{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BGTLGKF3TRKKQHKWH3EJ5RANWN","short_pith_number":"pith:BGTLGKF3","schema_version":"1.0","canonical_sha256":"09a6b328bb9c54a81d563ec89ec40db36531d9ed0b601508f67ec1c306b118f0","source":{"kind":"arxiv","id":"2504.02160","version":1},"attestation_state":"computed","paper":{"title":"Less-to-More Generalization: Unlocking More Controllability by In-Context Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Fei Ding, Mengqi Huang, Qian He, Shaojin Wu, Wenxu Wu, Yufeng Cheng","submitted_at":"2025-04-02T22:20:21Z","abstract_excerpt":"Although subject-driven generation has been extensively explored in image generation due to its wide applications, it still has challenges in data scalability and subject expansibility. For the first challenge, moving from curating single-subject datasets to multiple-subject ones and scaling them is particularly difficult. For the second, most recent methods center on single-subject generation, making it hard to apply when dealing with multi-subject scenarios. In this study, we propose a highly-consistent data synthesis pipeline to tackle this challenge. This pipeline harnesses the intrinsic i"},"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":"2504.02160","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-02T22:20:21Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4076ce4a526de6aa1c43616ffd9e6bb4c956d1c2f4ca3b3c94ec2894a0c011c1","abstract_canon_sha256":"adc2506997cb15573b77ee7e313d608474ad0267d30e0c246b3d60b5cabb7bef"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:43:51.527164Z","signature_b64":"YZNDvlEsxQSPmJZT9Fo/CxZiGa+Aiqo1opWr0Oe52rRlhVZ3whtRejlrsUwhzbl9Gf/7O/+UD57dqZGIwaqbBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"09a6b328bb9c54a81d563ec89ec40db36531d9ed0b601508f67ec1c306b118f0","last_reissued_at":"2026-07-05T10:43:51.526666Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:43:51.526666Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Less-to-More Generalization: Unlocking More Controllability by In-Context Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Fei Ding, Mengqi Huang, Qian He, Shaojin Wu, Wenxu Wu, Yufeng Cheng","submitted_at":"2025-04-02T22:20:21Z","abstract_excerpt":"Although subject-driven generation has been extensively explored in image generation due to its wide applications, it still has challenges in data scalability and subject expansibility. For the first challenge, moving from curating single-subject datasets to multiple-subject ones and scaling them is particularly difficult. For the second, most recent methods center on single-subject generation, making it hard to apply when dealing with multi-subject scenarios. In this study, we propose a highly-consistent data synthesis pipeline to tackle this challenge. This pipeline harnesses the intrinsic i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.02160","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2504.02160/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":"2504.02160","created_at":"2026-07-05T10:43:51.526726+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.02160v1","created_at":"2026-07-05T10:43:51.526726+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.02160","created_at":"2026-07-05T10:43:51.526726+00:00"},{"alias_kind":"pith_short_12","alias_value":"BGTLGKF3TRKK","created_at":"2026-07-05T10:43:51.526726+00:00"},{"alias_kind":"pith_short_16","alias_value":"BGTLGKF3TRKKQHKW","created_at":"2026-07-05T10:43:51.526726+00:00"},{"alias_kind":"pith_short_8","alias_value":"BGTLGKF3","created_at":"2026-07-05T10:43:51.526726+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":21,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17619","citing_title":"RAVA: Retrieval-Augmented Viewpoint Alignment for Subject-Driven Image Generation","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2607.01677","citing_title":"ICDepth: Taming Video Diffusion Models for Video Depth Estimation via In-Context Conditioning","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00351","citing_title":"UniVerse: A Unified Modulation Framework for Segmentation-Free,Disentangled Multi-Concept Personalization","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2504.15958","citing_title":"FreeGraftor: