{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:DT4W3ZITAWJMV6QIQAYMCL5XRZ","short_pith_number":"pith:DT4W3ZIT","schema_version":"1.0","canonical_sha256":"1cf96de5130592cafa088030c12fb78e6a2c974fbad9786cee1552a43ee497c8","source":{"kind":"arxiv","id":"2307.08698","version":1},"attestation_state":"computed","paper":{"title":"Flow Matching in Latent Space","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Anh Tran, Binh Nguyen, Hao Phung, Quan Dao","submitted_at":"2023-07-17T17:57:56Z","abstract_excerpt":"Flow matching is a recent framework to train generative models that exhibits impressive empirical performance while being relatively easier to train compared with diffusion-based models. Despite its advantageous properties, prior methods still face the challenges of expensive computing and a large number of function evaluations of off-the-shelf solvers in the pixel space. Furthermore, although latent-based generative methods have shown great success in recent years, this particular model type remains underexplored in this area. In this work, we propose to apply flow matching in the latent spac"},"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":"2307.08698","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-17T17:57:56Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"253b3c8a401daedd30f135f0d03d6d750228e7191c0aebe3111328f6c723ee29","abstract_canon_sha256":"0833c9a5944f4c8e8597ce2abc6db8d297b1eabcceeecc0c6497a546a39727aa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:31:27.807847Z","signature_b64":"6fe2ExOR4poN45e7S1L2RX6vFwAm4dZ7bOA6k3nHTtl3LLOvzopyLRUzFwVDRjIErWeQuHf5VAJILbbqzxHbBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1cf96de5130592cafa088030c12fb78e6a2c974fbad9786cee1552a43ee497c8","last_reissued_at":"2026-07-05T06:31:27.807353Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:31:27.807353Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Flow Matching in Latent Space","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Anh Tran, Binh Nguyen, Hao Phung, Quan Dao","submitted_at":"2023-07-17T17:57:56Z","abstract_excerpt":"Flow matching is a recent framework to train generative models that exhibits impressive empirical performance while being relatively easier to train compared with diffusion-based models. Despite its advantageous properties, prior methods still face the challenges of expensive computing and a large number of function evaluations of off-the-shelf solvers in the pixel space. Furthermore, although latent-based generative methods have shown great success in recent years, this particular model type remains underexplored in this area. In this work, we propose to apply flow matching in the latent spac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.08698","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/2307.08698/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":"2307.08698","created_at":"2026-07-05T06:31:27.807414+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.08698v1","created_at":"2026-07-05T06:31:27.807414+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.08698","created_at":"2026-07-05T06:31:27.807414+00:00"},{"alias_kind":"pith_short_12","alias_value":"DT4W3ZITAWJM","created_at":"2026-07-05T06:31:27.807414+00:00"},{"alias_kind":"pith_short_16","alias_value":"DT4W3ZITAWJMV6QI","created_at":"2026-07-05T06:31:27.807414+00:00"},{"alias_kind":"pith_short_8","alias_value":"DT4W3ZIT","created_at":"2026-07-05T06:31:27.807414+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":25,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06281","citing_title":"Straight-Path Flow Matching for Incomplete Multi-View Clustering","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2606.24375","citing_title":"MATCH: Flow Matching for Multi-View Anomaly Detection","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27377","citing_title":"DanceOPD: On-Policy Generative Field Distillation","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2606.22424","citing_title":"FlowDec: Temporal Conditional Flow Decorruptor for Robust Continuous Vision-Language Navigation","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00535","citing_title":"Flow-Map GRPO: Reinforcement Learning for Few-Step Flow-Map Generators via Anchored Stochastic Composition","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05552","citing_title":"Balancing Image Compression and Generation with Bootstrapped Tokenization","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29287","citing_title":"Beyond Trajectory Matching: Reflow with Marginal Distribution Alignment","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25413","citing_title":"Autoregression-Free Neural Operators for Time-Dependent PDEs","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2410.07430","citing_title":"EventFlow: Forecasting Temporal Point Processes with Flow Matching","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2502.02514","citing_title":"Privacy Attacks on Image AutoRegressive Models","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2509.24517","citing_title":"Physics Priors Offer Useful Accuracy-Carbon Trade-Offs in Spatio-Temporal Forecasting","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20640","citing_title":"Pareto-Enhanced Portrait Generation: Vision-Aligned Text Supervision for Alignment, Realism, and Aesthetics","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16573","citing_title":"Wavelet Flow Matching for Multi-Scale Physics Emulation","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19771","citing_title":"Beyond Imitation: Learning Safe End-to-End Autonomous Driving from Hard Negatives","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2506.02276","citing_title":"Latent Stochastic Interpolants","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2601.15884","citing_title":"Contrast-X: A Multi-Modal Contrast Image Synthesis Benchmark and Universal Modality Flow Matching","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2601.21831","citing_title":"Generative Modeling of Discrete Data Using Geometric Latent Subspaces","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2603.26357","citing_title":"MPDiT: Multi-Patch Global-to-Local Transformer Architecture For Efficient Flow Matching and Diffusion Model","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12754","citing_title":"Constraint-Aware Flow Matching: Decision Aligned End-to-End Training for Constrained Sampling","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03623","citing_title":"A Few-Step Generative Model on Cumulative Flow Maps","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06124","citing_title":"P-Guide: Parameter-Efficient Prior Steering for Single-Pass CFG Inference","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06364","citing_title":"Flow Matching with Arbitrary Auxiliary Paths","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07456","citing_title":"Inference-Time Attribute Distribution Alignment for Unconditional Diffusion","ref_index":76,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06701","citing_title":"Bi-Lipschitz Autoencoder With Injectivity Guarantee","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04487","citing_title":"Training-Free Image Editing with Visual Context Integration and Concept Alignment","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DT4W3ZITAWJMV6QIQAYMCL5XRZ","json":"https://pith.science/pith/DT4W3ZITAWJMV6QIQAYMCL5XRZ.json","graph_json":"https://pith.science/api/pith-number/DT4W3ZITAWJMV6QIQAYMCL5XRZ/graph.json","events_json":"https://pith.science/api/pith-number/DT4W3ZITAWJMV6QIQAYMCL5XRZ/events.json","paper":"https://pith.science/paper/DT4W3ZIT"},"agent_actions":{"view_html":"https://pith.science/pith/DT4W3ZITAWJMV6QIQAYMCL5XRZ","download_json":"https://pith.science/pith/DT4W3ZITAWJMV6QIQAYMCL5XRZ.json","view_paper":"https://pith.science/paper/DT4W3ZIT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.08698&json=true","fetch_graph":"https://pith.science/api/pith-number/DT4W3ZITAWJMV6QIQAYMCL5XRZ/graph.json","fetch_events":"https://pith.science/api/pith-number/DT4W3ZITAWJMV6QIQAYMCL5XRZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DT4W3ZITAWJMV6QIQAYMCL5XRZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DT4W3ZITAWJMV6QIQAYMCL5XRZ/action/storage_attestation","attest_author":"https://pith.science/pith/DT4W3ZITAWJMV6QIQAYMCL5XRZ/action/author_attestation","sign_citation":"https://pith.science/pith/DT4W3ZITAWJMV6QIQAYMCL5XRZ/action/citation_signature","submit_replication":"https://pith.science/pith/DT4W3ZITAWJMV6QIQAYMCL5XRZ/action/replication_record"}},"created_at":"2026-07-05T06:31:27.807414+00:00","updated_at":"2026-07-05T06:31:27.807414+00:00"}