{"as_of":"2026-08-09T05:53:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:83905aa698b631b685e5ceb0a3ad0f794908802101907d49722f7589a7f6a1fa","coverage":[{"denominator":57,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":57,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T20:46:25.184165Z","state":"measured"},{"denominator":58,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":58,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-06-28T10:47:33.349484Z","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":"2026-07-02T02:36:27.298802Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2507.01792","last_updated":"2025-07-02T15:16:59Z","snapshot_observed_at":"2026-08-08T19:57:19.375306Z","submitted_at":"2025-07-02T15:16:59Z","title":"FreeLoRA: Enabling Training-Free LoRA Fusion for Autoregressive Multi-Subject Personalization","version":1},"cited_work":{"arxiv_id":"2507.01792","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2507.01792","snapshot_observed_at":"2026-07-02T02:36:27.298802Z","title":"Freelora: Enabling training-free lora fusion for autoregressive multi- subject personalization.arXiv preprint arXiv:2507.01792,","venue":null,"work_id":"5b9eb887-7554-4a05-8515-002eaf80a329","year":null},"citing_paper":{"arxiv_id":"2606.03792","last_updated":"2026-06-02T15:42:09Z","snapshot_observed_at":"2026-07-06T23:44:00.144689Z","submitted_at":"2026-06-02T15:42:09Z","title":"Training-Free Multi-Concept LoRA Composition with Prompt-Aware Weighting","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-06-28T10:47:33.349484Z"},"links":{"cited_paper":"/paper/2507.01792","citing_paper":"/paper/2606.03792"},"observation_digest":"sha256:40d7bcf07f0331390b3e74ca303ab0626bfaf99f78eba9f8886cefd9337a8832","observation_id":"9c232075-9860-4f4f-bd18-c1f7400c07a5","resolution":{"observed_at":"2026-07-02T02:36:27.300440Z","resolver_source":"arxiv_id","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"}}],"links":{"evidence":"/evidence","html":"/paper/2507.01792/citation-record","integrity":"/paper/2507.01792/integrity","json":"/paper/2507.01792/citation-record.json","paper":"/paper/2507.01792"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T20:46:25.028880Z","title":"Emerging properties in self-supervised vision transformers","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.01792","last_updated":"2025-07-02T15:16:59Z","snapshot_observed_at":"2026-08-08T19:57:19.375306Z","submitted_at":"2025-07-02T15:16:59Z","title":"FreeLoRA: Enabling Training-Free LoRA Fusion for Autoregressive Multi-Subject Personalization","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-06T20:46:25.028880Z"},"links":{"citing_paper":"/paper/2507.01792"},"observation_digest":"sha256:484e786515d5aa327cb670a994c15015dcc136d8fe8f6b3233682e275b4d2a54","observation_id":"167cb2c2-ee55-4b97-ae9d-cd4272c8e5dd","resolution":{"observed_at":"2026-08-06T20:46:25.028880Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2209.14491","last_updated":"2022-11-22T02:09:38Z","snapshot_observed_at":"2026-08-03T22:24:49.500281Z","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":"2026-08-06T20:46:25.032495Z","title":"Re-imagen: Retrieval- augmented text-to-image generator","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.01792","last_updated":"2025-07-02T15:16:59Z","snapshot_observed_at":"2026-08-08T19:57:19.375306Z","submitted_at":"2025-07-02T15:16:59Z","title":"FreeLoRA: Enabling Training-Free LoRA Fusion for Autoregressive Multi-Subject Personalization","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-06T20:46:25.032495Z"},"links":{"cited_paper":"/paper/2209.14491","citing_paper":"/paper/2507.01792"},"observation_digest":"sha256:e3881cd383cb6c636c9ef8e280d478ee10adbd8bb998f4f2069602134a4fb1a7","observation_id":"d054a812-3821-4f3a-bce9-b399a73db620","resolution":{"observed_at":"2026-08-06T20:46:25.032495Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2504.02612","last_updated":"2025-07-30T13:15:26Z","snapshot_observed_at":"2026-08-07T16:11:25.924032Z","submitted_at":"2025-04-03T14:12:55Z","title":"Fine-Tuning Visual Autoregressive Models for Subject-Driven Generation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2504.02612","snapshot_observed_at":"2026-08-06T20:46:25.035597Z","title":"Fine-tuning visual autoregressive models for subject-driven generation","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2507.01792","last_updated":"2025-07-02T15:16:59Z","snapshot_observed_at":"2026-08-08T19:57:19.375306Z","submitted_at":"2025-07-02T15:16:59Z","title":"FreeLoRA: Enabling Training-Free LoRA Fusion for Autoregressive Multi-Subject Personalization","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-06T20:46:25.035597Z"},"links":{"cited_paper":"/paper/2504.02612","citing_paper":"/paper/2507.01792"},"observation_digest":"sha256:bdea586816d5ef9b359bfd11b6d06984ed4c57ac490521e1594fd78731677e9d","observation_id":"31ad391d-7f20-4207-b166-ed9e0f0c5353","resolution":{"observed_at":"2026-08-06T20:46:25.035597Z","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":"2026-08-06T20:46:25.039451Z","title":"Diffusion models beat gans on image synthesis","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.01792","last_updated":"2025-07-02T15:16:59Z","snapshot_observed_at":"2026-08-08T19:57:19.375306Z","submitted_at":"2025-07-02T15:16:59Z","title":"FreeLoRA: Enabling Training-Free LoRA Fusion for Autoregressive Multi-Subject Personalization","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-06T20:46:25.039451Z"},"links":{"citing_paper":"/paper/2507.01792"},"observation_digest":"sha256:6c2d36f96d788dbb3da0b84aba864634ff3379877de74b54255d7eab298372a1","observation_id":"a73352d4-ad94-4a69-a9ad-4eba3d790769","resolution":{"observed_at":"2026-08-06T20:46:25.039451Z","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":"2026-08-06T20:46:25.042581Z","title":"Freecustom: Tuning-free customized image generation for multi-concept composition","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.01792","last_updated":"2025-07-02T15:16:59Z","snapshot_observed_at":"2026-08-08T19:57:19.375306Z","submitted_at":"2025-07-02T15:16:59Z","title":"FreeLoRA: Enabling Training-Free LoRA Fusion for Autoregressive Multi-Subject Personalization","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-06T20:46:25.042581Z"},"links":{"citing_paper":"/paper/2507.01792"},"observation_digest":"sha256:7474ae99076215648ad0aeddb9dcad86f62366ed40694f8d89a1db4df37dd464","observation_id":"28332dc2-d5c0-40be-b0e7-8cd7f1bf6fb5","resolution":{"observed_at":"2026-08-06T20:46:25.042581Z","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":"2026-08-06T20:46:25.938400Z","title":"How to continually adapt text-to-image diffusion models for flexible customization? Advances in Neural Information Processing Systems, 37:130057– 130083, 2024","venue":null,"work_id":"bfab7a97-d40c-479d-b392-06e52be54968","year":2024},"citing_paper":{"arxiv_id":"2507.01792","last_updated":"2025-07-02T15:16:59Z","snapshot_observed_at":"2026-08-08T19:57:19.375306Z","submitted_at":"2025-07-02T15:16:59Z","title":"FreeLoRA: Enabling Training-Free LoRA Fusion for Autoregressive Multi-Subject