{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:TO5LNQAULC37754HUKVIECMLVH","short_pith_number":"pith:TO5LNQAU","schema_version":"1.0","canonical_sha256":"9bbab6c01458b7fff787a2aa82098ba9fdfc03781396732efe8ed18554d70459","source":{"kind":"arxiv","id":"2606.12575","version":1},"attestation_state":"computed","paper":{"title":"High-Fidelity Two-Step Image Generation via Teacher-Aligned End-to-End Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"David Liu, Dengyang Jiang, Dongyang Liu, Hongsheng Li, Liangchen Li, Peng Gao, Qilong Wu, Ruoyi Du, Steven C.H. Hoi, Zhen Li","submitted_at":"2026-06-10T18:24:50Z","abstract_excerpt":"Few-step diffusion distillation has become increasingly mature for 4-8-step generation, yet pushing further to 2 steps remains challenging. In this work, we introduce Z-Image Turbo++, a high-quality 2-step image generation model distilled from the 8-step Z-Image Turbo teacher. Our method addresses the central bottlenecks of increased task difficulty and limited model capacity in 2-step generation through three simple but effective design choices tailored to this regime. First, we propose Distribution-Aligned Adversarial Learning, which uses teacher-generated images rather than external real im"},"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":"2606.12575","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-10T18:24:50Z","cross_cats_sorted":[],"title_canon_sha256":"6a6ae6d249bf37902d19923a83c566689f60e7d63242368e25bf2f766fe76caa","abstract_canon_sha256":"ad8bb675c2de4bc420bc24c3fc0bf78582e8f2b54afabe7e93bd1d978f68a188"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-12T00:07:55.311513Z","signature_b64":"ELqPIg2JI3lZOMkw7AS+K1mvsFbfFSp9Xc7JsUR69VBOgdq7aZYCfuaT2MTJtVV5hY7Lf5K4SjhzsAq2b7bSCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9bbab6c01458b7fff787a2aa82098ba9fdfc03781396732efe8ed18554d70459","last_reissued_at":"2026-06-12T00:07:55.310860Z","signature_status":"signed_v1","first_computed_at":"2026-06-12T00:07:55.310860Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"High-Fidelity Two-Step Image Generation via Teacher-Aligned End-to-End Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"David Liu, Dengyang Jiang, Dongyang Liu, Hongsheng Li, Liangchen Li, Peng Gao, Qilong Wu, Ruoyi Du, Steven C.H. Hoi, Zhen Li","submitted_at":"2026-06-10T18:24:50Z","abstract_excerpt":"Few-step diffusion distillation has become increasingly mature for 4-8-step generation, yet pushing further to 2 steps remains challenging. In this work, we introduce Z-Image Turbo++, a high-quality 2-step image generation model distilled from the 8-step Z-Image Turbo teacher. Our method addresses the central bottlenecks of increased task difficulty and limited model capacity in 2-step generation through three simple but effective design choices tailored to this regime. First, we propose Distribution-Aligned Adversarial Learning, which uses teacher-generated images rather than external real im"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.12575","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/2606.12575/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":"2606.12575","created_at":"2026-06-12T00:07:55.310953+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.12575v1","created_at":"2026-06-12T00:07:55.310953+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.12575","created_at":"2026-06-12T00:07:55.310953+00:00"},{"alias_kind":"pith_short_12","alias_value":"TO5LNQAULC37","created_at":"2026-06-12T00:07:55.310953+00:00"},{"alias_kind":"pith_short_16","alias_value":"TO5LNQAULC37754H","created_at":"2026-06-12T00:07:55.310953+00:00"},{"alias_kind":"pith_short_8","alias_value":"TO5LNQAU","created_at":"2026-06-12T00:07:55.310953+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TO5LNQAULC37754HUKVIECMLVH","json":"https://pith.science/pith/TO5LNQAULC37754HUKVIECMLVH.json","graph_json":"https://pith.science/api/pith-number/TO5LNQAULC37754HUKVIECMLVH/graph.json","events_json":"https://pith.science/api/pith-number/TO5LNQAULC37754HUKVIECMLVH/events.json","paper":"https://pith.science/paper/TO5LNQAU"},"agent_actions":{"view_html":"https://pith.science/pith/TO5LNQAULC37754HUKVIECMLVH","download_json":"https://pith.science/pith/TO5LNQAULC37754HUKVIECMLVH.json","view_paper":"https://pith.science/paper/TO5LNQAU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.12575&json=true","fetch_graph":"https://pith.science/api/pith-number/TO5LNQAULC37754HUKVIECMLVH/graph.json","fetch_events":"https://pith.science/api/pith-number/TO5LNQAULC37754HUKVIECMLVH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TO5LNQAULC37754HUKVIECMLVH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TO5LNQAULC37754HUKVIECMLVH/action/storage_attestation","attest_author":"https://pith.science/pith/TO5LNQAULC37754HUKVIECMLVH/action/author_attestation","sign_citation":"https://pith.science/pith/TO5LNQAULC37754HUKVIECMLVH/action/citation_signature","submit_replication":"https://pith.science/pith/TO5LNQAULC37754HUKVIECMLVH/action/replication_record"}},"created_at":"2026-06-12T00:07:55.310953+00:00","updated_at":"2026-06-12T00:07:55.310953+00:00"}