{"work":{"id":"83654cbd-832b-4269-bec9-26faa87ececd","openalex_id":null,"doi":null,"arxiv_id":"2209.15571","raw_key":null,"title":"Building Normalizing Flows with Stochastic Interpolants","authors":null,"authors_text":"Michael S. Albergo, Eric Vanden-Eijnden","year":2022,"venue":"cs.LG","abstract":"A generative model based on a continuous-time normalizing flow between any pair of base and target probability densities is proposed. The velocity field of this flow is inferred from the probability current of a time-dependent density that interpolates between the base and the target in finite time. Unlike conventional normalizing flow inference methods based the maximum likelihood principle, which require costly backpropagation through ODE solvers, our interpolant approach leads to a simple quadratic loss for the velocity itself which is expressed in terms of expectations that are readily amenable to empirical estimation. The flow can be used to generate samples from either the base or target, and to estimate the likelihood at any time along the interpolant. In addition, the flow can be optimized to minimize the path length of the interpolant density, thereby paving the way for building optimal transport maps. In situations where the base is a Gaussian density, we also show that the velocity of our normalizing flow can also be used to construct a diffusion model to sample the target as well as estimate its score. However, our approach shows that we can bypass this diffusion completely and work at the level of the probability flow with greater simplicity, opening an avenue for methods based solely on ordinary differential equations as an alternative to those based on stochastic differential equations. Benchmarking on density estimation tasks illustrates that the learned flow can match and surpass conventional continuous flows at a fraction of the cost, and compares well with diffusions on image generation on CIFAR-10 and ImageNet $32\\times32$. The method scales ab-initio ODE flows to previously unreachable image resolutions, demonstrated up to $128\\times128$.","external_url":"https://arxiv.org/abs/2209.15571","cited_by_count":null,"metadata_source":"pith","metadata_fetched_at":"2026-05-25T08:36:48.435371+00:00","pith_arxiv_id":"2209.15571","created_at":"2026-05-10T06:06:19.010592+00:00","updated_at":"2026-05-25T08:36:48.435371+00:00","title_quality_ok":true,"display_title":"Building Normalizing Flows with Stochastic Interpolants","render_title":"Building Normalizing Flows with Stochastic Interpolants"},"hub":{"state":{"work_id":"83654cbd-832b-4269-bec9-26faa87ececd","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":57,"external_cited_by_count":null,"distinct_field_count":13,"first_pith_cited_at":"2023-11-08T00:24:50+00:00","last_pith_cited_at":"2026-05-21T14:17:21+00:00","author_build_status":"not_needed","summary_status":"needed","contexts_status":"needed","graph_status":"needed","ask_index_status":"not_needed","reader_status":"not_needed","recognition_status":"not_needed","updated_at":"2026-05-31T10:02:20.833110+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":12},{"context_role":"method","n":10}],"polarity_counts":[{"context_polarity":"background","n":12},{"context_polarity":"use_method","n":10}],"runs":{"context_extract":{"job_type":"context_extract","status":"succeeded","result":{"enqueued_papers":25},"error":null,"updated_at":"2026-05-14T18:20:13.261457+00:00"},"graph_features":{"job_type":"graph_features","status":"succeeded","result":{"co_cited":[{"title":"Flow Matching for Generative Modeling","work_id":"6edb71c4-5d64-40af-a394-9757ea051a36","shared_citers":28},{"title":"Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow","work_id":"a1989e1b-d66d-4533-be3a-fb9c5fd62290","shared_citers":26},{"title":"Score-Based Generative Modeling through Stochastic Differential Equations","work_id":"d9110e53-a5d4-4794-a4c5-a575e91c31ad","shared_citers":13},{"title":"Improving and generalizing flow-based generative models with minibatch optimal transport","work_id":"7b689852-603d-46be-aaa5-c38325ba2182","shared_citers":10},{"title":"Classifier-Free Diffusion Guidance","work_id":"acf2c588-c088-4a6c-938e-150ad7c666d7","shared_citers":7},{"title":"Progressive