{"work":{"id":"c2c7dd8f-fbfb-4591-89ec-9a3a0e6744bd","openalex_id":null,"doi":null,"arxiv_id":"2303.08797","raw_key":null,"title":"Stochastic Interpolants: A Unifying Framework for Flows and Diffusions","authors":null,"authors_text":"Michael S. Albergo, Nicholas M. Boffi, Eric Vanden-Eijnden","year":2023,"venue":"cs.LG","abstract":"A class of generative models that unifies flow-based and diffusion-based methods is introduced. These models extend the framework proposed in Albergo and Vanden-Eijnden (2023), enabling the use of a broad class of continuous-time stochastic processes called stochastic interpolants to bridge any two probability density functions exactly in finite time. These interpolants are built by combining data from the two prescribed densities with an additional latent variable that shapes the bridge in a flexible way. The time-dependent density function of the interpolant is shown to satisfy a transport equation as well as a family of forward and backward Fokker-Planck equations with tunable diffusion coefficient. Upon consideration of the time evolution of an individual sample, this viewpoint leads to both deterministic and stochastic generative models based on probability flow equations or stochastic differential equations with an adjustable level of noise. The drift coefficients entering these models are time-dependent velocity fields characterized as the unique minimizers of simple quadratic objective functions, one of which is a new objective for the score. We show that minimization of these quadratic objectives leads to control of the likelihood for generative models built upon stochastic dynamics, while likelihood control for deterministic dynamics is more stringent. We also construct estimators for the likelihood and the cross entropy of interpolant-based generative models, and we discuss connections with other methods such as score-based diffusion models, stochastic localization, probabilistic denoising, and rectifying flows. In addition, we demonstrate that stochastic interpolants recover the Schr\\\"odinger bridge between the two target densities when explicitly optimizing over the interpolant. Finally, algorithmic aspects are discussed and the approach is illustrated on numerical examples.","external_url":"https://arxiv.org/abs/2303.08797","cited_by_count":null,"metadata_source":"pith","metadata_fetched_at":"2026-05-24T05:36:00.841081+00:00","pith_arxiv_id":"2303.08797","created_at":"2026-05-09T06:10:42.359353+00:00","updated_at":"2026-05-24T05:36:00.841081+00:00","title_quality_ok":true,"display_title":"Stochastic Interpolants: A Unifying Framework for Flows and Diffusions","render_title":"Stochastic Interpolants: A Unifying Framework for Flows and Diffusions"},"hub":{"state":{"work_id":"c2c7dd8f-fbfb-4591-89ec-9a3a0e6744bd","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":80,"external_cited_by_count":null,"distinct_field_count":17,"first_pith_cited_at":"2023-11-08T00:24:50+00:00","last_pith_cited_at":"2026-05-21T11:24:48+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":"2026-06-03T20:26:24.530546+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":11},{"context_role":"method","n":5}],"polarity_counts":[{"context_polarity":"background","n":11},{"context_polarity":"use_method","n":5}],"runs":{"context_extract":{"job_type":"context_extract","status":"succeeded","result":{"enqueued_papers":25},"error":null,"updated_at":"2026-05-14T17:36:31.924433+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":26},{"title":"Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow","work_id":"a1989e1b-d66d-4533-be3a-fb9c5fd62290","shared_citers":18},{"title":"Score-Based Generative Modeling through Stochastic Differential Equations","work_id":"d9110e53-a5d4-4794-a4c5-a575e91c31ad","shared_citers":14},{"title":"Denoising Diffusion Implicit Models","work_id":"8fa2128b-d18c-405c-ac92-0e669cf89ac0","shared_citers":11},{"title":"Classifier-Free Diffusion Guidance","work_id":"acf2c588-c088-4a6c-938e-150ad7c666d7","shared_citers":9},{"title":"Building Normalizing