mlsanityData to 7 Oct 2026

Just on Time: Token-Level Early Stopping for Diffusion Language Models

arXiv 2602.11133 ↗First posted 11 Feb 2026cs.LG cs.CLcited by 1

On the map: Diffusion models → Discrete and text diffusion

Abstract (arXiv)

Diffusion language models generate text through iterative refinement, a process that is often computationally inefficient because many tokens reach stability long before the final denoising step. We introduce a training-free, token-level early stopping approach that identifies convergence independently at each position. Our method leverages lightweight signals derived from the model's predictions and local context to dynamically determine when individual tokens can be finalized. This yields adaptive per-token freezing without task-specific fine-tuning, substantially reducing the total number of diffusion steps required. Across diverse benchmarks, spanning mathematical reasoning, general question answering, and scientific understanding, our approach achieves substantial efficiency gains while preserving generation quality.

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 25 of its 29 references that are in the map. First posted on arXiv 11 Feb 2026.

Builds on

25 of 29 references.

Closest ancestors · 12

Same direction, newest first

  1. 2026Stopping Computation for Converged Tokens in Masked Diffusion-LM Decoding6 Feb
  2. 2025KLASS: KL-Guided Fast Inference in Masked Diffusion Models7 Nov
  3. 2025Diffusion Language Models Know the Answer Before Decoding27 Aug
  4. 2025Dream 7B: Diffusion Large Language Models21 Aug
  5. 2025Diffusion LLMs Can Do Faster-Than-AR Inference via Discrete Diffusion Forcing8 Aug
  6. 2025dKV-Cache: The Cache for Diffusion Language Models21 May
  7. 2025Large Language Diffusion Models14 Feb
  8. 2024Masked Diffusion Models are Secretly Time-Agnostic Masked Models and Exploit Inaccurate Categorical Sampling4 Sep
  9. 2024Simple and Effective Masked Diffusion Language Models11 Jun
  10. 2024Your Absorbing Discrete Diffusion Secretly Models the Conditional Distributions of Clean Data6 Jun
  11. 2023Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution25 Oct
  12. 2022DiffuSeq: Sequence to Sequence Text Generation with Diffusion Models17 Oct

Other references · 13

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  4. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  5. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  6. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  7. 2020Measuring Massive Multitask Language Understandingcited by 7,768
  8. 2019HellaSwag: Can a Machine Really Finish Your Sentence?cited by 4,018
  9. 2021Structured Denoising Diffusion Models in Discrete State-Spacescited by 1,665
  10. 2022Diffusion-LM Improves Controllable Text Generationcited by 1,006
  11. 2021MAUVE: Measuring the Gap Between Neural Text and Human Text using Divergence Frontierscited by 466
  12. 2025Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decodingcited by 404
1 more
  1. 2025Accelerating Diffusion Large Language Models with SlowFast Sampling: The Three Golden Principlescited by 43

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026ELF-REG: Scaling Continuous Diffusion Language Models to Reasoning Taskscited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2026ALoDLM: Adaptively Looped Diffusion Language Models
  2. 2026Window-Diffusion: Accelerating Diffusion Language Model Inference with Windowed Token Pruning and Caching
  3. 2026Remask, Don't Replace: Token-to-Mask Refinement in Diffusion Language Models
  4. 2026One Token Is Enough: Improving Diffusion Language Models with a Sink Token
  5. 2026Diffusion Language Models: An Experimental Analysis
  6. 2026Know When to Hold 'em: Correct-Token Retention in Uniform-State Diffusion Language Models
  7. 2025FlashDLM: Accelerating Diffusion Language Model Inference via Efficient KV Caching and Guided Diffusion
  8. 2026Temporally-Resolved Token Attribution Reveals the Generation Dynamics of Diffusion Language Models