Paper Citation Record · LEDGER

Learning Energy-Based Generative Models via Potential Flow: A Variational Principle Approach to Probability Density Homotopy Matching

As of 23 August 2026, this Paper Citation Record lists 24 of 24 outbound references and 0 inbound Pith citation observations for arXiv:2504.16262.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2504.16262 v1

Coverage vector

measured 24 of 24 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-16T11:14:57.937881Z

measured 24 of 24 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-23T06:30:58.430688+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: cited_works

Reference resolution

24 of 24 outbound references displayed

verified exact0
verified fuzzy15
unresolved9
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 71d0695d-48bf-4048-8b78-93da75fbe1e8 · outbound

This paper cites This process helps smoothout sharplocal minimaand mitigatesoverfittingto high-densityareas.

Learning Energy-Based Generative Models via Potential Flow: A Variational Principle Approach to Probability Density Homotopy Matching This process helps smoothout sharplocal minimaand mitigatesoverfittingto high-densityareas

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:14:58.142670Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 4357952c-e4aa-483d-99f3-2260c0a129fb · outbound

This paper cites Deep ritz revisited.

Learning Energy-Based Generative Models via Potential Flow: A Variational Principle Approach to Probability Density Homotopy Matching Deep ritz revisited

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:14:58.197856Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 87854335-b039-450b-915c-4f722604d3ad · outbound

This paper cites U-net: Convolutional networks for biomedical image segmentation.

Learning Energy-Based Generative Models via Potential Flow: A Variational Principle Approach to Probability Density Homotopy Matching U-net: Convolutional networks for biomedical image segmentation

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:14:58.186357Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 34bbfae7-36af-4a82-bdc0-39d6c5b821fc · outbound

This paper cites Tim Salimans and Jonathan Ho.

Learning Energy-Based Generative Models via Potential Flow: A Variational Principle Approach to Probability Density Homotopy Matching Tim Salimans and Jonathan Ho

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:14:58.175735Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 3a95dd34-e3f0-493f-8e03-2ac0c58f43cc · outbound

This paper cites Wide Residual Networks.

Learning Energy-Based Generative Models via Potential Flow: A Variational Principle Approach to Probability Density Homotopy Matching Wide Residual Networks

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:14:58.165207Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 9f85d5e0-1e49-4228-8f6f-0f28c1639cc2 · outbound

This paper cites Wide Residual Networks.

Learning Energy-Based Generative Models via Potential Flow: A Variational Principle Approach to Probability Density Homotopy Matching Wide Residual Networks

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-16T11:14:57.895448Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ad64fe25-be64-49a6-933b-24e11a7b9da3 · outbound

This paper cites (2021b), (2) an energy model parameterized by the NCSN++ architecture from Song et al.

Learning Energy-Based Generative Models via Potential Flow: A Variational Principle Approach to Probability Density Homotopy Matching (2021b), (2) an energy model parameterized by the NCSN++ architecture from Song et al

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:14:58.131860Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 3cac0f13-c193-424c-929f-6c26ea5d351c · outbound

This paper cites C.4 Proof of Proposition 4 To show that the conditional and marginal homotopies satisfy the reverse diffusion process, we first express the forward-time SDE and ODE of Song et al.

Learning Energy-Based Generative Models via Potential Flow: A Variational Principle Approach to Probability Density Homotopy Matching C.4 Proof of Proposition 4 To show that the conditional and marginal homotopies satisfy the reverse diffusion process, we first express the forward-time SDE and ODE of Song et al

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:14:58.121354Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 20078a72-47b4-4b21-9872-ae424cefe008 · outbound

This paper cites an unresolved cited work.

Learning Energy-Based Generative Models via Potential Flow: A Variational Principle Approach to Probability Density Homotopy Matching Unresolved cited work

Reference 18

Resolution: unresolved; raw_fallback, observed 2026-08-16T11:14:58.109858Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 23817ac1-6764-41cb-a80c-4e1b6a8fa758 · outbound

This paper cites The optimal solutionΦof the functional (84) is given by the first-order optimality condition: I(Φ,Ψ) = d dϵL(Φ(x) +ϵΨ(x),t) ⏐⏐⏐⏐ ϵ=0 = 0(85) which must hold for all trial functionΨ.

Learning Energy-Based Generative Models via Potential Flow: A Variational Principle Approach to Probability Density Homotopy Matching The optimal solutionΦof the functional (84) is given by the first-order optimality condition: I(Φ,Ψ) = d dϵL(Φ(x) +ϵΨ(x),t) ⏐⏐⏐⏐ ϵ=0 = 0(85) which must hold for all trial functionΨ

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:14:58.098513Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 4b4b9cab-013a-488c-b019-da41cb1a4247 · outbound

This paper cites For WideResNet, we include a spectral regularization loss during model training to penalize the spectral norm of the convolutional layer.

Learning Energy-Based Generative Models via Potential Flow: A Variational Principle Approach to Probability Density Homotopy Matching For WideResNet, we include a spectral regularization loss during model training to penalize the spectral norm of the convolutional layer

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:14:58.085496Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation a68cb99c-ac62-4527-a03f-7950266b78f5 · outbound

This paper cites Our WideResNet architecture adopts the model hyperparameters reported by Xiao et al.