Flows with Stochastic Interpolants","work_id":"83654cbd-832b-4269-bec9-26faa87ececd","shared_citers":7},{"title":"Proximal Policy Optimization Algorithms","work_id":"240c67fe-d14d-4520-91c1-38a4e272ca19","shared_citers":6},{"title":"Training Diffusion Models with Reinforcement Learning","work_id":"67684dda-3930-452a-b91a-36cbb8e2e219","shared_citers":6},{"title":"Auto-Encoding Variational Bayes","work_id":"97d95295-30e1-42b4-bbf6-85f0fa4edb44","shared_citers":5},{"title":"Decoupled Weight Decay Regularization","work_id":"07ef7360-d385-4033-83f7-8384a6325204","shared_citers":5},{"title":"Improving and generalizing flow-based generative models with minibatch optimal transport","work_id":"7b689852-603d-46be-aaa5-c38325ba2182","shared_citers":5},{"title":"Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of Diffusion, March 2024","work_id":"a90058e8-51cb-4b7e-af8c-00f24d35a065","shared_citers":4},{"title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","work_id":"c5006563-f3ec-438a-9e35-b7b484f34828","shared_citers":4},{"title":"Dpm-solver: A fast ode solver for diffusion probabilistic model sampling in around 10 steps.Advances in neural information processing systems, 35:5775–5787, 2022a","work_id":"a7e16614-fbfc-45d6-8fb6-714035cb707c","shared_citers":4},{"title":"Flow Matching Guide and Code","work_id":"2be93143-ab6f-48d6-96d5-3e85d7246f07","shared_citers":4},{"title":"Lopez-Paz and M","work_id":"8350be10-3e2d-41b0-96c4-0663ca69d9dd","shared_citers":4},{"title":"Mean Flows for One-step Generative Modeling","work_id":"07a52ad5-0f82-4095-9a66-559b09fea1ae","shared_citers":4},{"title":"One step diffusion via shortcut models","work_id":"4017f821-b436-40dd-a38d-0b3bb52f7d99","shared_citers":4},{"title":"Simplifying, Stabilizing and Scaling Continuous-Time Consistency Models","work_id":"1151c0b6-2be7-436c-ab83-843d92dea769","shared_citers":4},{"title":"$\\pi_0$: A Vision-Language-Action Flow Model for General Robot Control","work_id":"f790abdc-a796-482f-a40d-f8ee035ecfc2","shared_citers":3},{"title":"Adam: A Method for Stochastic Optimization","work_id":"1910796d-9b52-4683-bf5c-de9632c1028b","shared_citers":3},{"title":"arXiv preprint arXiv:1810.01367 , year=","work_id":"4e8ec919-d6eb-46d4-b10d-8a9c7af0126d","shared_citers":3},{"title":"A survey on diffusion models for inverse problems","work_id":"f2cbc6cc-8d87-4b5d-9751-74f49d4e3b63","shared_citers":3},{"title":"Coefficients-preserving sampling for reinforcement learning with flow matching.arXiv preprint arXiv:2509.05952","work_id":"3bc58f2f-e4be-4ee5-804f-29ffd6dfdb30","shared_citers":3}],"time_series":[{"n":1,"year":2024},{"n":3,"year":2025},{"n":37,"year":2026}],"dependency_candidates":[]},"error":null,"updated_at":"2026-05-14T17:36:28.844386+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":"2026-05-14T17:36:28.772928+00:00"},"summary_claims":{"job_type":"summary_claims","status":"succeeded","result":{"title":"Stochastic Interpolants: A Unifying Framework for Flows and Diffusions","claims":[{"claim_text":"A class of generative models that unifies flow-based and diffusion-based methods is introduced. These models extend the framework proposed in Albergo and Vanden-Eijnden (2023), enabling the use of a broad class of continuous-time stochastic processes called stochastic interpolants to bridge any two probability density functions exactly in finite time. These interpolants are built by combining data from the two prescribed densities with an additional latent variable that shapes the bridge in a flexible way. The time-dependent density function of the interpolant is shown to satisfy a transport e","claim_type":"abstract","evidence_strength":"source_metadata"}],"why_cited":"Pith tracks Stochastic Interpolants: A Unifying Framework for Flows and Diffusions because it crossed a citation-hub threshold.","role_counts":[]},"error":null,"updated_at":"2026-05-14T17:36:28.809696+00:00"}},"summary":{"title":"Stochastic Interpolants: A Unifying Framework for Flows and Diffusions","claims":[{"claim_text":"A class of generative