Personalization","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-06T20:46:25.045369Z"},"links":{"citing_paper":"/paper/2507.01792"},"observation_digest":"sha256:fbf82a780c8fd5573bd3dc2dc60f3c2000a1b58f65e285a970d5f55d4e338dbb","observation_id":"353f6925-f21c-457e-8976-4fc8c8e9418d","resolution":{"observed_at":"2026-08-06T20:46:25.941830Z","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":"2503.12590","last_updated":"2025-03-16T17:51:16Z","snapshot_observed_at":"2026-08-09T01:55:20.435340Z","submitted_at":"2025-03-16T17:51:16Z","title":"Personalize Anything for Free with Diffusion Transformer","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.12590","snapshot_observed_at":"2026-08-06T20:46:25.049029Z","title":"Personalize anything for free with diffusion transformer","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2507.01792","last_updated":"2025-07-02T15:16:59Z","snapshot_observed_at":"2026-08-08T19:57:19.375306Z","submitted_at":"2025-07-02T15:16:59Z","title":"FreeLoRA: Enabling Training-Free LoRA Fusion for Autoregressive Multi-Subject Personalization","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-06T20:46:25.049029Z"},"links":{"cited_paper":"/paper/2503.12590","citing_paper":"/paper/2507.01792"},"observation_digest":"sha256:4de671ee30aec8bfcc702898d7fc6993330f83652e2213c330dacbc479f016a3","observation_id":"86bd7420-c899-4e96-9b17-393579d95aef","resolution":{"observed_at":"2026-08-06T20:46:25.049029Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"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":"2026-08-06T20:46:25.051723Z","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":"2507.01792","last_updated":"2025-07-02T15:16:59Z","snapshot_observed_at":"2026-08-08T19:57:19.375306Z","submitted_at":"2025-07-02T15:16:59Z","title":"FreeLoRA: Enabling Training-Free LoRA Fusion for Autoregressive Multi-Subject Personalization","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-06T20:46:25.051723Z"},"links":{"cited_paper":"/paper/2208.01618","citing_paper":"/paper/2507.01792"},"observation_digest":"sha256:465e3f5e0597bafc8268da32e26553d095fe332c542a3712f7e547dcfbfe685f","observation_id":"92e56349-3952-4fad-b58d-02baae021b17","resolution":{"observed_at":"2026-08-06T20:46:25.051723Z","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":"2026-08-06T20:46:25.929305Z","title":"Mix-of-show: Decentralized low-rank adaptation for multi-concept customization of diffusion models","venue":null,"work_id":"3a0ce255-10fd-4c37-9632-675de0f4b4ed","year":2023},"citing_paper":{"arxiv_id":"2507.01792","last_updated":"2025-07-02T15:16:59Z","snapshot_observed_at":"2026-08-08T19:57:19.375306Z","submitted_at":"2025-07-02T15:16:59Z","title":"FreeLoRA: Enabling Training-Free LoRA Fusion for Autoregressive Multi-Subject Personalization","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-06T20:46:25.054541Z"},"links":{"citing_paper":"/paper/2507.01792"},"observation_digest":"sha256:e50069bcb6742f925b9438bd71e34110a2eb81f1ebf3e48eb20552485bb1f5b0","observation_id":"31f846a3-0f91-4d1a-bf93-2fe5372e71d4","resolution":{"observed_at":"2026-08-06T20:46:25.932205Z","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":"2412.04431","last_updated":"2025-06-17T15:32:20Z","snapshot_observed_at":"2026-08-07T20:34:58.400387Z","submitted_at":"2024-12-05T18:53:02Z","title":"Infinity: Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesis","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.04431","snapshot_observed_at":"2026-08-06T20:46:25.057308Z","title":"Infinity: Scaling bitwise autoregressive modeling for high-resolution image synthesis","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.01792","last_updated":"2025-07-02T15:16:59Z","snapshot_observed_at":"2026-08-08T19:57:19.375306Z","submitted_at":"2025-07-02T15:16:59Z","title":"FreeLoRA: Enabling Training-Free LoRA Fusion for Autoregressive Multi-Subject Personalization","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-06T20:46:25.057308Z"},"links":{"cited_paper":"/paper/2412.04431","citing_paper":"/paper/2507.01792"},"observation_digest":"sha256:81a7a44aefdbc9838d05c4f3c4ed3f0a71bfe0f84c45f2d0fba24b320c6a6088","observation_id":"d132c8c1-a64a-4d34-9b98-fe717b4f3f61","resolution":{"observed_at":"2026-08-06T20:46:25.057308Z","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":"2026-08-06T20:46:25.920085Z","title":null,"venue":null,"work_id":"7872962b-eeab-4924-9eae-1310fae328fa","year":2023},"citing_paper":{"arxiv_id":"2507.01792","last_updated":"2025-07-02T15:16:59Z","snapshot_observed_at":"2026-08-08T19:57:19.375306Z","submitted_at":"2025-07-02T15:16:59Z","title":"FreeLoRA: Enabling Training-Free LoRA Fusion for Autoregressive Multi-Subject Personalization","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-06T20:46:25.060286Z"},"links":{"citing_paper":"/paper/2507.01792"},"observation_digest":"sha256:b0a56980f47d29b7a40861746e5d8aae81fa586d2660df58f92364e82b5a0555","observation_id":"3daeb8a1-c6b2-420d-b9ae-d9249e1a1eb6","resolution":{"observed_at":"2026-08-06T20:46:25.922772Z","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":{"arxiv_id":"2501.09503","last_updated":"2025-05-01T09:16:20Z","snapshot_observed_at":"2026-07-06T20:21:55.366596Z","submitted_at":"2025-01-16T12:28:39Z","title":"AnyStory: Towards Unified Single and Multiple Subject Personalization in Text-to-Image Generation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.09503","snapshot_observed_at":"2026-08-06T20:46:25.063313Z","title":"Anys- tory: Towards unified single and multiple subject personalization in text-to-image generation","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2507.01792","last_updated":"2025-07-02T15:16:59Z","snapshot_observed_at":"2026-08-08T19:57:19.375306Z","submitted_at":"2025-07-02T15:16:59Z","title":"FreeLoRA: Enabling Training-Free LoRA Fusion for Autoregressive Multi-Subject Personalization","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-06T20:46:25.063313Z"},"links":{"cited_paper":"/paper/2501.09503","citing_paper":"/paper/2507.01792"},"observation_digest":"sha256:893b380d7f8524948b11d5c0fb4661075de5f7127490191aed78a156d830981b","observation_id":"99b509e4-117e-4b28-9ca2-1c3707f95bbb","resolution":{"observed_at":"2026-08-06T20:46:25.063313Z","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":"2026-08-06T20:46:25.065994Z","title":"Lora: Low-rank adaptation of large language models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.01792","last_updated":"2025-07-02T15:16:59Z","snapshot_observed_at":"2026-08-08T19:57:19.375306Z","submitted_at":"2025-07-02T15:16:59Z","title":"FreeLoRA: Enabling Training-Free LoRA Fusion for Autoregressive Multi-Subject Personalization","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-06T20:46:25.065994Z"},"links":{"citing_paper":"/paper/2507.01792"},"observation_digest":"sha256:d7d61d4914650cff3ebc444f3bbf3330993b4f2f33cc0f6492d1b4ccf0ab8263","observation_id":"f836a9de-8462-4938-af5d-0b7253f5c689","resolution":{"observed_at":"2026-08-06T20:46:25.065994Z","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":"2026-08-06T20:46:25.904035Z","title":"Resolving multi- condition confusion for finetuning-free personalized image generation","venue":null,"work_id":"5d5e6dd6-41e6-414d-b6be-905ef5968f1b","year":2025},"citing_paper":{"arxiv_id":"2507.01792","last_updated":"2025-07-02T15:16:59Z","snapshot_observed_at":"2026-08-08T19:57:19.375306Z","submitted_at":"2025-07-02T15:16:59Z","title":"FreeLoRA: Enabling Training-Free LoRA Fusion for Autoregressive Multi-Subject Personalization","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-06T20:46:25.068267Z"},"links":{"citing_paper":"/paper/2507.01792"},"observation_digest":"sha256:67a79498e23252d2eede737f82345ec431aed1646264b42d073a7d5c162da906","observation_id":"8f391735-07ac-4300-91b5-dbfa85984df6","resolution":{"observed_at":"2026-08-06T20:46:25.907395Z","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":"2504.11478","last_updated":"2025-04-19T05:17:32Z","snapshot_observed_at":"2026-08-07T16:06:16.592168Z","submitted_at":"2025-04-12T20:41:53Z","title":"Flux Already Knows -- Activating Subject-Driven Image Generation without Training","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2504.11478","snapshot_observed_at":"2026-08-06T20:46:25.070895Z","title":"Flux already knows-activating subject-driven image generation without training","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2507.01792","last_updated":"2025-07-02T15:16:59Z","snapshot_observed_at":"2026-08-08T19:57:19.375306Z","submitted_at":"2025-07-02T15:16:59Z","title":"FreeLoRA: Enabling Training-Free LoRA Fusion for Autoregressive Multi-Subject Personalization","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-06T20:46:25.070895Z"},"links":{"cited_paper":"/paper/2504.11478","citing_paper":"/paper/2507.01792"},"observation_digest":"sha256:355cf28064c6b4ee4193240e11d2adbafd81ed3529687ea821502bd48e991e12","observation_id":"3416f94e-0d6b-46db-abcc-b1c2dd9a0fa2","resolution":{"observed_at":"2026-08-06T20:46:25.070895Z","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":"2026-08-06T20:46:25.073707Z","title":"Multi- concept customization of text-to-image diffusion","venue":null,"work_id":null,"year":1931},"citing_paper":{"arxiv_id":"2507.01792","last_updated":"2025-07-02T15:16:59Z","snapshot_observed_at":"2026-08-08T19:57:19.375306Z","submitted_at":"2025-07-02T15:16:59Z","title":"FreeLoRA: Enabling Training-Free LoRA Fusion for Autoregressive Multi-Subject Personalization","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-06T20:46:25.073707Z"},"links":{"citing_paper":"/paper/2507.01792"},"observation_digest":"sha256:cf0ce6bc04d54a02d95b406f26d0f33a2fb6bbd0f1f61a455a4ceaacd26d449a","observation_id":"8466ba5c-5d21-4684-8459-68c8e58b99f7","resolution":{"observed_at":"2026-08-06T20:46:25.073707Z","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":"2026-08-06T20:46:25.076498Z","title":"Blip-diffusion: Pre-trained subject representation for controllable text-to-image generation and editing","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.01792","last_updated":"2025-07-02T15:16:59Z","snapshot_observed_at":"2026-08-08T19:57:19.375306Z","submitted_at":"2025-07-02T15:16:59Z","title":"FreeLoRA: Enabling Training-Free LoRA Fusion for Autoregressive Multi-Subject Personalization","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-06T20:46:25.076498Z"},"links":{"citing_paper":"/paper/2507.01792"},"observation_digest":"sha256:ad02aca86eefb6c66d4620a8a50873f4063a192ab559070d3fcb1e088b6545d6","observation_id":"064eb7af-dd58-4c65-9870-5515ccf13194","resolution":{"observed_at":"2026-08-06T20:46:25.076498Z","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":"2026-08-06T20:46:25.881735Z","title":"Autoregressive image generation without vector quantization","venue":null,"work_id":"7152726f-f1cd-44fe-b574-398c3be020a2","year":2025},"citing_paper":{"arxiv_id":"2507.01792","last_updated":"2025-07-02T15:16:59Z","snapshot_observed_at":"2026-08-08T19:57:19.375306Z","submitted_at":"2025-07-02T15:16:59Z","title":"FreeLoRA: Enabling Training-Free LoRA Fusion for Autoregressive Multi-Subject Personalization","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-06T20:46:25.079075Z"},"links":{"citing_paper":"/paper/2507.01792"},"observation_digest":"sha256:cf4b593e21e4e3c14096863d6570ef1f677cea22de02729b94a4634fc9d21022","observation_id":"50196571-73bb-4890-98f8-fe7b5f56ac8f","resolution":{"observed_at":"2026-08-06T20:46:25.884595Z","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":"2303.05125","last_updated":"2023-03-09T09:16:04Z","snapshot_observed_at":"2026-07-06T15:00:31.814027Z","submitted_at":"2023-03-09T09:16:04Z","title":"Cones: Concept Neurons in Diffusion Models for Customized Generation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.05125","snapshot_observed_at":"2026-08-06T20:46:25.081451Z","title":"Cones: Concept neurons in diffusion models for customized generation","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.01792","last_updated":"2025-07-02T15:16:59Z","snapshot_observed_at":"2026-08-08T19:57:19.375306Z","submitted_at":"2025-07-02T15:16:59Z","title":"FreeLoRA: Enabling Training-Free LoRA Fusion for Autoregressive Multi-Subject Personalization","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-06T20:46:25.081451Z"},"links":{"cited_paper":"/paper/2303.05125","citing_paper":"/paper/2507.01792"},"observation_digest":"sha256:edbea6ae9fb601de748150a1984dbc04b6ff64e1aedf331eb1f1c1fd1245b90e","observation_id":"8435961e-0f4c-41df-b9cf-b6be601b9b84","resolution":{"observed_at":"2026-08-06T20:46:25.081451Z","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":"2026-08-06T20:46:25.872565Z","title":"Subject-diffusion: Open domain per- sonalized text-to-image generation without test-time fine-tuning","venue":null,"work_id":"b9471538-c680-4d2b-8a2c-5741faa29fa6","year":2024},"citing_paper":{"arxiv_id":"2507.01792","last_updated":"2025-07-02T15:16:59Z","snapshot_observed_at":"2026-08-08T19:57:19.375306Z","submitted_at":"2025-07-02T15:16:59Z","title":"FreeLoRA: Enabling Training-Free LoRA Fusion for Autoregressive Multi-Subject Personalization","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-06T20:46:25.084086Z"},"links":{"citing_paper":"/paper/2507.01792"},"observation_digest":"sha256:070aca459d10eed1f3704457481e37c82b8f08324c9f6005f2f5c3982d9db7b7","observation_id":"9ee6b897-399d-47f5-9a18-feff517941a7","resolution":{"observed_at":"2026-08-06T20:46:25.875411Z","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":"2026-08-06T20:46:25.086500Z","title":"Realcustom++: Representing images as real-word for real-time customization","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.01792","last_updated":"2025-07-02T15:16:59Z","snapshot_observed_at":"2026-08-08T19:57:19.375306Z","submitted_at":"2025-07-02T15:16:59Z","title":"FreeLoRA: Enabling Training-Free LoRA Fusion for Autoregressive Multi-Subject Personalization","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-06T20:46:25.086500Z"},"links":{"citing_paper":"/paper/2507.01792"},"observation_digest":"sha256:b39d9c5c7284d64558bce1b1014c24fac628122ec0c015779a81b12ccfcb33c7","observation_id":"184c3bfd-f53c-4790-b513-d24ab9a734f4","resolution":{"observed_at":"2026-08-06T20:46:25.086500Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.19776","last_updated":"2025-07-29T20:38:01Z","snapshot_observed_at":"2026-08-05T00:16:35.320085Z","submitted_at":"2024-03-28T18:58:43Z","title":"Contrastive Test-Time Composition of Multiple LoRA Models for Image Generation","version":2},"cited_work":{"arxiv_id":"2403.19776","doi":null,"metadata_source":"pith","pith_arxiv_id":"2403.19776","snapshot_observed_at":"2026-08-06T20:46:25.617394Z","title":"Contrastive