mlsanityData to 14 Oct 2026

Discrete Guidance Matching: Exact Guidance for Discrete Flow Matching

arXiv 2509.21912 ↗First posted 26 Sep 2025cs.LG stat.MLcited by 6

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

Guidance provides a simple and effective framework for posterior sampling by steering the generation process towards the desired distribution. When modeling discrete data, existing approaches mostly focus on guidance with the first-order approximation to improve the sampling efficiency. However, such an approximation is inappropriate in discrete state spaces since the approximation error could be large. A novel guidance framework for discrete data is proposed to address this problem: we derive the exact transition rate for the desired distribution given a learned discrete flow matching model, leading to guidance that only requires a single forward pass in each sampling step, significantly improving efficiency. This unified novel framework is general enough, encompassing existing guidance methods as special cases, and it can also be seamlessly applied to the masked diffusion model. We demonstrate the effectiveness of our proposed guidance on energy-guided simulations and preference alignment on text-to-image generation and multimodal understanding tasks. The code is available at https://github.com/WanZhengyan/Discrete-Guidance-Matching.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 86 of its 95 references that are in the map. First posted on arXiv 26 Sep 2025.

Builds on

86 of 95 references.

Closest ancestors · 17

Same direction, newest first

  1. 2024Simple Guidance Mechanisms for Discrete Diffusion Models13 Dec
  2. 2024Derivative-Free Guidance in Continuous and Discrete Diffusion Models with Soft Value-Based Decoding15 Aug
  3. 2024Transfer Learning for Diffusion Models27 May
  4. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesis5 Mar
  5. 2023PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis30 Sep
  6. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis4 Jul
  7. 2022Score-based Continuous-time Discrete Diffusion Models30 Nov
  8. 2022From Denoising Diffusions to Denoising Markov Models7 Nov
  9. 2022Classifier-Free Diffusion Guidance26 Jul
  10. 2022Elucidating the Design Space of Diffusion-Based Generative Models1 Jun
  11. 2022A Continuous Time Framework for Discrete Denoising Models30 May
  12. 2021High-Resolution Image Synthesis with Latent Diffusion Models20 Dec
5 more
  1. 2021Structured Denoising Diffusion Models in Discrete State-Spaces7 Jul
  2. 2021Diffusion Models Beat GANs on Image Synthesis11 May
  3. 2020Score-Based Generative Modeling through Stochastic Differential Equations26 Nov
  4. 2020Denoising Diffusion Implicit Models6 Oct
  5. 2020Denoising Diffusion Probabilistic Models19 Jun