Learning Energy-Based Generative Models via Potential Flow: A Variational Principle Approach to Probability Density Homotopy Matching Our WideResNet architecture adopts the model hyperparameters reported by Xiao et al

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:14:58.073448Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation d345cea7-0909-4f7e-a43d-f28945c26ea4 · outbound

This paper cites We find that Lamb performs better than Adam over large learning rates.

Learning Energy-Based Generative Models via Potential Flow: A Variational Principle Approach to Probability Density Homotopy Matching We find that Lamb performs better than Adam over large learning rates

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:14:58.049637Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation dba62db5-c599-4762-8145-152a63b7ea89 · outbound

This paper cites CIFAR-10 consists of50,000training images and10,000test images at a resolution of32×32.

Learning Energy-Based Generative Models via Potential Flow: A Variational Principle Approach to Probability Density Homotopy Matching CIFAR-10 consists of50,000training images and10,000test images at a resolution of32×32

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:14:58.037409Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 97391668-3950-444a-9a82-a8bbeea93787 · outbound

This paper cites doi: https://doi.org/10.1016/0771-050X(80) 90013-3.

Learning Energy-Based Generative Models via Potential Flow: A Variational Principle Approach to Probability Density Homotopy Matching doi: https://doi.org/10.1016/0771-050X(80) 90013-3

Reference 1980

Resolution: unresolved; no resolver link, observed 2026-08-16T11:14:57.849623Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ff039641-edc7-4455-9a42-43105e98119c · outbound

This paper cites Yuntian Deng, Anton Bakhtin, Myle Ott, Arthur Szlam, and Marc’Aurelio Ranzato.

Learning Energy-Based Generative Models via Potential Flow: A Variational Principle Approach to Probability Density Homotopy Matching Yuntian Deng, Anton Bakhtin, Myle Ott, Arthur Szlam, and Marc’Aurelio Ranzato

Reference 2007

Resolution: unresolved; no resolver link, observed 2026-08-16T11:14:57.845160Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 997fff71-54b0-44c2-ba5d-9260092ee4da · outbound

This paper cites Knowledge Distillation in Iterative Generative Models for Improved Sampling Speed.

Learning Energy-Based Generative Models via Potential Flow: A Variational Principle Approach to Probability Density Homotopy Matching Knowledge Distillation in Iterative Generative Models for Improved Sampling Speed

Reference 2015

Resolution: unresolved; no resolver link, observed 2026-08-16T11:14:57.866525Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a7b7a5da-d93a-4165-9d49-5173d3bea7d7 · outbound

This paper cites PixelCNN++: Improving the PixelCNN with Discretized Logistic Mixture Likelihood and Other Modifications.

Learning Energy-Based Generative Models via Potential Flow: A Variational Principle Approach to Probability Density Homotopy Matching PixelCNN++: Improving the PixelCNN with Discretized Logistic Mixture Likelihood and Other Modifications

Reference 2016

Resolution: unresolved; no resolver link, observed 2026-08-16T11:14:57.882843Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3f3b7f18-ad39-424f-9df7-4da331caae78 · outbound

This paper cites Reconstruction of pairwise interactions using energy-based models*.

Learning Energy-Based Generative Models via Potential Flow: A Variational Principle Approach to Probability Density Homotopy Matching Reconstruction of pairwise interactions using energy-based models*

Reference 2018

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:14:58.218644Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation d1999885-63f8-44cc-9095-bae9230f87b8 · outbound

This paper cites A Tale of Two Flows: Cooperative Learning of Langevin Flow and Normalizing Flow Toward Energy-Based Model.

Learning Energy-Based Generative Models via Potential Flow: A Variational Principle Approach to Probability Density Homotopy Matching A Tale of Two Flows: Cooperative Learning of Langevin Flow and Normalizing Flow Toward Energy-Based Model

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-08-16T11:14:57.886929Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 82b79e1a-855c-4c55-a500-d9cf4d42028a · outbound

This paper cites Our U-Net architecture adopts the hyperparameters used by Lipman et al.

Learning Energy-Based Generative Models via Potential Flow: A Variational Principle Approach to Probability Density Homotopy Matching Our U-Net architecture adopts the hyperparameters used by Lipman et al

Reference 2021

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:14:58.060891Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 32963631-8364-4128-a428-3099a436b225 · outbound

This paper cites Soft Truncation: A Universal Training Technique of Score-based Diffusion Model for High Precision Score Estimation.

Learning Energy-Based Generative Models via Potential Flow: A Variational Principle Approach to Probability Density Homotopy Matching Soft Truncation: A Universal Training Technique of Score-based Diffusion Model for High Precision Score Estimation

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-16T11:14:57.858088Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 06e712af-16cb-44d5-b70e-9ab1007e51fc · outbound

This paper cites GraphEBM: Molecular graph generation with energy-based models.

Learning Energy-Based Generative Models via Potential Flow: A Variational Principle Approach to Probability Density Homotopy Matching GraphEBM: Molecular graph generation with energy-based models

Reference 2023

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:14:58.208246Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation aaa2c68e-faba-4365-9fa7-d272fe553f54 · outbound

This paper cites an unresolved cited work.

Learning Energy-Based Generative Models via Potential Flow: A Variational Principle Approach to Probability Density Homotopy Matching Unresolved cited work

Reference 2024

Resolution: unresolved; raw_fallback, observed 2026-08-16T11:14:58.153739Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Pith citing papers

No inbound Pith citation observations are available.