Test-Time Composition of Multiple LoRA Models for Image Generation","venue":"cs.CV","work_id":"bea94201-9348-47fd-bbab-3798c96ef3d1","year":2024},"citing_paper":{"arxiv_id":"2507.01792","last_updated":"2025-07-02T15:16:59Z","snapshot_observed_at":"2026-08-08T19:57:19.375306Z","submitted_at":"2025-07-02T15:16:59Z","title":"FreeLoRA: Enabling Training-Free LoRA Fusion for Autoregressive Multi-Subject Personalization","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-06T20:46:25.088929Z"},"links":{"cited_paper":"/paper/2403.19776","citing_paper":"/paper/2507.01792"},"observation_digest":"sha256:17567b0e541874e73dc998828dc2c89497fe53e2e79f3f26e6a874f149387739","observation_id":"4fbb41c4-4cdf-4264-8c9a-fd24853709cc","resolution":{"observed_at":"2026-08-06T20:46:25.620182Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T20:46:25.091792Z","title":"Dreamo: A unified framework for image customization","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2507.01792","last_updated":"2025-07-02T15:16:59Z","snapshot_observed_at":"2026-08-08T19:57:19.375306Z","submitted_at":"2025-07-02T15:16:59Z","title":"FreeLoRA: Enabling Training-Free LoRA Fusion for Autoregressive Multi-Subject Personalization","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-06T20:46:25.091792Z"},"links":{"citing_paper":"/paper/2507.01792"},"observation_digest":"sha256:f94d8be15cdb7e97002f15e43af224e3ff723e80e414e3562cb5562a3d0aab20","observation_id":"8e07b5f1-3843-4086-90c0-b4e8cae814b9","resolution":{"observed_at":"2026-08-06T20:46:25.091792Z","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":"2026-08-06T20:46:25.862986Z","title":"Dreammatcher: appearance matching self-attention for semantically-consistent text-to-image personalization","venue":null,"work_id":"2f1d7b50-f222-433c-bfd6-4e6dbe1c4372","year":2024},"citing_paper":{"arxiv_id":"2507.01792","last_updated":"2025-07-02T15:16:59Z","snapshot_observed_at":"2026-08-08T19:57:19.375306Z","submitted_at":"2025-07-02T15:16:59Z","title":"FreeLoRA: Enabling Training-Free LoRA Fusion for Autoregressive Multi-Subject Personalization","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-06T20:46:25.094480Z"},"links":{"citing_paper":"/paper/2507.01792"},"observation_digest":"sha256:bd2fbbe0ff2c4db18e23062f60425ef266e8abaa2f96e5742f2858adb072c6b1","observation_id":"e53d76d1-8a9f-4ed9-814e-c6aa7b432b57","resolution":{"observed_at":"2026-08-06T20:46:25.866209Z","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":"2502.18461","last_updated":"2025-03-02T12:44:06Z","snapshot_observed_at":"2026-08-08T06:47:49.944081Z","submitted_at":"2025-02-25T18:59:12Z","title":"K-LoRA: Unlocking Training-Free Fusion of Any Subject and Style LoRAs","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.18461","snapshot_observed_at":"2026-08-06T20:46:25.097061Z","title":"K-lora: Unlocking training-free fusion of any subject and style loras","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2507.01792","last_updated":"2025-07-02T15:16:59Z","snapshot_observed_at":"2026-08-08T19:57:19.375306Z","submitted_at":"2025-07-02T15:16:59Z","title":"FreeLoRA: Enabling Training-Free LoRA Fusion for Autoregressive Multi-Subject Personalization","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-06T20:46:25.097061Z"},"links":{"cited_paper":"/paper/2502.18461","citing_paper":"/paper/2507.01792"},"observation_digest":"sha256:2a6f0e7dbe725bccc5c607991e88f132ad6a7a0877f7c36799b75cdffffde201","observation_id":"84c9b0e8-f94d-405c-9106-b7a2561077e9","resolution":{"observed_at":"2026-08-06T20:46:25.097061Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"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":"2026-08-06T20:46:25.100071Z","title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.01792","last_updated":"2025-07-02T15:16:59Z","snapshot_observed_at":"2026-08-08T19:57:19.375306Z","submitted_at":"2025-07-02T15:16:59Z","title":"FreeLoRA: Enabling Training-Free LoRA Fusion for Autoregressive Multi-Subject Personalization","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-06T20:46:25.100071Z"},"links":{"cited_paper":"/paper/2307.01952","citing_paper":"/paper/2507.01792"},"observation_digest":"sha256:1c96b93494643c7ed7f85d9b9a8f231a9c34e331dcd88b2852c0acc65206c2a4","observation_id":"88e5f9ab-6a6c-4bd2-996d-15b552a271cd","resolution":{"observed_at":"2026-08-06T20:46:25.100071Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.13974","last_updated":"2024-01-25T06:18:20Z","snapshot_observed_at":"2026-08-03T00:16:06.403631Z","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":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.13974","snapshot_observed_at":"2026-08-06T20:46:25.102618Z","title":"Bootpig: Bootstrapping zero-shot personalized image generation capabilities in pretrained diffusion models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.01792","last_updated":"2025-07-02T15:16:59Z","snapshot_observed_at":"2026-08-08T19:57:19.375306Z","submitted_at":"2025-07-02T15:16:59Z","title":"FreeLoRA: Enabling Training-Free LoRA Fusion for Autoregressive Multi-Subject Personalization","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-06T20:46:25.102618Z"},"links":{"cited_paper":"/paper/2401.13974","citing_paper":"/paper/2507.01792"},"observation_digest":"sha256:dde46c7cc22066bcd233dcabb7592b31259bd2101450dacfaee36624f5335523","observation_id":"8821270a-c7a6-4894-a09b-e374cf55f68c","resolution":{"observed_at":"2026-08-06T20:46:25.102618Z","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":"2026-08-06T20:46:25.105748Z","title":"Learning transferable visual models from natural language supervision","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.01792","last_updated":"2025-07-02T15:16:59Z","snapshot_observed_at":"2026-08-08T19:57:19.375306Z","submitted_at":"2025-07-02T15:16:59Z","title":"FreeLoRA: Enabling Training-Free LoRA Fusion for Autoregressive Multi-Subject Personalization","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-06T20:46:25.105748Z"},"links":{"citing_paper":"/paper/2507.01792"},"observation_digest":"sha256:9fce83ba9f306578ae0bfd52370078a992bb5a89ff26ae504177deea51b4ddff","observation_id":"51bd59b6-8b18-44d4-9b9f-c0a0341899a9","resolution":{"observed_at":"2026-08-06T20:46:25.105748Z","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":"2026-08-06T20:46:25.108416Z","title":"High- resolution image synthesis with latent diffusion models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.01792","last_updated":"2025-07-02T15:16:59Z","snapshot_observed_at":"2026-08-08T19:57:19.375306Z","submitted_at":"2025-07-02T15:16:59Z","title":"FreeLoRA: Enabling Training-Free LoRA Fusion for Autoregressive Multi-Subject Personalization","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-06T20:46:25.108416Z"},"links":{"citing_paper":"/paper/2507.01792"},"observation_digest":"sha256:7a5d0f0a51da9cb7eb7e07811f76ed19aa20b49470450934b58544183cf8c2b1","observation_id":"b15c852f-b5e5-4e93-83d3-a785b4b11723","resolution":{"observed_at":"2026-08-06T20:46:25.108416Z","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":"2026-08-06T20:46:25.839805Z","title":"Dreambooth: Fine tuning text-to-image diffusion models for subject-driven