models that unifies flow-based and diffusion-based methods is introduced. These models extend the framework proposed in Albergo and Vanden-Eijnden (2023), enabling the use of a broad class of continuous-time stochastic processes called stochastic interpolants to bridge any two probability density functions exactly in finite time. These interpolants are built by combining data from the two prescribed densities with an additional latent variable that shapes the bridge in a flexible way. The time-dependent density function of the interpolant is shown to satisfy a transport e","claim_type":"abstract","evidence_strength":"source_metadata"}],"why_cited":"Pith tracks Stochastic Interpolants: A Unifying Framework for Flows and Diffusions 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":26},{"title":"Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow","work_id":"a1989e1b-d66d-4533-be3a-fb9c5fd62290","shared_citers":18},{"title":"Score-Based Generative Modeling through Stochastic Differential Equations","work_id":"d9110e53-a5d4-4794-a4c5-a575e91c31ad","shared_citers":14},{"title":"Denoising Diffusion Implicit Models","work_id":"8fa2128b-d18c-405c-ac92-0e669cf89ac0","shared_citers":11},{"title":"Classifier-Free Diffusion Guidance","work_id":"acf2c588-c088-4a6c-938e-150ad7c666d7","shared_citers":9},{"title":"Building Normalizing Flows with Stochastic Interpolants","work_id":"83654cbd-832b-4269-bec9-26faa87ececd","shared_citers":7},{"title":"Proximal Policy Optimization Algorithms","work_id":"240c67fe-d14d-4520-91c1-38a4e272ca19","shared_citers":6},{"title":"Training Diffusion Models with Reinforcement Learning","work_id":"67684dda-3930-452a-b91a-36cbb8e2e219","shared_citers":6},{"title":"Auto-Encoding Variational Bayes","work_id":"97d95295-30e1-42b4-bbf6-85f0fa4edb44","shared_citers":5},{"title":"Decoupled Weight Decay Regularization","work_id":"07ef7360-d385-4033-83f7-8384a6325204","shared_citers":5},{"title":"Improving and generalizing flow-based generative models with minibatch optimal transport","work_id":"7b689852-603d-46be-aaa5-c38325ba2182","shared_citers":5},{"title":"Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of Diffusion, March 2024","work_id":"a90058e8-51cb-4b7e-af8c-00f24d35a065","shared_citers":4},{"title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","work_id":"c5006563-f3ec-438a-9e35-b7b484f34828","shared_citers":4},{"title":"Dpm-solver: A fast ode solver for diffusion probabilistic model sampling in around 10 steps.Advances in neural information processing systems, 35:5775–5787, 2022a","work_id":"a7e16614-fbfc-45d6-8fb6-714035cb707c","shared_citers":4},{"title":"Flow Matching Guide and Code","work_id":"2be93143-ab6f-48d6-96d5-3e85d7246f07","shared_citers":4},{"title":"Lopez-Paz and M","work_id":"8350be10-3e2d-41b0-96c4-0663ca69d9dd","shared_citers":4},{"title":"Mean Flows for One-step Generative Modeling","work_id":"07a52ad5-0f82-4095-9a66-559b09fea1ae","shared_citers":4},{"title":"One step diffusion via shortcut models","work_id":"4017f821-b436-40dd-a38d-0b3bb52f7d99","shared_citers":4},{"title":"Simplifying, Stabilizing and Scaling Continuous-Time Consistency Models","work_id":"1151c0b6-2be7-436c-ab83-843d92dea769","shared_citers":4},{"title":"$\\pi_0$: A Vision-Language-Action Flow Model for General Robot Control","work_id":"f790abdc-a796-482f-a40d-f8ee035ecfc2","shared_citers":3},{"title":"Adam: A Method for Stochastic Optimization","work_id":"1910796d-9b52-4683-bf5c-de9632c1028b","shared_citers":3},{"title":"arXiv preprint arXiv:1810.01367 , year=","work_id":"4e8ec919-d6eb-46d4-b10d-8a9c7af0126d","shared_citers":3},{"title":"A survey on diffusion models for inverse problems","work_id":"f2cbc6cc-8d87-4b5d-9751-74f49d4e3b63","shared_citers":3},{"title":"Coefficients-preserving sampling for reinforcement learning with flow matching.arXiv preprint arXiv:2509.05952","work_id":"3bc58f2f-e4be-4ee5-804f-29ffd6dfdb30","shared_citers":3}],"time_series":[{"n":1,"year":2024},{"n":3,"year":2025},{"n":37,"year":2026}],"dependency_candidates":[]},"authors":[]}}