Diffusion Language Models Are Natively Length-Aware

• URL: http://arxiv.org/abs/2603.06123v1
• Date: Fri, 06 Mar 2026 10:30:13 GMT
• Title: Diffusion Language Models Are Natively Length-Aware
• Abstract summary: We propose a zero-shot mechanism to dynamically crop the context window before generation begins.<n>We report significant reductions in FLOPs across all tasks, with no statistically significant performance degradation.
• Score: 29.070013714054877
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Unlike autoregressive language models, which terminate variable-length generation upon predicting an End-of-Sequence (EoS) token, Diffusion Language Models (DLMs) operate over a fixed maximum-length context window for a predetermined number of denoising steps. However, this process is independent of the required response length, resulting in computational waste for the majority of short responses common in reasoning and chat tasks. To address this problem, we conjecture that the latent prompt representation contains sufficient information to estimate the required output length. We provide empirical evidence for this phenomenon and propose a zero-shot mechanism to dynamically crop the context window before generation begins, leading to fewer diffusion steps and substantial computational savings. We evaluate our approach on four benchmarks with diverse tasks -- GSM8K (reasoning), HumanEval (code generation), IfEval (instruction following), and LongFormQA (question answering) -- revealing massive efficiency gains at minimal performance impact. We report significant reductions in FLOPs across all tasks, with no statistically significant performance degradation, and significant performance improvements in 2 out of 4 tasks.

Related papers

• Predict-then-Diffuse: Adaptive Response Length for Compute-Budgeted Inference in Diffusion LLMs [7.630708097054872]
  Diffusion-based Large Language Models (D-LLMs) represent a promising frontier in generative AI.<n>We propose Predict-then-Diffuse, a model-agnostic framework that enables compute-budgeted inference per input query.<n>We show that Predict-then-Diffuse significantly reduces computational costs (FLOP) compared to the default D-LLM inference mechanism.
  arXiv  Detail & Related papers  (2026-05-05T18:55:24Z)
• Thinking in Latents: Adaptive Anchor Refinement for Implicit Reasoning in LLMs [3.0215547730060206]
  We introduce AdaAnchor, a latent reasoning framework that performs silent iterative computation by refining a set of latent anchor vectors attached to the input.<n>AdaAnchor with adaptive halting yields accuracy gains of up to 5% over fixed-step latent refinement while reducing average latent refinement steps by 48-60% under the same maximum-step budget.
  arXiv  Detail & Related papers  (2026-03-16T10:06:05Z)
• TokenSqueeze: Performance-Preserving Compression for Reasoning LLMs [57.217593337454026]
  TokenSqueeze is a novel Long2Short method that condenses reasoning paths while preserving performance and relying exclusively on self-generated data.<n>We show that TokenSqueeze reduces token usage while maintaining accuracy on the MATH500 benchmark.
  arXiv  Detail & Related papers  (2025-11-17T10:38:56Z)
• Beyond Fixed: Training-Free Variable-Length Denoising for Diffusion Large Language Models [74.15250326312179]
  Diffusion Large Language Models offer efficient parallel generation and capable global modeling.<n>The dominant application ofDLLMs is hindered by the need for a statically predefined generation length.<n>We introduce DAEDAL, a novel training-free denoising strategy that enables Dynamic Adaptive Length Expansion.
  arXiv  Detail & Related papers  (2025-08-01T17:56:07Z)
• ONLY: One-Layer Intervention Sufficiently Mitigates Hallucinations in Large Vision-Language Models [67.75439511654078]
  Large Vision-Language Models (LVLMs) have introduced a new paradigm for understanding and reasoning about image input through textual responses.<n>They face the persistent challenge of hallucination, which introduces practical weaknesses and raises concerns about their reliable deployment in real-world applications.<n>We propose ONLY, a training-free decoding approach that requires only a single query and a one-layer intervention during decoding, enabling efficient real-time deployment.
  arXiv  Detail & Related papers  (2025-07-01T16:01:08Z)
• S$^4$C: Speculative Sampling with Syntactic and Semantic Coherence for Efficient Inference of Large Language Models [38.784951111677856]
  Large language models (LLMs) exhibit remarkable reasoning capabilities across diverse downstream tasks.<n>Their autoregressive nature leads to substantial latency inference, posing challenges for real-time applications.<n>We propose a Speculative Sampling with Syntactic and Semantic Coherence framework, which extends speculative sampling by leveraging multi-head drafting.
  arXiv  Detail & Related papers  (2025-06-17T03:38:19Z)
• Accelerated Test-Time Scaling with Model-Free Speculative Sampling [58.69141724095398]
  We introduce STAND (STochastic Adaptive N-gram Drafting), a novel model-free speculative decoding approach.<n>We show that STAND reduces inference latency by 60-65% compared to standard autoregressive decoding.<n>As a model-free approach, STAND can be applied to any existing language model without additional training.
  arXiv  Detail & Related papers  (2025-06-05T07:31:18Z)
• Accelerating LLaMA Inference by Enabling Intermediate Layer Decoding via Instruction Tuning with LITE [62.13435256279566]
  Large Language Models (LLMs) have achieved remarkable performance across a wide variety of natural language tasks. However, their large size makes their inference slow and computationally expensive. We show that it enables these layers to acquire 'good' generation ability without affecting the generation ability of the final layer.
  arXiv  Detail & Related papers  (2023-10-28T04:07:58Z)
• ReWOO: Decoupling Reasoning from Observations for Efficient Augmented Language Models [32.95155349925248]
  We propose a modular paradigm ReWOO that detaches the reasoning process from external observations, thus significantly reducing token consumption. We show that ReWOO achieves 5x token efficiency and 4% accuracy improvement on HotpotQA, a multi-step reasoning benchmark. Our illustrative work offloads reasoning ability from 175B GPT3.5 into 7B LLaMA, demonstrating the significant potential for truly efficient and scalable ALM systems.
  arXiv  Detail & Related papers  (2023-05-23T00:16:48Z)
• Confident Adaptive Language Modeling [95.45272377648773]
  CALM is a framework for dynamically allocating different amounts of compute per input and generation timestep. We demonstrate the efficacy of our framework in reducing compute -- potential speedup of up to $times 3$ -- while provably maintaining high performance.
  arXiv  Detail & Related papers  (2022-07-14T17:00:19Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.