generation","venue":null,"work_id":"55ea10b6-d951-4fcb-b0b8-fb48f2545acb","year":2023},"citing_paper":{"arxiv_id":"2507.01792","last_updated":"2025-07-02T15:16:59Z","snapshot_observed_at":"2026-08-08T19:57:19.375306Z","submitted_at":"2025-07-02T15:16:59Z","title":"FreeLoRA: Enabling Training-Free LoRA Fusion for Autoregressive Multi-Subject Personalization","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-06T20:46:25.111227Z"},"links":{"citing_paper":"/paper/2507.01792"},"observation_digest":"sha256:712a1c97fb53d505ba313ebc7a68e004c31bfed187c8bde5adebe589f75054f7","observation_id":"080a2875-7a96-4f60-ad82-09f20c471452","resolution":{"observed_at":"2026-08-06T20:46:25.843195Z","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":"2026-08-06T20:46:25.830505Z","title":"Low-rank adaptation for fast text-to-image diffusion fine-tuning","venue":null,"work_id":"2cc58d57-2ba5-48e9-8d2e-406dba2dd35b","year":null},"citing_paper":{"arxiv_id":"2507.01792","last_updated":"2025-07-02T15:16:59Z","snapshot_observed_at":"2026-08-08T19:57:19.375306Z","submitted_at":"2025-07-02T15:16:59Z","title":"FreeLoRA: Enabling Training-Free LoRA Fusion for Autoregressive Multi-Subject Personalization","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-06T20:46:25.113835Z"},"links":{"citing_paper":"/paper/2507.01792"},"observation_digest":"sha256:60f48e4c9a4c88ce417837605dc797fa6d3eaa6a11e5cabbd8857e0237913d37","observation_id":"5ff741cb-f447-4a7f-a467-0b95b850ef47","resolution":{"observed_at":"2026-08-06T20:46:25.833385Z","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":"2026-08-06T20:46:25.820847Z","title":"Ziplora: Any subject in any style by effectively merging loras","venue":null,"work_id":"7deceb13-d69d-410e-a171-8fcdd76cbac3","year":2024},"citing_paper":{"arxiv_id":"2507.01792","last_updated":"2025-07-02T15:16:59Z","snapshot_observed_at":"2026-08-08T19:57:19.375306Z","submitted_at":"2025-07-02T15:16:59Z","title":"FreeLoRA: Enabling Training-Free LoRA Fusion for Autoregressive Multi-Subject Personalization","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-06T20:46:25.116949Z"},"links":{"citing_paper":"/paper/2507.01792"},"observation_digest":"sha256:df57e3e834f6d278e9a1ada54e16efd490869879dc8a5709c2adbd88ee7b8ec4","observation_id":"6844e95e-d764-4373-ab3d-6481ebae83f4","resolution":{"observed_at":"2026-08-06T20:46:25.823848Z","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":"2026-08-06T20:46:25.811114Z","title":"Instantbooth: Personalized text-to- image generation without test-time finetuning","venue":null,"work_id":"72ec3742-217c-443e-9e39-43f7810b6063","year":2024},"citing_paper":{"arxiv_id":"2507.01792","last_updated":"2025-07-02T15:16:59Z","snapshot_observed_at":"2026-08-08T19:57:19.375306Z","submitted_at":"2025-07-02T15:16:59Z","title":"FreeLoRA: Enabling Training-Free LoRA Fusion for Autoregressive Multi-Subject Personalization","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-06T20:46:25.119585Z"},"links":{"citing_paper":"/paper/2507.01792"},"observation_digest":"sha256:376cd86f92604c6b2ff820ee9d35a0973aac6708442a01ef4384229af5cd0d77","observation_id":"2876a87b-c445-4776-ae44-01f6a2031df1","resolution":{"observed_at":"2026-08-06T20:46:25.813999Z","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":"2412.15188","last_updated":"2025-02-05T02:26:38Z","snapshot_observed_at":"2026-08-02T19:18:33.010410Z","submitted_at":"2024-12-19T18:56:24Z","title":"LMFusion: Adapting Pretrained Language Models for Multimodal Generation","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.15188","snapshot_observed_at":"2026-08-06T20:46:25.122139Z","title":"Llamafusion: Adapting pretrained language models for multimodal generation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.01792","last_updated":"2025-07-02T15:16:59Z","snapshot_observed_at":"2026-08-08T19:57:19.375306Z","submitted_at":"2025-07-02T15:16:59Z","title":"FreeLoRA: Enabling Training-Free LoRA Fusion for Autoregressive Multi-Subject Personalization","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-06T20:46:25.122139Z"},"links":{"cited_paper":"/paper/2412.15188","citing_paper":"/paper/2507.01792"},"observation_digest":"sha256:0f4553bf9d1a9abe99f55c6dff362aba90a0d65334512b97e634fe0ecde9901e","observation_id":"d2c473d0-10b9-4e03-938d-35c50e31c5ef","resolution":{"observed_at":"2026-08-06T20:46:25.122139Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2411.15466","last_updated":"2025-06-04T01:35:55Z","snapshot_observed_at":"2026-08-05T03:22:01.656713Z","submitted_at":"2024-11-23T06:17:43Z","title":"Large-Scale Text-to-Image Model with Inpainting is a Zero-Shot Subject-Driven Image Generator","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.15466","snapshot_observed_at":"2026-08-06T20:46:25.125226Z","title":"Large-scale text-to- image model with inpainting is a zero-shot subject-driven image generator","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.01792","last_updated":"2025-07-02T15:16:59Z","snapshot_observed_at":"2026-08-08T19:57:19.375306Z","submitted_at":"2025-07-02T15:16:59Z","title":"FreeLoRA: Enabling Training-Free LoRA Fusion for Autoregressive Multi-Subject Personalization","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-06T20:46:25.125226Z"},"links":{"cited_paper":"/paper/2411.15466","citing_paper":"/paper/2507.01792"},"observation_digest":"sha256:1e21b213b9bedb6034549eacc4d914ed9ec14a81dc4e28ab792243589877b20a","observation_id":"d4a7eb96-39b5-49a4-a10e-94d32ea7ec29","resolution":{"observed_at":"2026-08-06T20:46:25.125226Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2504.13162","last_updated":"2025-04-17T17:58:26Z","snapshot_observed_at":"2026-08-07T16:01:21.245500Z","submitted_at":"2025-04-17T17:58:26Z","title":"Personalized Text-to-Image Generation with Auto-Regressive Models","version":1},"cited_work":{"arxiv_id":"2504.13162","doi":null,"metadata_source":"pith","pith_arxiv_id":"2504.13162","snapshot_observed_at":"2026-08-06T20:46:25.490563Z","title":"Personalized Text-to-Image Generation with Auto-Regressive Models","venue":"cs.CV","work_id":"2d3402ae-a500-4ab3-8b33-70b71c0dc9b6","year":2025},"citing_paper":{"arxiv_id":"2507.01792","last_updated":"2025-07-02T15:16:59Z","snapshot_observed_at":"2026-08-08T19:57:19.375306Z","submitted_at":"2025-07-02T15:16:59Z","title":"FreeLoRA: Enabling Training-Free LoRA Fusion for Autoregressive Multi-Subject Personalization","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-06T20:46:25.128283Z"},"links":{"cited_paper":"/paper/2504.13162","citing_paper":"/paper/2507.01792"},"observation_digest":"sha256:72f25710d580e9367a367a3316e5d6e1f95b32b60b989b742a87962970f31bc6","observation_id":"6d30520e-af56-4eaa-94ec-2ec3f0cd33a4","resolution":{"observed_at":"2026-08-06T20:46:25.493407Z","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":{"arxiv_id":"2411.15098","last_updated":"2025-07-07T17:33:23Z","snapshot_observed_at":"2026-08-09T00:44:58.573039Z","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":"2026-08-06T20:46:25.131067Z","title":"Ominicontrol: Minimal and universal control for diffusion transformer","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.01792","last_updated":"2025-07-02T15:16:59Z","snapshot_observed_at":"2026-08-08T19:57:19.375306Z","submitted_at":"2025-07-02T15:16:59Z","title":"FreeLoRA: Enabling Training-Free LoRA Fusion for