Training-Free Cross-Image Feature Grafting for Subject-Driven Text-to-Image Generation","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2603.07561","citing_title":"PureCC: Pure Learning for Text-to-Image Concept Customization","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18678","citing_title":"Lance: Unified Multimodal Modeling by Multi-Task Synergy","ref_index":129,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18678","citing_title":"Lance: Unified Multimodal Modeling by Multi-Task Synergy","ref_index":128,"is_internal_anchor":false},{"citing_arxiv_id":"2506.18871","citing_title":"OmniGen2: Towards Instruction-Aligned Multimodal Generation","ref_index":79,"is_internal_anchor":false},{"citing_arxiv_id":"2510.20512","citing_title":"Adversarial Concept Distillation for One-Step Diffusion Personalization","ref_index":98,"is_internal_anchor":false},{"citing_arxiv_id":"2510.26583","citing_title":"Emu3.5: Native Multimodal Models are World Learners","ref_index":109,"is_internal_anchor":false},{"citing_arxiv_id":"2512.01236","citing_title":"PSR: Scaling Multi-Subject Personalized Image Generation with Pairwise Subject-Consistency Rewards","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2512.12675","citing_title":"Scone: Bridging Composition and Distinction in Subject-Driven Image Generation via Unified Understanding-Generation Modeling","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2512.21788","citing_title":"InstructMoLE: Instruction-Guided Mixture of Low-rank Experts for Multi-Conditional Image Generation","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2504.20690","citing_title":"In-Context Edit: Enabling Instructional Image Editing with In-Context Generation in Large Scale Diffusion Transformer","ref_index":28,"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":67,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10127","citing_title":"Fashion130K: An E-commerce Fashion Dataset for Outfit Generation with Unified Multi-modal Condition","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10127","citing_title":"Fashion130K: An E-commerce Fashion Dataset for Outfit Generation with Unified Multi-modal Condition","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05039","citing_title":"ID-Sim: An Identity-Focused Similarity Metric","ref_index":93,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04934","citing_title":"Vanast: Virtual Try-On with Human Image Animation via Synthetic Triplet Supervision","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13938","citing_title":"ASTRA: Enhancing Multi-Subject Generation with Retrieval-Augmented Pose Guidance and Disentangled Position Embedding","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16114","citing_title":"Towards In-Context Tone Style Transfer with A Large-Scale Triplet Dataset","ref_index":44,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BGTLGKF3TRKKQHKWH3EJ5RANWN","json":"https://pith.science/pith/BGTLGKF3TRKKQHKWH3EJ5RANWN.json","graph_json":"https://pith.science/api/pith-number/BGTLGKF3TRKKQHKWH3EJ5RANWN/graph.json","events_json":"https://pith.science/api/pith-number/BGTLGKF3TRKKQHKWH3EJ5RANWN/events.json","paper":"https://pith.science/paper/BGTLGKF3"},"agent_actions":{"view_html":"https://pith.science/pith/BGTLGKF3TRKKQHKWH3EJ5RANWN","download_json":"https://pith.science/pith/BGTLGKF3TRKKQHKWH3EJ5RANWN.json","view_paper":"https://pith.science/paper/BGTLGKF3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.02160&json=true","fetch_graph":"https://pith.science/api/pith-number/BGTLGKF3TRKKQHKWH3EJ5RANWN/graph.json","fetch_events":"https://pith.science/api/pith-number/BGTLGKF3TRKKQHKWH3EJ5RANWN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BGTLGKF3TRKKQHKWH3EJ5RANWN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BGTLGKF3TRKKQHKWH3EJ5RANWN/action/storage_attestation","attest_author":"https://pith.science/pith/BGTLGKF3TRKKQHKWH3EJ5RANWN/action/author_attestation","sign_citation":"https://pith.science/pith/BGTLGKF3TRKKQHKWH3EJ5RANWN/action/citation_signature","submit_replication":"https://pith.science/pith/BGTLGKF3TRKKQHKWH3EJ5RANWN/action/replication_record"}},"created_at":"2026-07-05T10:43:51.526726+00:00","updated_at":"2026-07-05T10:43:51.526726+00:00"}