mlsanityData to 14 Oct 2026

Energy-based generator matching: A neural sampler for general state space

arXiv 2505.19646 ↗First posted 26 May 2025cs.LGcited by 3

Not on the map. Why?

Abstract (arXiv)

We propose Energy-based generator matching (EGM), a modality-agnostic approach to train generative models from energy functions in the absence of data. Extending the recently proposed generator matching, EGM enables training of arbitrary continuous-time Markov processes, e.g., diffusion, flow, and jump, and can generate data from continuous, discrete, and a mixture of two modalities. To this end, we propose estimating the generator matching loss using self-normalized importance sampling with an additional bootstrapping trick to reduce variance in the importance weight. We validate EGM on both discrete and multimodal tasks up to 100 and 20 dimensions, respectively.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 29 of its 46 references that are in the map. First posted on arXiv 26 May 2025.

Builds on

29 of 46 references.

References · 29

  1. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  2. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  3. 2022Flow Matching for Generative Modelingcited by 5,702
  4. 2020DiffWave: A Versatile Diffusion Model for Audio Synthesiscited by 1,354
  5. 2022Diffusion-LM Improves Controllable Text Generationcited by 1,027
  6. 2021Flow Network based Generative Models for Non-Iterative Diverse Candidate Generationcited by 392
  7. 2024Discrete Flow Matchingcited by 317
  8. 2024Generative Flows on Discrete State-Spaces: Enabling Multimodal Flows with Applications to Protein Co-Designcited by 305
  9. 2021GFlowNet Foundationscited by 290
  10. 2022Trajectory balance: Improved credit assignment in GFlowNetscited by 251
  11. 2021Path Integral Sampler: a stochastic control approach for samplingcited by 181
  12. 2023Denoising Diffusion Samplerscited by 149
17 more
  1. 2022An optimal control perspective on diffusion-based generative modelingcited by 147
  2. 2024Iterated Denoising Energy Matching for Sampling from Boltzmann Densitiescited by 116
  3. 2023Improved sampling via learned diffusionscited by 104
  4. 2023A theory of continuous generative flow networkscited by 101
  5. 2024Generator Matching: Generative modeling with arbitrary Markov processescited by 86
  6. 2024NETS: A Non-Equilibrium Transport Samplercited by 69
  7. 2024Target Score Matchingcited by 50
  8. 2024Improved off-policy training of diffusion samplerscited by 48
  9. 2023Learning Interpolations between Boltzmann Densitiescited by 43
  10. 2025LEAPS: A discrete neural sampler via locally equivariant networkscited by 31
  11. 2024Liouville Flow Importance Samplercited by 25
  12. 2025Target Concrete Score Matching: A Holistic Framework for Discrete Diffusioncited by 25
  13. 2025From discrete-time policies to continuous-time diffusion samplers: Asymptotic equivalences and faster trainingcited by 19
  14. 2024BNEM: A Boltzmann Sampler Based on Bootstrapped Noised Energy Matchingcited by 15
  15. 2024Iterated Energy-based Flow Matching for Sampling from Boltzmann Densitiescited by 13
  16. 2023Delta-AI: Local objectives for amortized inference in sparse graphical modelscited by 7
  17. 2025Neural Flow Samplers with Shortcut Modelscited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026Scaling Autoregressive Models for Lattice Thermodynamicscited by 5
  2. 2026Discrete Adjoint Schr"odinger Bridge Samplercited by 4
  3. 2026Fixed-point neural samplers on discrete spacescited by 0