_digest":"sha256:fe2ecc797cb35e173c561f3ca2c365da00ee82d661d0911f0f417e8a3928583f","observation_id":"46c47027-63f6-4c6f-8666-a2d674ebba13","resolution":{"observed_at":"2026-08-05T16:07:24.685128Z","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":"2026-08-05T16:07:24.687669Z","title":"High-resolution image synthesis with latent diffusion models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2508.18966","last_updated":"2025-08-26T12:10:24Z","snapshot_observed_at":"2026-08-14T18:15:49.266112Z","submitted_at":"2025-08-26T12:10:24Z","title":"USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-05T16:07:24.687669Z"},"links":{"citing_paper":"/paper/2508.18966"},"observation_digest":"sha256:1fdeb520b627a9033cbe5b8e4677172e92934399e0bbb6012f3fcca2efdd2000","observation_id":"9aeababf-79bd-48a0-a132-72af3cdcc824","resolution":{"observed_at":"2026-08-05T16:07:24.687669Z","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":"2026-08-05T16:07:24.690145Z","title":"Dreambooth: Fine tuning text-to-image diffusion models for subject-driven generation","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.18966","last_updated":"2025-08-26T12:10:24Z","snapshot_observed_at":"2026-08-14T18:15:49.266112Z","submitted_at":"2025-08-26T12:10:24Z","title":"USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-05T16:07:24.690145Z"},"links":{"citing_paper":"/paper/2508.18966"},"observation_digest":"sha256:2228db5f3a656867c407937af05ba6a0b3a7739509fa9413af42d288d6888d00","observation_id":"7c63eb10-94e5-4e13-b913-8742fdc37524","resolution":{"observed_at":"2026-08-05T16:07:24.690145Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.01292","last_updated":"2024-04-01T17:58:30Z","snapshot_observed_at":"2026-08-16T14:04:34.113791Z","submitted_at":"2024-04-01T17:58:30Z","title":"Measuring Style Similarity in Diffusion Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.01292","snapshot_observed_at":"2026-08-05T16:07:24.692815Z","title":"Measuring style similarity in diffusion models.arXiv preprint arXiv:2404.01292, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.18966","last_updated":"2025-08-26T12:10:24Z","snapshot_observed_at":"2026-08-14T18:15:49.266112Z","submitted_at":"2025-08-26T12:10:24Z","title":"USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-05T16:07:24.692815Z"},"links":{"cited_paper":"/paper/2404.01292","citing_paper":"/paper/2508.18966"},"observation_digest":"sha256:c796d171890e2d798ae22c34a0586da64243e0f49829d03cfca90bacef909b28","observation_id":"8c76ada6-c7a6-4fe6-be94-6e90d8cfc7b5","resolution":{"observed_at":"2026-08-05T16:07:24.692815Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2411.15098","last_updated":"2025-07-07T17:33:23Z","snapshot_observed_at":"2026-08-12T17:19:10.028618Z","submitted_at":"2024-11-22T17:55:15Z","title":"OminiControl: Minimal and Universal Control for Diffusion Transformer","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.15098","snapshot_observed_at":"2026-08-05T16:07:24.695962Z","title":"Ominicontrol: Minimal and universal control for diffusion transformer.arXiv preprint arXiv:2411.15098, 3, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.18966","last_updated":"2025-08-26T12:10:24Z","snapshot_observed_at":"2026-08-14T18:15:49.266112Z","submitted_at":"2025-08-26T12:10:24Z","title":"USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-05T16:07:24.695962Z"},"links":{"cited_paper":"/paper/2411.15098","citing_paper":"/paper/2508.18966"},"observation_digest":"sha256:b6536de5f9b97283bfa10a040d9882c3e3cb1b61e516ee6e8dd18aceae85b25a","observation_id":"64c788c7-30cd-47d7-b930-2f59bb5fde59","resolution":{"observed_at":"2026-08-05T16:07:24.695962Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.02733","last_updated":"2024-04-04T19:42:32Z","snapshot_observed_at":"2026-08-16T14:03:57.454330Z","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":"2026-08-05T16:07:24.698825Z","title":"Instantstyle: Free lunch towards style-preserving in text-to-image generation.arXiv preprint