{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:NOITT5ANB73HZA6G4RIM3W3KDY","short_pith_number":"pith:NOITT5AN","schema_version":"1.0","canonical_sha256":"6b9139f40d0ff67c83c6e450cddb6a1e3279672585a73adc76e838fd4e69dbb1","source":{"kind":"arxiv","id":"2112.07804","version":2},"attestation_state":"computed","paper":{"title":"Tackling the Generative Learning Trilemma with Denoising Diffusion GANs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Arash Vahdat, Karsten Kreis, Zhisheng Xiao","submitted_at":"2021-12-15T00:09:38Z","abstract_excerpt":"A wide variety of deep generative models has been developed in the past decade. Yet, these models often struggle with simultaneously addressing three key requirements including: high sample quality, mode coverage, and fast sampling. We call the challenge imposed by these requirements the generative learning trilemma, as the existing models often trade some of them for others. Particularly, denoising diffusion models have shown impressive sample quality and diversity, but their expensive sampling does not yet allow them to be applied in many real-world applications. In this paper, we argue that"},"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":"2112.07804","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-15T00:09:38Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"2c2dbf292a387b20b1c185c985bce37090b4bfe383d3c6caa45b47980eb5825d","abstract_canon_sha256":"19c0c849ebdda78ac483eeb07e58b0764678ce30451a6ee45406c86741eba466"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:11:29.346563Z","signature_b64":"lcIzqo957RhMmWeaoFH5qbkdZtlyXh363z2kol7XR9Kc/kZ9PDadLTF48DuNnSvr5tcaWzw4njBpDFSTWF3gCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6b9139f40d0ff67c83c6e450cddb6a1e3279672585a73adc76e838fd4e69dbb1","last_reissued_at":"2026-07-05T04:11:29.346160Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:11:29.346160Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Tackling the Generative Learning Trilemma with Denoising Diffusion GANs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Arash Vahdat, Karsten Kreis, Zhisheng Xiao","submitted_at":"2021-12-15T00:09:38Z","abstract_excerpt":"A wide variety of deep generative models has been developed in the past decade. Yet, these models often struggle with simultaneously addressing three key requirements including: high sample quality, mode coverage, and fast sampling. We call the challenge imposed by these requirements the generative learning trilemma, as the existing models often trade some of them for others. Particularly, denoising diffusion models have shown impressive sample quality and diversity, but their expensive sampling does not yet allow them to be applied in many real-world applications. In this paper, we argue that"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.07804","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/2112.07804/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":"2112.07804","created_at":"2026-07-05T04:11:29.346214+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.07804v2","created_at":"2026-07-05T04:11:29.346214+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.07804","created_at":"2026-07-05T04:11:29.346214+00:00"},{"alias_kind":"pith_short_12","alias_value":"NOITT5ANB73H","created_at":"2026-07-05T04:11:29.346214+00:00"},{"alias_kind":"pith_short_16","alias_value":"NOITT5ANB73HZA6G","created_at":"2026-07-05T04:11:29.346214+00:00"},{"alias_kind":"pith_short_8","alias_value":"NOITT5AN","created_at":"2026-07-05T04:11:29.346214+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23267","citing_title":"Safe Few-Step Generation via Velocity Editing","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2606.19162","citing_title":"The Reward Was in Your Data All Along: Correcting Flow Matching with Discriminator-Guided RL","ref_index":162,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00630","citing_title":"A Systematic Benchmark of Intraoperative Ultrasound-to-MR Synthesis for Brain Tumour Surgery","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2304.12906","citing_title":"The Score-Difference Flow for Implicit Generative Modeling","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2412.15689","citing_title":"DOLLAR: Few-Step Video Generation via Distillation and Latent Reward Optimization","ref_index":64,"is_internal_anchor":false},{"citing_arxiv_id":"2505.09831","citing_title":"IMPLICITSTAINER: Resolution Agnostic Data-Efficient Virtual Staining Using Neural Implicit Functions","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2209.14577","citing_title":"Rectified Flow: A Marginal Preserving Approach to Optimal Transport","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2208.06193","citing_title":"Diffusion Policies as an Expressive Policy Class for Offline Reinforcement Learning","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22379","citing_title":"Efficient Diffusion Distillation via Embedding Loss","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18343","citing_title":"DAG-STL: A Hierarchical Framework for Zero-Shot Trajectory Planning under Signal Temporal Logic Specifications","ref_index":80,"is_internal_anchor":false},{"citing_arxiv_id":"2209.03003","citing_title":"Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow","ref_index":91,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NOITT5ANB73HZA6G4RIM3W3KDY","json":"https://pith.science/pith/NOITT5ANB73HZA6G4RIM3W3KDY.json","graph_json":"https://pith.science/api/pith-number/NOITT5ANB73HZA6G4RIM3W3KDY/graph.json","events_json":"https://pith.science/api/pith-number/NOITT5ANB73HZA6G4RIM3W3KDY/events.json","paper":"https://pith.science/paper/NOITT5AN"},"agent_actions":{"view_html":"https://pith.science/pith/NOITT5ANB73HZA6G4RIM3W3KDY","download_json":"https://pith.science/pith/NOITT5ANB73HZA6G4RIM3W3KDY.json","view_paper":"https://pith.science/paper/NOITT5AN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.07804&json=true","fetch_graph":"https://pith.science/api/pith-number/NOITT5ANB73HZA6G4RIM3W3KDY/graph.json","fetch_events":"https://pith.science/api/pith-number/NOITT5ANB73HZA6G4RIM3W3KDY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NOITT5ANB73HZA6G4RIM3W3KDY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NOITT5ANB73HZA6G4RIM3W3KDY/action/storage_attestation","attest_author":"https://pith.science/pith/NOITT5ANB73HZA6G4RIM3W3KDY/action/author_attestation","sign_citation":"https://pith.science/pith/NOITT5ANB73HZA6G4RIM3W3KDY/action/citation_signature","submit_replication":"https://pith.science/pith/NOITT5ANB73HZA6G4RIM3W3KDY/action/replication_record"}},"created_at":"2026-07-05T04:11:29.346214+00:00","updated_at":"2026-07-05T04:11:29.346214+00:00"}