Autoregressive Multi-Subject Personalization","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-06T20:46:25.131067Z"},"links":{"cited_paper":"/paper/2411.15098","citing_paper":"/paper/2507.01792"},"observation_digest":"sha256:6bcc8994d33e38f3988f2a14203ea9c3cf29c5aaafd62caed384760d9a90c433","observation_id":"8a1efbc7-0eaf-4a23-bcba-d1d859027651","resolution":{"observed_at":"2026-08-06T20:46:25.131067Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.09818","last_updated":"2025-03-21T05:54:00Z","snapshot_observed_at":"2026-08-07T22:11:30.869700Z","submitted_at":"2024-05-16T05:23:41Z","title":"Chameleon: Mixed-Modal Early-Fusion Foundation Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.09818","snapshot_observed_at":"2026-08-06T20:46:25.134133Z","title":"Chameleon: Mixed-modal early-fusion foundation models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.01792","last_updated":"2025-07-02T15:16:59Z","snapshot_observed_at":"2026-08-08T19:57:19.375306Z","submitted_at":"2025-07-02T15:16:59Z","title":"FreeLoRA: Enabling Training-Free LoRA Fusion for Autoregressive Multi-Subject Personalization","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-06T20:46:25.134133Z"},"links":{"cited_paper":"/paper/2405.09818","citing_paper":"/paper/2507.01792"},"observation_digest":"sha256:33068aacd47516f9acacd1506e64a2fa4e6e119df51892fde02f20d349045210","observation_id":"9cef4ad4-c3d5-42dd-9fab-7c553379faf5","resolution":{"observed_at":"2026-08-06T20:46:25.134133Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2312.11805","last_updated":"2025-05-09T21:04:06Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-12-19T02:39:27Z","title":"Gemini: A Family of Highly Capable Multimodal Models","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.11805","snapshot_observed_at":"2026-08-06T20:46:25.137294Z","title":"Gemini: a family of highly capable multimodal models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.01792","last_updated":"2025-07-02T15:16:59Z","snapshot_observed_at":"2026-08-08T19:57:19.375306Z","submitted_at":"2025-07-02T15:16:59Z","title":"FreeLoRA: Enabling Training-Free LoRA Fusion for Autoregressive Multi-Subject Personalization","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-06T20:46:25.137294Z"},"links":{"cited_paper":"/paper/2312.11805","citing_paper":"/paper/2507.01792"},"observation_digest":"sha256:35b82edad13f813d5f94422bd73c6726bc781f4ca3d215d64078b65149b03e86","observation_id":"718177c7-6241-4a17-8f60-a388b90dd866","resolution":{"observed_at":"2026-08-06T20:46:25.137294Z","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":"2026-08-06T20:46:25.802023Z","title":"Visual autoregressive modeling: Scalable image generation via next-scale prediction","venue":null,"work_id":"bce7c621-462a-49f5-96f4-ce40cac781c2","year":2025},"citing_paper":{"arxiv_id":"2507.01792","last_updated":"2025-07-02T15:16:59Z","snapshot_observed_at":"2026-08-08T19:57:19.375306Z","submitted_at":"2025-07-02T15:16:59Z","title":"FreeLoRA: Enabling Training-Free LoRA Fusion for Autoregressive Multi-Subject Personalization","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-06T20:46:25.139909Z"},"links":{"citing_paper":"/paper/2507.01792"},"observation_digest":"sha256:787a7ce0525c5d997210bd9e6abf18703d6f7cb49a1b553646340a6cf91a2c1d","observation_id":"cfe0b1b8-2fc4-408e-b4f4-bd0c26f872fb","resolution":{"observed_at":"2026-08-06T20:46:25.804927Z","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":"2412.14164","last_updated":"2024-12-18T18:58:50Z","snapshot_observed_at":"2026-08-08T15:05:21.947334Z","submitted_at":"2024-12-18T18:58:50Z","title":"MetaMorph: Multimodal Understanding and Generation via Instruction Tuning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.14164","snapshot_observed_at":"2026-08-06T20:46:25.142498Z","title":"Metamorph: Multimodal under- standing and generation via instruction tuning","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.01792","last_updated":"2025-07-02T15:16:59Z","snapshot_observed_at":"2026-08-08T19:57:19.375306Z","submitted_at":"2025-07-02T15:16:59Z","title":"FreeLoRA: Enabling Training-Free LoRA Fusion for Autoregressive Multi-Subject Personalization","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-06T20:46:25.142498Z"},"links":{"cited_paper":"/paper/2412.14164","citing_paper":"/paper/2507.01792"},"observation_digest":"sha256:f841109522fe0711fa336b43a2efbc1bcabe0e0d209a972c65953f0e704194be","observation_id":"422d8613-9e19-4c61-8bd0-ac6ee5921553","resolution":{"observed_at":"2026-08-06T20:46:25.142498Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.07209","last_updated":"2025-03-04T06:21:26Z","snapshot_observed_at":"2026-07-06T18:28:51.180903Z","submitted_at":"2024-06-11T12:32:53Z","title":"MS-Diffusion: Multi-subject Zero-shot Image Personalization with Layout Guidance","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.07209","snapshot_observed_at":"2026-08-06T20:46:25.145387Z","title":"Ms-diffusion: Multi- subject zero-shot image personalization with layout guidance","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.01792","last_updated":"2025-07-02T15:16:59Z","snapshot_observed_at":"2026-08-08T19:57:19.375306Z","submitted_at":"2025-07-02T15:16:59Z","title":"FreeLoRA: Enabling Training-Free LoRA Fusion for Autoregressive Multi-Subject Personalization","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-06T20:46:25.145387Z"},"links":{"cited_paper":"/paper/2406.07209","citing_paper":"/paper/2507.01792"},"observation_digest":"sha256:e94918d1f0e243bcc3e8d9aeb3bba1bd76b7fbb9041f22191aafb2eae78181c2","observation_id":"01d4ffab-c112-4897-a612-a5bcaabc56c8","resolution":{"observed_at":"2026-08-06T20:46:25.145387Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.18869","last_updated":"2024-09-27T16:06:11Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-09-27T16:06:11Z","title":"Emu3: Next-Token Prediction is All You Need","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.18869","snapshot_observed_at":"2026-08-06T20:46:25.148076Z","title":"Emu3: Next-token prediction is all you need","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.01792","last_updated":"2025-07-02T15:16:59Z","snapshot_observed_at":"2026-08-08T19:57:19.375306Z","submitted_at":"2025-07-02T15:16:59Z","title":"FreeLoRA: Enabling Training-Free LoRA Fusion for Autoregressive Multi-Subject Personalization","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-06T20:46:25.148076Z"},"links":{"cited_paper":"/paper/2409.18869","citing_paper":"/paper/2507.01792"},"observation_digest":"sha256:457686f0d9f54988c59cb6722c339a78e54fd74445b55da88428eb3d57e2e7e0","observation_id":"cb5a61bf-9868-47f0-8061-ffdbdac3eaaf","resolution":{"observed_at":"2026-08-06T20:46:25.148076Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.16211","last_updated":"2024-12-08T19:55:36Z","snapshot_observed_at":"2026-08-04T16:36:02.143481Z","submitted_at":"2024-09-24T16:12:12Z","title":"MaskBit: Embedding-free Image Generation via Bit Tokens","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.16211","snapshot_observed_at":"2026-08-06T20:46:25.150779Z","title":"Maskbit: Embedding-free image generation via bit tokens","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.01792","last_updated":"2025-07-02T15:16:59Z","snapshot_observed_at":"2026-08-08T19:57:19.375306Z","submitted_at":"2025-07-02T15:16:59Z","title":"FreeLoRA: