mlsanityData to 14 Oct 2026

Continuous Semi-Implicit Models

arXiv 2506.06778 ↗First posted 7 Jun 2025stat.ML cs.LGcited by 0

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

Semi-implicit distributions have shown great promise in variational inference and generative modeling. Hierarchical semi-implicit models, which stack multiple semi-implicit layers, enhance the expressiveness of semi-implicit distributions and can be used to accelerate diffusion models given pretrained score networks. However, their sequential training often suffers from slow convergence. In this paper, we introduce CoSIM, a continuous semi-implicit model that extends hierarchical semi-implicit models into a continuous framework. By incorporating a continuous transition kernel, CoSIM enables efficient, simulation-free training. Furthermore, we show that CoSIM achieves consistency with a carefully designed transition kernel, offering a novel approach for multistep distillation of generative models at the distributional level. Extensive experiments on image generation demonstrate that CoSIM performs on par or better than existing diffusion model acceleration methods, achieving superior performance on FD-DINOv2.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 42 of its 57 references that are in the map. First posted on arXiv 7 Jun 2025.

Builds on

42 of 57 references.

Closest ancestors · 19

Same direction, newest first

  1. 2024Adversarial Score identity Distillation: Rapidly Surpassing the Teacher in One Step19 Oct
  2. 2024Multistep Distillation of Diffusion Models via Moment Matching6 Jun
  3. 2024Score identity Distillation: Exponentially Fast Distillation of Pretrained Diffusion Models for One-Step Generation5 Apr
  4. 2024Towards a mathematical theory for consistency training in diffusion models12 Feb
  5. 2023Analyzing and Improving the Training Dynamics of Diffusion Models5 Dec
  6. 2023One-step Diffusion with Distribution Matching Distillation30 Nov
  7. 2023Hierarchical Semi-Implicit Variational Inference with Application to Diffusion Model Acceleration26 Oct
  8. 2023Improved Techniques for Training Consistency Models22 Oct
  9. 2023Learning Stackable and Skippable LEGO Bricks for Efficient, Reconfigurable, and Variable-Resolution Diffusion Modeling10 Oct
  10. 2023Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of Diffusion1 Oct
  11. 2023Diff-Instruct: A Universal Approach for Transferring Knowledge From Pre-trained Diffusion Models29 May
  12. 2023Consistency Models2 Mar
7 more
  1. 2022Improved Analysis of Score-based Generative Modeling: User-Friendly Bounds under Minimal Smoothness Assumptions3 Nov
  2. 2022Convergence for score-based generative modeling with polynomial complexity13 Jun
  3. 2022DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps2 Jun
  4. 2022Elucidating the Design Space of Diffusion-Based Generative Models1 Jun
  5. 2020Score-Based Generative Modeling through Stochastic Differential Equations26 Nov
  6. 2020Denoising Diffusion Implicit Models6 Oct
  7. 2020Denoising Diffusion Probabilistic Models19 Jun

Other references · 23

  1. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
  2. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  3. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,475
  4. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,101
  5. 2016Improved Techniques for Training GANscited by 2,970
  6. 2015Variational Inference with Normalizing Flowscited by 2,170
  7. 2019Generating Diverse High-Fidelity Images with VQ-VAE-2cited by 1,387
  8. 2023ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillationcited by 1,219
  9. 2016Improving Variational Inference with Inverse Autoregressive Flowcited by 640
  10. 2020NVAE: A Deep Hierarchical Variational Autoencodercited by 637
  11. 2016Ladder Variational Autoencoderscited by 318
  12. 2016Generating Images with Perceptual Similarity Metrics based on Deep Networkscited by 222
11 more
  1. 2022Diffusion-GAN: Training GANs with Diffusioncited by 205
  2. 2023Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion modelscited by 205
  3. 2015DRAW: A Recurrent Neural Network For Image Generationcited by 191
  4. 2015Hierarchical Variational Modelscited by 89
  5. 2023PFGM++: Unlocking the Potential of Physics-Inspired Generative Modelscited by 73
  6. 2018Semi-Implicit Variational Inferencecited by 55
  7. 2018Unbiased Implicit Variational Inferencecited by 33
  8. 2023Semi-Implicit Variational Inference via Score Matchingcited by 19
  9. 2023Particle-based Variational Inference with Generalized Wasserstein Gradient Flowcited by 10
  10. 2021Efficient Semi-Implicit Variational Inferencecited by 9
  11. 2024Kernel Semi-Implicit Variational Inferencecited by 8

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2023LCM-LoRA: A Universal Stable-Diffusion Acceleration Module
  2. 2024On Improved Conditioning Mechanisms and Pre-training Strategies for Diffusion Models
  3. 2022Understanding Diffusion Models: A Unified Perspective
  4. 2026Are We Overthinking One-Step Generation?
  5. 2023A Complete Recipe for Diffusion Generative Models
  6. 2022f-DM: A Multi-stage Diffusion Model via Progressive Signal Transformation
  7. 2022Accelerating Score-based Generative Models with Preconditioned Diffusion Sampling
  8. 2026Semi-Supervised Generative Learning via Latent Space Distribution Matching