mlsanityData to 7 Oct 2026

D5P4: Partition Determinantal Point Process for Diversity in Parallel Discrete Diffusion Decoding

arXiv 2603.19146 ↗First posted 19 Mar 2026cs.AI cs.LGcited by 1

On the map: Diffusion models → Discrete and text diffusion

Abstract (arXiv)

Discrete diffusion models are promising alternatives to autoregressive approaches for text generation, yet their decoding methods remain under-studied. Standard autoregressive search procedures, such as beam search, do not directly apply to iterative denoising, where hypotheses are complete intermediate sequences rather than left-to-right prefixes. Furthermore, existing diffusion decoding procedures only provide limited control over the diversity and coverage of retained hypotheses. In this work, we introduce D5P4, a beam-style decoding method tailored to discrete diffusion models, which casts intermediate beam selection as MAP inference under a partitioned Determinantal Point Process. This yields a model-internal batch objective that balances quality and diversity without external verifiers. Experiments on open-ended generation, question answering, and mathematical reasoning show that D5P4 improves diversity and pass@k coverage while matching or surpassing baseline quality and fidelity

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Discrete and text diffusion, one of 14 directions in Diffusion models. Builds on 40 of its 55 references that are in the map. First posted on arXiv 19 Mar 2026.

Builds on

40 of 55 references.

Closest ancestors · 8

Same direction, newest first

  1. 2025Optimizing Decoding Paths in Masked Diffusion Models by Quantifying Uncertainty24 Dec
  2. 2025Scaling Behavior of Discrete Diffusion Language Models11 Dec
  3. 2025Dream 7B: Diffusion Large Language Models21 Aug
  4. 2025Diffusion LLMs Can Do Faster-Than-AR Inference via Discrete Diffusion Forcing8 Aug
  5. 2025dKV-Cache: The Cache for Diffusion Language Models21 May
  6. 2025Large Language Diffusion Models14 Feb
  7. 2024Scaling up Masked Diffusion Models on Text24 Oct
  8. 2024Simple and Effective Masked Diffusion Language Models11 Jun

Other references · 32

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  3. 2024The Llama 3 Herd of Modelscited by 14,192
  4. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  5. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  6. 2022Scalable Diffusion Models with Transformerscited by 5,931
  7. 2018Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challengecited by 4,710
  8. 2021TruthfulQA: Measuring How Models Mimic Human Falsehoodscited by 2,919
  9. 2019The Curious Case of Neural Text Degenerationcited by 2,881
  10. 2018CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledgecited by 1,793
  11. 2019Similarity of Neural Network Representations Revisitedcited by 1,695
  12. 2021Structured Denoising Diffusion Models in Discrete State-Spacescited by 1,665
20 more
  1. 2015A Diversity-Promoting Objective Function for Neural Conversation Modelscited by 1,068
  2. 2025Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?cited by 948
  3. 2021Argmax Flows and Multinomial Diffusion: Learning Categorical Distributionscited by 566
  4. 2018Texygen: A Benchmarking Platform for Text Generation Modelscited by 484
  5. 2021MAUVE: Measuring the Gap Between Neural Text and Human Text using Divergence Frontierscited by 466
  6. 2025Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decodingcited by 404
  7. 2016Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Modelscited by 299
  8. 2024Applying Guidance in a Limited Interval Improves Sample and Distribution Quality in Diffusion Modelscited by 240
  9. 2019Stochastic Beams and Where to Find Them: The Gumbel-Top-k Trick for Sampling Sequences Without Replacementcited by 205
  10. 2025Scalable Best-of-N Selection for Large Language Models via Self-Certaintycited by 182
  11. 2024Simple Guidance Mechanisms for Discrete Diffusion Modelscited by 148
  12. 2023CADS: Unleashing the Diversity of Diffusion Models through Condition-Annealed Samplingcited by 124
  13. 2025Accelerating Diffusion LLMs via Adaptive Parallel Decodingcited by 108
  14. 2024Probabilistic Inference in Language Models via Twisted Sequential Monte Carlocited by 85
  15. 2025Feynman-Kac Correctors in Diffusion: Annealing, Guidance, and Product of Expertscited by 85
  16. 2025Inference-Time Alignment in Diffusion Models with Reward-Guided Generation: Tutorial and Reviewcited by 82
  17. 2024Preserving Diversity in Supervised Fine-Tuning of Large Language Modelscited by 68
  18. 2025Debiasing Guidance for Discrete Diffusion with Sequential Monte Carlocited by 29
  19. 2022Rethinking and Refining the Distinct Metriccited by 27
  20. 2021Determinantal Beam Searchcited by 18

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Self-Repulsive Sampling for Diffusion Language Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Loopholing Discrete Diffusion: Deterministic Bypass of the Sampling Wall
  2. 2026Search or Accelerate: Confidence-Switched Position Beam Search for Diffusion Language Models
  3. 2025Accelerating Diffusion LLM Inference via Local Determinism Propagation
  4. 2026Efficient Diffusion LLMs via Temporal-Spatial Parallel Decoding and Confidence Extrapolation
  5. 2026Self-Augmenting Retrieval for Diffusion Language Models
  6. 2025Encoder-Decoder Diffusion Language Models for Efficient Training and Inference
  7. 2026Unified Energy for Invariant and Independent Decoding in Diffusion Language Models
  8. 2025Diffusion Language Model Inference with Monte Carlo Tree Search