mlsanityData to 7 Oct 2026

Survival-Guided Length Control for Efficient Diffusion Language Models

arXiv 2608.26374 ↗First posted 26 Aug 2026cs.CLcited by 0

On the map: Diffusion models → Discrete and text diffusion

Abstract (arXiv)

Diffusion language models (DLMs) generate text by iteratively denoising masked sequences, but standard decoding either fixes the sequence length or relies on ad hoc stopping rules, often leading to unnecessary denoising steps. We recast length selection as a discrete-time survival problem over the end-of-sequence token and propose a plug-in, training-free length predictor that can be added to any existing DLM. Across reasoning and code-generation benchmarks, survival-guided length decoding speeds up inference by up to 7 times while preserving task accuracy. We further find that predicted lengths vary widely even within the same dataset, making model performance sensitive to the chosen length.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Discrete and text diffusion, one of 14 directions in Diffusion models. Builds on 12 of its 19 references that are in the map. First posted on arXiv 26 Aug 2026.

Builds on

12 of 19 references.

Closest ancestors · 3

Same direction, newest first

  1. 2025Diffusion Language Models Know the Answer Before Decoding27 Aug
  2. 2024Simplified and Generalized Masked Diffusion for Discrete Data6 Jun
  3. 2024Your Absorbing Discrete Diffusion Secretly Models the Conditional Distributions of Clean Data6 Jun

Other references · 9

  1. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  2. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  3. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,203
  4. 2022Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Themcited by 1,767
  5. 2021Structured Denoising Diffusion Models in Discrete State-Spacescited by 1,665
  6. 2016Variational Inference: A Review for Statisticianscited by 1,466
  7. 2025Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decodingcited by 404
  8. 2025dLLM-Cache: Accelerating Diffusion Large Language Models with Adaptive Cachingcited by 168
  9. 2025Accelerating Diffusion Large Language Models with SlowFast Sampling: The Three Golden Principlescited by 43

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Predict, Don't Iterate: Efficient Adaptive-Length Infilling for Diffusion Language Models
  2. 2026Diffusion Language Models Are Natively Length-Aware
  3. 2026Improving Variable-Length Generation in Diffusion Language Models via Length Regularization
  4. 2026CARVE: Verified Expansion for Variable-Length Generation in Diffusion Language Models
  5. 2026Diffusion LMs Can Approximate Optimal Infilling Lengths Implicitly
  6. 2025Sequential Diffusion Language Models
  7. 2026CAI-DLLM: Convergence Aware Inference for Diffusion Language Models
  8. 2026From Position Risks to Block Survival: Faster Generation for Diffusion Language Models