Distillation for Fast Sampling of Diffusion Models","work_id":"fd04f498-ff85-4de3-bcc7-31ef072b2ceb","shared_citers":7},{"title":"Stochastic Interpolants: A Unifying Framework for Flows and Diffusions","work_id":"c2c7dd8f-fbfb-4591-89ec-9a3a0e6744bd","shared_citers":7},{"title":"Denoising Diffusion Implicit Models","work_id":"8fa2128b-d18c-405c-ac92-0e669cf89ac0","shared_citers":6},{"title":"Mean Flows for One-step Generative Modeling","work_id":"07a52ad5-0f82-4095-9a66-559b09fea1ae","shared_citers":6},{"title":"arXiv preprint arXiv:1810.01367 , year=","work_id":"4e8ec919-d6eb-46d4-b10d-8a9c7af0126d","shared_citers":5},{"title":"Auto-Encoding Variational Bayes","work_id":"97d95295-30e1-42b4-bbf6-85f0fa4edb44","shared_citers":5},{"title":"Flow Matching Guide and Code","work_id":"2be93143-ab6f-48d6-96d5-3e85d7246f07","shared_citers":5},{"title":"HunyuanVideo: A Systematic Framework For Large Video Generative Models","work_id":"881efa7e-7e73-4c66-9cc3-2803e551061c","shared_citers":4},{"title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","work_id":"4f68eada-27e3-437a-a2fe-6e4ca524d0d3","shared_citers":4},{"title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","work_id":"c5006563-f3ec-438a-9e35-b7b484f34828","shared_citers":3},{"title":"DINOv2: Learning Robust Visual Features without Supervision","work_id":"26b304e5-b54a-4f26-be7e-83299eca52e4","shared_citers":3},{"title":"Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems","work_id":"597b6f46-d60f-451f-8f34-7d32876a9014","shared_citers":3},{"title":"Offline Reinforcement Learning with Implicit Q-Learning","work_id":"4adca4ff-8975-49b3-aee4-2ef7e0f95275","shared_citers":3},{"title":"Ogbench: Benchmarking offline goal-conditioned rl","work_id":"f84e0fbd-005f-4e9d-9d5f-4c39b8222a5d","shared_citers":3},{"title":"Prompt-to-Prompt Image Editing with Cross Attention Control","work_id":"196f7eef-d65a-47e4-b815-9a188f6aedcf","shared_citers":3},{"title":"Proximal Policy Optimization Algorithms","work_id":"240c67fe-d14d-4520-91c1-38a4e272ca19","shared_citers":3},{"title":"Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think","work_id":"1aff8ef8-079b-4afe-9e6a-148e6fd08e6a","shared_citers":3},{"title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","work_id":"8034c587-fba6-4941-87ba-c98f2ac962cb","shared_citers":3},{"title":"Wan: Open and Advanced Large-Scale Video Generative Models","work_id":"ad3ebc3b-4224-46c9-b61d-bcf135da0a7c","shared_citers":3}],"time_series":[{"n":1,"year":2024},{"n":3,"year":2025},{"n":30,"year":2026}],"dependency_candidates":[]},"error":null,"updated_at":"2026-05-14T18:19:50.459416+00:00"},"identity_refresh":{"job_type":"identity_refresh","status":"succeeded","result":{"items":[{"title":"Qwen3 Technical Report","outcome":"unchanged","work_id":"25a4e30c-1232-48e7-9925-02fa12ba7c9e","resolver":"local_arxiv","confidence":0.98,"old_work_id":"25a4e30c-1232-48e7-9925-02fa12ba7c9e"}],"counts":{"fixed":0,"merged":0,"unchanged":1,"quarantined":0,"needs_external_resolution":0},"errors":[],"attempted":1},"error":null,"updated_at":"2026-05-14T18:19:25.424507+00:00"},"summary_claims":{"job_type":"summary_claims","status":"succeeded","result":{"title":"Building Normalizing Flows with Stochastic Interpolants","claims":[{"claim_text":"A generative model based on a continuous-time normalizing flow between any pair of base and target probability densities is proposed. The velocity field of this flow is inferred from the probability current of a time-dependent density that interpolates between the base and the target in finite time. Unlike conventional normalizing flow inference methods based the maximum likelihood principle, which require costly backpropagation through ODE solvers, our interpolant approach leads to a simple quadratic loss for the velocity itself which is expressed in terms of expectations that are readily ame","claim_type":"abstract","evidence_strength":"source_metadata"}],"why_cited":"Pith tracks Building Normalizing Flows with Stochastic Interpolants because it crossed a citation-hub threshold.","role_counts":[]},"error":null,"updated_at":"2026-05-14T18:20:27.144130+00:00"}},"summary":{"title":"Building