Enabling Training-Free LoRA Fusion for Autoregressive Multi-Subject Personalization","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-06T20:46:25.150779Z"},"links":{"cited_paper":"/paper/2409.16211","citing_paper":"/paper/2507.01792"},"observation_digest":"sha256:69d67a02d63218aba98604e5c3eaa314b6017e417966f8d655d7da1e581a9954","observation_id":"8aef106a-6b53-4159-ab89-819768ddd9f4","resolution":{"observed_at":"2026-08-06T20:46:25.150779Z","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":"2026-08-06T20:46:25.792331Z","title":"Elite: Encoding visual concepts into textual embeddings for customized text-to-image generation","venue":null,"work_id":"fe5836a2-8cc8-40ed-8fdf-8347f27e2600","year":2023},"citing_paper":{"arxiv_id":"2507.01792","last_updated":"2025-07-02T15:16:59Z","snapshot_observed_at":"2026-08-08T19:57:19.375306Z","submitted_at":"2025-07-02T15:16:59Z","title":"FreeLoRA: Enabling Training-Free LoRA Fusion for Autoregressive Multi-Subject Personalization","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-06T20:46:25.153481Z"},"links":{"citing_paper":"/paper/2507.01792"},"observation_digest":"sha256:22a450bba4ce987d57abe37ab95456dfbc997fe0ff1b8d2b697293bef917375a","observation_id":"77bbd027-384c-4110-af1b-a363a1daa04a","resolution":{"observed_at":"2026-08-06T20:46:25.795510Z","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":"2504.02160","last_updated":"2025-04-02T22:20:21Z","snapshot_observed_at":"2026-08-07T16:13:24.968703Z","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":"2026-08-06T20:46:25.155847Z","title":"Less-to- more generalization: Unlocking more controllability by in-context generation","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2507.01792","last_updated":"2025-07-02T15:16:59Z","snapshot_observed_at":"2026-08-08T19:57:19.375306Z","submitted_at":"2025-07-02T15:16:59Z","title":"FreeLoRA: Enabling Training-Free LoRA Fusion for Autoregressive Multi-Subject Personalization","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-06T20:46:25.155847Z"},"links":{"cited_paper":"/paper/2504.02160","citing_paper":"/paper/2507.01792"},"observation_digest":"sha256:e5e85076c5400601b9cda60772ac6401ff800f9018840e7b2ac8e1c3bd631e60","observation_id":"b6c24b32-0c70-4d77-9ea5-2b4950a3001b","resolution":{"observed_at":"2026-08-06T20:46:25.155847Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.04429","last_updated":"2025-03-04T16:31:57Z","snapshot_observed_at":"2026-08-01T23:38:04.510222Z","submitted_at":"2024-09-06T17:49:56Z","title":"VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.04429","snapshot_observed_at":"2026-08-06T20:46:25.158437Z","title":"Vila-u: a unified foundation model integrating visual understanding and generation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.01792","last_updated":"2025-07-02T15:16:59Z","snapshot_observed_at":"2026-08-08T19:57:19.375306Z","submitted_at":"2025-07-02T15:16:59Z","title":"FreeLoRA: Enabling Training-Free LoRA Fusion for Autoregressive Multi-Subject Personalization","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-06T20:46:25.158437Z"},"links":{"cited_paper":"/paper/2409.04429","citing_paper":"/paper/2507.01792"},"observation_digest":"sha256:077eb0ea2fe5cb4c06ed581847ed634c1f32723cd0e4fed249a80e253a4d751f","observation_id":"84399f32-9b05-44de-be7b-e6d63279cf5c","resolution":{"observed_at":"2026-08-06T20:46:25.158437Z","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":"2026-08-06T20:46:25.160916Z","title":"Proxy-tuning: Tailoring multimodal autoregressive models for subject-driven image generation.arXiv preprint arXiv:2503.10125, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2507.01792","last_updated":"2025-07-02T15:16:59Z","snapshot_observed_at":"2026-08-08T19:57:19.375306Z","submitted_at":"2025-07-02T15:16:59Z","title":"FreeLoRA: Enabling Training-Free LoRA Fusion for Autoregressive Multi-Subject Personalization","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-06T20:46:25.160916Z"},"links":{"citing_paper":"/paper/2507.01792"},"observation_digest":"sha256:cc4358f9db7e115cfa038a47dc2b98c063eaca862fbd4665d58ae9be46351e67","observation_id":"16a9940c-6d55-4c0c-8409-f132b31d3964","resolution":{"observed_at":"2026-08-06T20:46:25.160916Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.11340","last_updated":"2024-11-21T14:09:12Z","snapshot_observed_at":"2026-07-06T19:16:51.512681Z","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":"2026-08-06T20:46:25.163303Z","title":"Omnigen: Unified image generation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.01792","last_updated":"2025-07-02T15:16:59Z","snapshot_observed_at":"2026-08-08T19:57:19.375306Z","submitted_at":"2025-07-02T15:16:59Z","title":"FreeLoRA: Enabling Training-Free LoRA Fusion for Autoregressive Multi-Subject Personalization","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-06T20:46:25.163303Z"},"links":{"cited_paper":"/paper/2409.11340","citing_paper":"/paper/2507.01792"},"observation_digest":"sha256:ebd6ee21a08b22f81ed5b61dc7a28b4be8e8de656d55ddd4e28ad1718a978821","observation_id":"5219faa1-abd7-4c91-92e6-a98c9087b37c","resolution":{"observed_at":"2026-08-06T20:46:25.163303Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2408.12528","last_updated":"2025-09-08T02:42:57Z","snapshot_observed_at":"2026-07-06T19:04:43.716629Z","submitted_at":"2024-08-22T16:32:32Z","title":"Show-o: One Single Transformer to Unify Multimodal Understanding and Generation","version":7},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.12528","snapshot_observed_at":"2026-08-06T20:46:25.166001Z","title":"Show-o: One single trans- former to unify multimodal understanding and generation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.01792","last_updated":"2025-07-02T15:16:59Z","snapshot_observed_at":"2026-08-08T19:57:19.375306Z","submitted_at":"2025-07-02T15:16:59Z","title":"FreeLoRA: Enabling Training-Free LoRA Fusion for Autoregressive Multi-Subject Personalization","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-06T20:46:25.166001Z"},"links":{"cited_paper":"/paper/2408.12528","citing_paper":"/paper/2507.01792"},"observation_digest":"sha256:bc80c62a720743707aa7a7cba970da5a9fd1883e5c68ed5b734f218637e79a4e","observation_id":"2a250201-6323-47f5-aa9b-08bfbc18b5e5","resolution":{"observed_at":"2026-08-06T20:46:25.166001Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.11627","last_updated":"2024-07-11T02:30:02Z","snapshot_observed_at":"2026-07-06T17:46:11.859512Z","submitted_at":"2024-03-18T09:58:52Z","title":"LoRA-Composer: Leveraging Low-Rank Adaptation for Multi-Concept Customization in Training-Free Diffusion Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.11627","snapshot_observed_at":"2026-08-06T20:46:25.168524Z","title":"Lora-composer: Leveraging low-rank adaptation for multi-concept customization in training-free diffusion models.arXiv preprint arXiv:2403.11627, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.01792","last_updated":"2025-07-02T15:16:59Z","snapshot_observed_at":"2026-08-08T19:57:19.375306Z","submitted_at":"2025-07-02T15:16:59Z","title":"FreeLoRA: Enabling Training-Free LoRA Fusion for Autoregressive Multi-Subject