{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:EMTODNFMXS22HONLVD3NUHI33J","short_pith_number":"pith:EMTODNFM","schema_version":"1.0","canonical_sha256":"2326e1b4acbcb5a3b9aba8f6da1d1bda775d603aecfac5c31cc9213b551795e1","source":{"kind":"arxiv","id":"2402.05195","version":2},"attestation_state":"computed","paper":{"title":"$\\lambda$-ECLIPSE: Multi-Concept Personalized Text-to-Image Diffusion Models by Leveraging CLIP Latent Space","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Chitta Baral, Maitreya Patel, Sangmin Jung, Yezhou Yang","submitted_at":"2024-02-07T19:07:10Z","abstract_excerpt":"Despite the recent advances in personalized text-to-image (P-T2I) generative models, it remains challenging to perform finetuning-free multi-subject-driven T2I in a resource-efficient manner. Predominantly, contemporary approaches, involving the training of Hypernetworks and Multimodal Large Language Models (MLLMs), require heavy computing resources that range from 600 to 12300 GPU hours of training. These subject-driven T2I methods hinge on Latent Diffusion Models (LDMs), which facilitate T2I mapping through cross-attention layers. While LDMs offer distinct advantages, P-T2I methods' reliance"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2402.05195","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-07T19:07:10Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"c5a7cbec4529c274c86521b65ddff780bc4c0c156cd9525c0adde4f76ad5f214","abstract_canon_sha256":"00bfe71c6cfbeb8e1650d71879a0540ee86f225217e82be9df22081eb910b911"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:06:12.492255Z","signature_b64":"cpQKosVKRYfGMplllbH14bWzSjLUmjvawp1bGVVv+v0SqSPWPhqoq+QpXHS9aDP5xfvkdU+HotfjrBHMs7C7BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2326e1b4acbcb5a3b9aba8f6da1d1bda775d603aecfac5c31cc9213b551795e1","last_reissued_at":"2026-07-05T08:06:12.491801Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:06:12.491801Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"$\\lambda$-ECLIPSE: Multi-Concept Personalized Text-to-Image Diffusion Models by Leveraging CLIP Latent Space","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Chitta Baral, Maitreya Patel, Sangmin Jung, Yezhou Yang","submitted_at":"2024-02-07T19:07:10Z","abstract_excerpt":"Despite the recent advances in personalized text-to-image (P-T2I) generative models, it remains challenging to perform finetuning-free multi-subject-driven T2I in a resource-efficient manner. Predominantly, contemporary approaches, involving the training of Hypernetworks and Multimodal Large Language Models (MLLMs), require heavy computing resources that range from 600 to 12300 GPU hours of training. These subject-driven T2I methods hinge on Latent Diffusion Models (LDMs), which facilitate T2I mapping through cross-attention layers. While LDMs offer distinct advantages, P-T2I methods' reliance"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.05195","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2402.05195/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2402.05195","created_at":"2026-07-05T08:06:12.491856+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.05195v2","created_at":"2026-07-05T08:06:12.491856+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.05195","created_at":"2026-07-05T08:06:12.491856+00:00"},{"alias_kind":"pith_short_12","alias_value":"EMTODNFMXS22","created_at":"2026-07-05T08:06:12.491856+00:00"},{"alias_kind":"pith_short_16","alias_value":"EMTODNFMXS22HONL","created_at":"2026-07-05T08:06:12.491856+00:00"},{"alias_kind":"pith_short_8","alias_value":"EMTODNFM","created_at":"2026-07-05T08:06:12.491856+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2510.20512","citing_title":"Adversarial Concept Distillation for One-Step Diffusion Personalization","ref_index":61,"is_internal_anchor":false},{"citing_arxiv_id":"2603.08090","citing_title":"DSH-Bench: A Difficulty- and Scenario-Aware Benchmark with Hierarchical Subject Taxonomy for Subject-Driven Text-to-Image Generation","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06074","citing_title":"Graph-PiT: Enhancing Structural Coherence in Part-Based Image Synthesis via Graph Priors","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EMTODNFMXS22HONLVD3NUHI33J","json":"https://pith.science/pith/EMTODNFMXS22HONLVD3NUHI33J.json","graph_json":"https://pith.science/api/pith-number/EMTODNFMXS22HONLVD3NUHI33J/graph.json","events_json":"https://pith.science/api/pith-number/EMTODNFMXS22HONLVD3NUHI33J/events.json","paper":"https://pith.science/paper/EMTODNFM"},"agent_actions":{"view_html":"https://pith.science/pith/EMTODNFMXS22HONLVD3NUHI33J","download_json":"https://pith.science/pith/EMTODNFMXS22HONLVD3NUHI33J.json","view_paper":"https://pith.science/paper/EMTODNFM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.05195&json=true","fetch_graph":"https://pith.science/api/pith-number/EMTODNFMXS22HONLVD3NUHI33J/graph.json","fetch_events":"https://pith.science/api/pith-number/EMTODNFMXS22HONLVD3NUHI33J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EMTODNFMXS22HONLVD3NUHI33J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EMTODNFMXS22HONLVD3NUHI33J/action/storage_attestation","attest_author":"https://pith.science/pith/EMTODNFMXS22HONLVD3NUHI33J/action/author_attestation","sign_citation":"https://pith.science/pith/EMTODNFMXS22HONLVD3NUHI33J/action/citation_signature","submit_replication":"https://pith.science/pith/EMTODNFMXS22HONLVD3NUHI33J/action/replication_record"}},"created_at":"2026-07-05T08:06:12.491856+00:00","updated_at":"2026-07-05T08:06:12.491856+00:00"}