Normalizing Flows with Stochastic Interpolants","claims":[{"claim_text":"A generative model based on a continuous-time normalizing flow between any pair of base and target probability densities is proposed. The velocity field of this flow is inferred from the probability current of a time-dependent density that interpolates between the base and the target in finite time. Unlike conventional normalizing flow inference methods based the maximum likelihood principle, which require costly backpropagation through ODE solvers, our interpolant approach leads to a simple quadratic loss for the velocity itself which is expressed in terms of expectations that are readily ame","claim_type":"abstract","evidence_strength":"source_metadata"}],"why_cited":"Pith tracks Building Normalizing Flows with Stochastic Interpolants because it crossed a citation-hub threshold.","role_counts":[]},"graph":{"co_cited":[{"title":"Flow Matching for Generative Modeling","work_id":"6edb71c4-5d64-40af-a394-9757ea051a36","shared_citers":28},{"title":"Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow","work_id":"a1989e1b-d66d-4533-be3a-fb9c5fd62290","shared_citers":26},{"title":"Score-Based Generative Modeling through Stochastic Differential Equations","work_id":"d9110e53-a5d4-4794-a4c5-a575e91c31ad","shared_citers":13},{"title":"Improving and generalizing flow-based generative models with minibatch optimal transport","work_id":"7b689852-603d-46be-aaa5-c38325ba2182","shared_citers":10},{"title":"Classifier-Free Diffusion Guidance","work_id":"acf2c588-c088-4a6c-938e-150ad7c666d7","shared_citers":7},{"title":"Progressive Distillation for Fast Sampling of Diffusion Models","work_id":"fd04f498-ff85-4de3-bcc7-31ef072b2ceb","shared_citers":7},{"title":"Stochastic Interpolants: A Unifying Framework for Flows and Diffusions","work_id":"c2c7dd8f-fbfb-4591-89ec-9a3a0e6744bd","shared_citers":7},{"title":"Denoising Diffusion Implicit Models","work_id":"8fa2128b-d18c-405c-ac92-0e669cf89ac0","shared_citers":6},{"title":"Mean Flows for One-step Generative Modeling","work_id":"07a52ad5-0f82-4095-9a66-559b09fea1ae","shared_citers":6},{"title":"arXiv preprint arXiv:1810.01367 , year=","work_id":"4e8ec919-d6eb-46d4-b10d-8a9c7af0126d","shared_citers":5},{"title":"Auto-Encoding Variational Bayes","work_id":"97d95295-30e1-42b4-bbf6-85f0fa4edb44","shared_citers":5},{"title":"Flow Matching Guide and Code","work_id":"2be93143-ab6f-48d6-96d5-3e85d7246f07","shared_citers":5},{"title":"HunyuanVideo: A Systematic Framework For Large Video Generative Models","work_id":"881efa7e-7e73-4c66-9cc3-2803e551061c","shared_citers":4},{"title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","work_id":"4f68eada-27e3-437a-a2fe-6e4ca524d0d3","shared_citers":4},{"title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","work_id":"c5006563-f3ec-438a-9e35-b7b484f34828","shared_citers":3},{"title":"DINOv2: Learning Robust Visual Features without Supervision","work_id":"26b304e5-b54a-4f26-be7e-83299eca52e4","shared_citers":3},{"title":"Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems","work_id":"597b6f46-d60f-451f-8f34-7d32876a9014","shared_citers":3},{"title":"Offline Reinforcement Learning with Implicit Q-Learning","work_id":"4adca4ff-8975-49b3-aee4-2ef7e0f95275","shared_citers":3},{"title":"Ogbench: Benchmarking offline goal-conditioned rl","work_id":"f84e0fbd-005f-4e9d-9d5f-4c39b8222a5d","shared_citers":3},{"title":"Prompt-to-Prompt Image Editing with Cross Attention Control","work_id":"196f7eef-d65a-47e4-b815-9a188f6aedcf","shared_citers":3},{"title":"Proximal Policy Optimization Algorithms","work_id":"240c67fe-d14d-4520-91c1-38a4e272ca19","shared_citers":3},{"title":"Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think","work_id":"1aff8ef8-079b-4afe-9e6a-148e6fd08e6a","shared_citers":3},{"title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","work_id":"8034c587-fba6-4941-87ba-c98f2ac962cb","shared_citers":3},{"title":"Wan: Open and Advanced Large-Scale Video Generative Models","work_id":"ad3ebc3b-4224-46c9-b61d-bcf135da0a7c","shared_citers":3}],"time_series":[{"n":1,"year":2024},{"n":3,"year":2025},{"n":30,"year":2026}],"dependency_candidates":[]},"authors":[]}}