Other references · 69

  1. 2022Training language models to follow instructions with human feedbackcited by 15,971
  2. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
  3. 2023Visual Instruction Tuningcited by 7,869
  4. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  5. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,585
  6. 2022Flow Matching for Generative Modelingcited by 5,702
  7. 2023Improved Baselines with Visual Instruction Tuningcited by 4,418
  8. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,700
  9. 2024Gemini 1.5: Unlocking multimodal understanding across millions of tokens of contextcited by 3,224
  10. 2023InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuningcited by 2,876
  11. 2023MMBench: Is Your Multi-modal Model an All-around Player?cited by 2,141
  12. 2023MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGIcited by 2,080
38 more
  1. 2023Evaluating Object Hallucination in Large Vision-Language Modelscited by 1,729
  2. 2023MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Modelscited by 1,652
  3. 2023MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilitiescited by 1,239
  4. 2022MaskGIT: Masked Generative Image Transformercited by 1,099
  5. 2022Building Normalizing Flows with Stochastic Interpolantscited by 995
  6. 2023Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generationcited by 977
  7. 2023GenEval: An Object-Focused Framework for Evaluating Text-to-Image Alignmentcited by 972
  8. 2023SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehensioncited by 940
  9. 2024Chameleon: Mixed-Modal Early-Fusion Foundation Modelscited by 927
  10. 2025Large Language Diffusion Modelscited by 912
  11. 2024Simple and Effective Masked Diffusion Language Modelscited by 848
  12. 2025Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scalingcited by 812
  13. 2024Emu3: Next-Token Prediction is All You Needcited by 781
  14. 2024Autoregressive Model Beats Diffusion: Llama for Scalable Image Generationcited by 777
  15. 2024Show-o: One Single Transformer to Unify Multimodal Understanding and Generationcited by 752
  16. 2023Discrete Diffusion Modeling by Estimating the Ratios of the Data Distributioncited by 745
  17. 2025Flow-GRPO: Training Flow Matching Models via Online RLcited by 661
  18. 2024Simplified and Generalized Masked Diffusion for Discrete Datacited by 626
  19. 2021Argmax Flows and Multinomial Diffusion: Learning Categorical Distributionscited by 574
  20. 2022DiGress: Discrete Denoising diffusion for graph generationcited by 520
  21. 2024Transfusion: Predict the Next Token and Diffuse Images with One Multi-Modal Modelcited by 483
  22. 2024Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generationcited by 457
  23. 2024VLMEvalKit: An Open-Source Toolkit for Evaluating Large Multi-Modality Modelscited by 455
  24. 2025Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Modelscited by 409
  25. 2024Your Absorbing Discrete Diffusion Secretly Models the Conditional Distributions of Clean Datacited by 381
  26. 2024SEED-X: Multimodal Models with Unified Multi-granularity Comprehension and Generationcited by 331
  27. 2024Discrete Flow Matchingcited by 317
  28. 2024Generative Flows on Discrete State-Spaces: Enabling Multimodal Flows with Applications to Protein Co-Designcited by 305
  29. 2024VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generationcited by 295
  30. 2025LLaDA 1.5: Variance-Reduced Preference Optimization for Large Language Diffusion Modelscited by 285
  31. 2025MMaDA: Multimodal Large Diffusion Language Modelscited by 250
  32. 2021Autoregressive Diffusion Modelscited by 210
  33. 2024MetaMorph: Multimodal Understanding and Generation via Instruction Tuningcited by 206
  34. 2024TokenFlow: Unified Image Tokenizer for Multimodal Understanding and Generationcited by 202
  35. 2024Scaling up Masked Diffusion Models on Textcited by 199
  36. 2024World Model on Million-Length Video And Language With Blockwise RingAttentioncited by 198
  37. 2025d1: Scaling Reasoning in Diffusion Large Language Models via Reinforcement Learningcited by 186
  38. 2024MobileVLM V2: Faster and Stronger Baseline for Vision Language Modelcited by 174

50 most cited of 69 All 69 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 6.

6 papers.

  1. 2026Flow Matching for Offline Reinforcement Learning with Discrete Actionscited by 6
  2. 2026Corrected Samplers for Discrete Flow Modelscited by 3
  3. 2026Minimax Optimality of Score-Entropy Discrete Diffusioncited by 3
  4. 2026Advances in GRPO for Generation Models: A Surveycited by 2
  5. 2026Entropy Can Flow, or It Can Guide. Be Entropy. LEDFlow: Introducing Entropy-guided Generation Order into Uniform Discrete Flowcited by 0
  6. 2026Iterative Exact Discrete Guidance for Energy-Based Samplingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025GLASS Flows: Transition Sampling for Alignment of Flow and Diffusion Models
  2. 2025Debiasing Guidance for Discrete Diffusion with Sequential Monte Carlo
  3. 2025How Much To Guide: Revisiting Adaptive Guidance in Classifier-Free Guidance Text-to-Vision Diffusion Models
  4. 2024Compress Guidance in Conditional Diffusion Sampling
  5. 2026Correcting Guided Diffusion Trajectories with Spectral Alignment
  6. 2026Alignment of Diffusion Model and Flow Matching for Text-to-Image Generation
  7. 2024Self-Guidance: Boosting Flow and Diffusion Generation on Their Own
  8. 2026Context-weighted Discrete Flow Matching