arXiv:2404.02733, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.18966","last_updated":"2025-08-26T12:10:24Z","snapshot_observed_at":"2026-08-14T18:15:49.266112Z","submitted_at":"2025-08-26T12:10:24Z","title":"USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-05T16:07:24.698825Z"},"links":{"cited_paper":"/paper/2404.02733","citing_paper":"/paper/2508.18966"},"observation_digest":"sha256:e43b12502da3fce22f818dbf426c1604aa3ca62dfe8e2e1e47740ffa294a09dd","observation_id":"9c7298f5-de34-445c-b55c-ecca2a88ba55","resolution":{"observed_at":"2026-08-05T16:07:24.698825Z","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":"2026-08-05T16:07:24.701568Z","title":"Omnistyle: Filtering high quality style transfer data at scale","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2508.18966","last_updated":"2025-08-26T12:10:24Z","snapshot_observed_at":"2026-08-14T18:15:49.266112Z","submitted_at":"2025-08-26T12:10:24Z","title":"USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-05T16:07:24.701568Z"},"links":{"citing_paper":"/paper/2508.18966"},"observation_digest":"sha256:346a2cc2dc9af7340cc99fbc7c8336aba11eec48e90372c082f988a6647eebeb","observation_id":"593897fd-7a6c-4c3d-b121-bb1ff8c02e9c","resolution":{"observed_at":"2026-08-05T16:07:24.701568Z","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":"2026-08-05T16:07:25.097672Z","title":"Elite: Encoding visual concepts into textual embeddings for customized text-to-image generation","venue":null,"work_id":"78c2547a-4fdd-478e-8e7a-13e1d9a575dc","year":2023},"citing_paper":{"arxiv_id":"2508.18966","last_updated":"2025-08-26T12:10:24Z","snapshot_observed_at":"2026-08-14T18:15:49.266112Z","submitted_at":"2025-08-26T12:10:24Z","title":"USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-05T16:07:24.704297Z"},"links":{"citing_paper":"/paper/2508.18966"},"observation_digest":"sha256:8d381b65c0b0f81baafd4a9f25140d6009ed02d87b7987909b7e6cd34fc755ce","observation_id":"89f1fb6e-8929-498a-bd12-5477a50256b8","resolution":{"observed_at":"2026-08-05T16:07:25.100761Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2508.02324","last_updated":"2025-08-04T11:49:20Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-08-04T11:49:20Z","title":"Qwen-Image Technical Report","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2508.02324","snapshot_observed_at":"2026-08-05T16:07:24.706877Z","title":"Qwen-image technical report.arXiv preprint arXiv:2508.02324, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2508.18966","last_updated":"2025-08-26T12:10:24Z","snapshot_observed_at":"2026-08-14T18:15:49.266112Z","submitted_at":"2025-08-26T12:10:24Z","title":"USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-05T16:07:24.706877Z"},"links":{"cited_paper":"/paper/2508.02324","citing_paper":"/paper/2508.18966"},"observation_digest":"sha256:7065f6f276d635067e1de18df40f1645a4b94cbb5f0bf404ce5ab1a85a7fb96a","observation_id":"9773e485-df0d-4c4d-9e6f-ef5e1af2f9fa","resolution":{"observed_at":"2026-08-05T16:07:24.706877Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2506.18871","last_updated":"2026-04-21T17:32:47Z","snapshot_observed_at":"2026-08-18T21:48:45.801096Z","submitted_at":"2025-06-23T17:38:54Z","title":"OmniGen2: Towards Instruction-Aligned Multimodal Generation","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.18871","snapshot_observed_at":"2026-08-05T16:07:24.709716Z","title":"Omnigen2: Exploration to advanced multimodal generation.arXiv preprint arXiv:2506.18871, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2508.18966","last_updated":"2025-08-26T12:10:24Z","snapshot_observed_at":"2026-08-14T18:15:49.266112Z","submitted_at":"2025-08-26T12:10:24Z","title":"USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-05T16:07:24.709716Z"},"links":{"cited_paper":"/paper/2506.18871","citing_paper":"/paper/2508.18966"},"observation_digest":"sha256:0e69e7b83ce8a1f65281aa8c2d949a102e78192de0c0b6cab4e606b2f587aab9","observation_id":"bac6495b-4c04-458e-b93f-75e5e925cdec","resolution":{"observed_at":"2026-08-05T16:07:24.709716Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.20800","last_updated":"2024-12-30T08:47:25Z","snapshot_observed_at":"2026-08-18T15:16:02.109877Z","submitted_at":"2024-12-30T08:47:25Z","title":"VMix: Improving Text-to-Image Diffusion Model with Cross-Attention Mixing Control","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.20800","snapshot_observed_at":"2026-08-05T16:07:24.712500Z","title":"Vmix: Improving text-to-image