Personalization","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-06T20:46:25.168524Z"},"links":{"cited_paper":"/paper/2403.11627","citing_paper":"/paper/2507.01792"},"observation_digest":"sha256:d0575a9c11ea045fabfcf0aeac93e5cfae525bf4ba0e2f5fb68faaff820a0922","observation_id":"ba274313-38db-4100-aad5-7433f328081c","resolution":{"observed_at":"2026-08-06T20:46:25.168524Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2411.00776","last_updated":"2024-11-01T17:59:58Z","snapshot_observed_at":"2026-07-06T19:43:42.287026Z","submitted_at":"2024-11-01T17:59:58Z","title":"Randomized Autoregressive Visual Generation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.00776","snapshot_observed_at":"2026-08-06T20:46:25.171340Z","title":"Randomized autore- gressive visual generation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.01792","last_updated":"2025-07-02T15:16:59Z","snapshot_observed_at":"2026-08-08T19:57:19.375306Z","submitted_at":"2025-07-02T15:16:59Z","title":"FreeLoRA: Enabling Training-Free LoRA Fusion for Autoregressive Multi-Subject Personalization","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-06T20:46:25.171340Z"},"links":{"cited_paper":"/paper/2411.00776","citing_paper":"/paper/2507.01792"},"observation_digest":"sha256:32ce52ba07ee6005647162c78af349b5e74b53f1756b307519a51a515b6420d9","observation_id":"9e8881ac-002b-4dbf-962e-e43d4bddf7e9","resolution":{"observed_at":"2026-08-06T20:46:25.171340Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.15641","last_updated":"2025-05-20T14:39:58Z","snapshot_observed_at":"2026-07-06T20:26:26.110538Z","submitted_at":"2025-01-26T19:01:19Z","title":"IP-Prompter: Training-Free Theme-Specific Image Generation via Dynamic Visual Prompting","version":2},"cited_work":{"arxiv_id":"2501.15641","doi":null,"metadata_source":"pith","pith_arxiv_id":"2501.15641","snapshot_observed_at":"2026-08-06T20:46:25.254453Z","title":"IP-Prompter: Training-Free Theme-Specific Image Generation via Dynamic Visual Prompting","venue":"cs.CV","work_id":"b7df501f-17c1-4033-8e12-5b1b5480da0f","year":2025},"citing_paper":{"arxiv_id":"2507.01792","last_updated":"2025-07-02T15:16:59Z","snapshot_observed_at":"2026-08-08T19:57:19.375306Z","submitted_at":"2025-07-02T15:16:59Z","title":"FreeLoRA: Enabling Training-Free LoRA Fusion for Autoregressive Multi-Subject Personalization","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-06T20:46:25.173889Z"},"links":{"cited_paper":"/paper/2501.15641","citing_paper":"/paper/2507.01792"},"observation_digest":"sha256:2c088694d241667e4a9d5ed6ae0ef65eb90c158eba93bff473351785bbae1bbf","observation_id":"6c76c341-23da-4ae6-8b4a-634a321a2f69","resolution":{"observed_at":"2026-08-06T20:46:25.259185Z","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":"2026-08-06T20:46:25.783155Z","title":"Ssr-encoder: Encoding selective subject representation for subject- driven generation","venue":null,"work_id":"38e23380-f924-4941-958b-fdee51e2022d","year":2024},"citing_paper":{"arxiv_id":"2507.01792","last_updated":"2025-07-02T15:16:59Z","snapshot_observed_at":"2026-08-08T19:57:19.375306Z","submitted_at":"2025-07-02T15:16:59Z","title":"FreeLoRA: Enabling Training-Free LoRA Fusion for Autoregressive Multi-Subject Personalization","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-06T20:46:25.176398Z"},"links":{"citing_paper":"/paper/2507.01792"},"observation_digest":"sha256:52c41ec3adf91ddbcc96ff885353d00787e7e0c9f97fee8d3b6ef91e9a7151b0","observation_id":"9a92617c-a5a8-4975-8e5d-49b5eb53fbf9","resolution":{"observed_at":"2026-08-06T20:46:25.786130Z","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":"2402.16843","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":"2026-08-06T20:46:25.179142Z","title":"Multi-lora composition for image generation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.01792","last_updated":"2025-07-02T15:16:59Z","snapshot_observed_at":"2026-08-08T19:57:19.375306Z","submitted_at":"2025-07-02T15:16:59Z","title":"FreeLoRA: Enabling Training-Free LoRA Fusion for Autoregressive Multi-Subject Personalization","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-06T20:46:25.179142Z"},"links":{"cited_paper":"/paper/2402.16843","citing_paper":"/paper/2507.01792"},"observation_digest":"sha256:428c954832152d4f62d918b788065b127fc852fa46c2902e87e8f3b5d3226198","observation_id":"e858c169-9f28-4f67-bf7f-92c83b2fc23f","resolution":{"observed_at":"2026-08-06T20:46:25.179142Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2408.11039","last_updated":"2024-08-20T17:48:20Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-08-20T17:48:20Z","title":"Transfusion: Predict the Next Token and Diffuse Images with One Multi-Modal Model","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.11039","snapshot_observed_at":"2026-08-06T20:46:25.181575Z","title":"Transfusion: Predict the next token and diffuse images with one multi-modal model","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.01792","last_updated":"2025-07-02T15:16:59Z","snapshot_observed_at":"2026-08-08T19:57:19.375306Z","submitted_at":"2025-07-02T15:16:59Z","title":"FreeLoRA: Enabling Training-Free LoRA Fusion for Autoregressive Multi-Subject Personalization","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-06T20:46:25.181575Z"},"links":{"cited_paper":"/paper/2408.11039","citing_paper":"/paper/2507.01792"},"observation_digest":"sha256:6c0ae40ba450728463957810aea73cbb91608fd357da516f5219d70291735c26","observation_id":"c94e3f62-b8a5-4d1f-b77b-32154ac0ebf5","resolution":{"observed_at":"2026-08-06T20:46:25.181575Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.13370","last_updated":"2025-05-21T08:18:59Z","snapshot_observed_at":"2026-07-06T19:35:08.846184Z","submitted_at":"2024-10-17T09:22:53Z","title":"MagicTailor: Component-Controllable Personalization in Text-to-Image Diffusion Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.13370","snapshot_observed_at":"2026-08-06T20:46:25.184165Z","title":"Magictailor: Component-controllable personalization in text-to-image diffusion models","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.01792","last_updated":"2025-07-02T15:16:59Z","snapshot_observed_at":"2026-08-08T19:57:19.375306Z","submitted_at":"2025-07-02T15:16:59Z","title":"FreeLoRA: Enabling Training-Free LoRA Fusion for Autoregressive Multi-Subject Personalization","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-06T20:46:25.184165Z"},"links":{"cited_paper":"/paper/2410.13370","citing_paper":"/paper/2507.01792"},"observation_digest":"sha256:e63da21b04cf947df501631d49f45dc0bc60f3ddd43f7011d48e0ab231be29dd","observation_id":"241b398b-0eb7-4dce-a27f-cd8f7abdcbc2","resolution":{"observed_at":"2026-08-06T20:46:25.184165Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2507.01792","last_updated":"2025-07-02T15:16:59Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-08T19:57:19.375306Z","submitted_at":"2025-07-02T15:16:59Z","title":"FreeLoRA: Enabling Training-Free LoRA Fusion for Autoregressive Multi-Subject Personalization"},"reference_resolution":{"displayed":57,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":41,"verified_exact":3,"verified_fuzzy":13},"total_outbound_references":57},"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 57 of 57 outbound references and 1 inbound Pith citation observation for arXiv:2507.01792."}