diffusion model with cross-attention mixing control.arXiv preprint arXiv:2412.20800, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.18966","last_updated":"2025-08-26T12:10:24Z","snapshot_observed_at":"2026-08-14T18:15:49.266112Z","submitted_at":"2025-08-26T12:10:24Z","title":"USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-05T16:07:24.712500Z"},"links":{"cited_paper":"/paper/2412.20800","citing_paper":"/paper/2508.18966"},"observation_digest":"sha256:188b47a3257162d569192563dd56695825ff676229a87dedd548947b78851b77","observation_id":"aa3ec40c-2d58-4253-bce6-f92b281dfccb","resolution":{"observed_at":"2026-08-05T16:07:24.712500Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2504.02160","last_updated":"2025-04-02T22:20:21Z","snapshot_observed_at":"2026-08-16T19:13:10.251184Z","submitted_at":"2025-04-02T22:20:21Z","title":"Less-to-More Generalization: Unlocking More Controllability by In-Context Generation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2504.02160","snapshot_observed_at":"2026-08-05T16:07:24.715507Z","title":"Less-to-more generalization: Unlocking more controllability by in-context generation.arXiv preprint arXiv:2504.02160, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2508.18966","last_updated":"2025-08-26T12:10:24Z","snapshot_observed_at":"2026-08-14T18:15:49.266112Z","submitted_at":"2025-08-26T12:10:24Z","title":"USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-05T16:07:24.715507Z"},"links":{"cited_paper":"/paper/2504.02160","citing_paper":"/paper/2508.18966"},"observation_digest":"sha256:c915daccb1f983c7708562af76e8280d0834f610fcb0ae1b50d6b6471d19daf7","observation_id":"e6420c93-3141-4cb9-bc5a-1443315e3a4b","resolution":{"observed_at":"2026-08-05T16:07:24.715507Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2110.11323","last_updated":"2022-05-05T17:59:06Z","snapshot_observed_at":"2026-08-16T17:47:32.737413Z","submitted_at":"2021-10-21T17:55:16Z","title":"StyleAlign: Analysis and Applications of Aligned StyleGAN Models","version":2},"cited_work":{"arxiv_id":"2110.11323","doi":null,"metadata_source":"pith","pith_arxiv_id":"2110.11323","snapshot_observed_at":"2026-08-05T16:07:24.780295Z","title":"StyleAlign: Analysis and Applications of Aligned StyleGAN Models","venue":"cs.CV","work_id":"547e6c95-e314-4610-8625-6d4bfee6f9e1","year":2021},"citing_paper":{"arxiv_id":"2508.18966","last_updated":"2025-08-26T12:10:24Z","snapshot_observed_at":"2026-08-14T18:15:49.266112Z","submitted_at":"2025-08-26T12:10:24Z","title":"USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-05T16:07:24.718370Z"},"links":{"cited_paper":"/paper/2110.11323","citing_paper":"/paper/2508.18966"},"observation_digest":"sha256:375cff01454ee3948b56d21a2c3aef3526ede6685c8d58c6b1033711d7fe8788","observation_id":"c0ba062e-8ad5-4bbf-9789-47192892d7bd","resolution":{"observed_at":"2026-08-05T16:07:24.785290Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2409.11340","last_updated":"2024-11-21T14:09:12Z","snapshot_observed_at":"2026-08-16T13:17:46.268142Z","submitted_at":"2024-09-17T16:42:46Z","title":"OmniGen: Unified Image Generation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.11340","snapshot_observed_at":"2026-08-05T16:07:24.721187Z","title":"Omnigen: Unified image generation.arXiv preprint arXiv:2409.11340, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.18966","last_updated":"2025-08-26T12:10:24Z","snapshot_observed_at":"2026-08-14T18:15:49.266112Z","submitted_at":"2025-08-26T12:10:24Z","title":"USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-05T16:07:24.721187Z"},"links":{"cited_paper":"/paper/2409.11340","citing_paper":"/paper/2508.18966"},"observation_digest":"sha256:a4d5ccb0f29a4b5a20f259dec680f93032e707ef1c6f4120aa1cd738283228fd","observation_id":"e5fb1619-8d3f-4ddf-9ea9-597676a3823f","resolution":{"observed_at":"2026-08-05T16:07:24.721187Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2408.16766","last_updated":"2024-09-04T10:42:41Z","snapshot_observed_at":"2026-08-16T13:22:49.816942Z","submitted_at":"2024-08-29T17:59:30Z","title":"CSGO: Content-Style Composition in Text-to-Image Generation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.16766","snapshot_observed_at":"2026-08-05T16:07:24.723979Z","title":"Csgo: Content-style composition in text-to-image generation.arXiv preprint arXiv:2408.16766, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.18966","last_updated":"2025-08-26T12:10:24Z","snapshot_observed_at":"2026-08-14T18:15:49.266112Z","submitted_at":"2025-08-26T12:10:24Z","title":"USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-05T16:07:24.723979Z"},"links":{"cited_paper":"/paper/2408.16766","citing_paper":"/paper/2508.18966"},"observation_digest":"sha256:1e5ca098ce6297dd3e98d0b540ff29f4c3283b143c837bab1a55bc6abc7282a5","observation_id":"986665d2-9465-4df2-9dcb-8fd911f9237f","resolution":{"observed_at":"2026-08-05T16:07:24.723979Z","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":"2026-08-05T16:07:24.726795Z","title":"Imagereward: Learning and evaluating human preferences for text-to-image generation","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.18966","last_updated":"2025-08-26T12:10:24Z","snapshot_observed_at":"2026-08-14T18:15:49.266112Z","submitted_at":"2025-08-26T12:10:24Z","title":"USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-05T16:07:24.726795Z"},"links":{"citing_paper":"/paper/2508.18966"},"observation_digest":"sha256:8338ca150378f6927c81af13fa99a52f02375ab14a45eb46b847b1c02e049895","observation_id":"372c0820-4c5d-4f9d-9542-43aa5a310d52","resolution":{"observed_at":"2026-08-05T16:07:24.726795Z","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":"2026-08-05T16:07:24.729303Z","title":"Ip-adapter: Text compatible image prompt adapter for text-to-image diffusion models.arXiv preprint arXiv:2308.06721, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.18966","last_updated":"2025-08-26T12:10:24Z","snapshot_observed_at":"2026-08-14T18:15:49.266112Z","submitted_at":"2025-08-26T12:10:24Z","title":"USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-05T16:07:24.729303Z"},"links":{"cited_paper":"/paper/2308.06721","citing_paper":"/paper/2508.18966"},"observation_digest":"sha256:b891b5a686d958ef07f3fd2b305540bbfb83cfdf096d9842c8d674f441a71e3e","observation_id":"ea8d63d9-5230-4548-805a-7784c90b13bf","resolution":{"observed_at":"2026-08-05T16:07:24.729303Z","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":"2026-08-05T16:07:24.732133Z","title":"Sigmoid loss for language image pre-training","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.18966","last_updated":"2025-08-26T12:10:24Z","snapshot_observed_at":"2026-08-14T18:15:49.266112Z","submitted_at":"2025-08-26T12:10:24Z","title":"USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-05T16:07:24.732133Z"},"links":{"citing_paper":"/paper/2508.18966"},"observation_digest":"sha256:75e4cee17535df8435dc621f7a61ba1128e58d6c5620d01d7e38a92c3c2dba69","observation_id":"50544936-e08e-4044-98bb-f77254976b9a","resolution":{"observed_at":"2026-08-05T16:07:24.732133Z","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":"2026-08-05T16:07:25.079966Z","title":"The girl is riding a bike in the street","venue":null,"work_id":"2d8c84c1-77d0-442f-967c-b76bd5367d55","year":2024},"citing_paper":{"arxiv_id":"2508.18966","last_updated":"2025-08-26T12:10:24Z","snapshot_observed_at":"2026-08-14T18:15:49.266112Z","submitted_at":"2025-08-26T12:10:24Z","title":"USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-05T16:07:24.734639Z"},"links":{"citing_paper":"/paper/2508.18966"},"observation_digest":"sha256:e3c01efc64816decf0f821c693a104b2507db5f99a86d569d41437237481a03c","observation_id":"30f54828-8d8f-4760-b35c-f4703dd850c9","resolution":{"observed_at":"2026-08-05T16:07:25.083292Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2508.18966","last_updated":"2025-08-26T12:10:24Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-14T18:15:49.266112Z","submitted_at":"2025-08-26T12:10:24Z","title":"USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning"},"reference_resolution":{"displayed":41,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":33,"verified_exact":2,"verified_fuzzy":6},"total_outbound_references":41},"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":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"thesis":"As of 19 August 2026, this Paper Citation Record lists 41 of 41 outbound references and 14 inbound Pith citation observations for arXiv:2508.18966."}