# Batch-Paced: Fixed-Budget Batch Decoding in Discrete Diffusion Language Models

arXiv: https://arxiv.org/abs/2610.17917 · HTML: https://mlsanity.com/paper/2610.17917/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Discrete and text diffusion, one of 14 directions in Diffusion models.
- Builds on 20 of its 35 references that are in the map.
- First posted on arXiv 13 Oct 2026.

## Placed in

- Diffusion models / [Discrete and text diffusion](https://mlsanity.com/diffusion/discrete-and-text-diffusion/)

## Builds on (most cited first, 20 of 20)

- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve](https://mlsanity.com/paper/2403.02310/) (2024)
- [Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding](https://mlsanity.com/paper/2505.22618/) (2025)
- [LLaDA 1.5: Variance-Reduced Preference Optimization for Large Language Diffusion Models](https://mlsanity.com/paper/2505.19223/) (2025)
- [DFlash: Block Diffusion for Flash Speculative Decoding](https://mlsanity.com/paper/2602.06036/) (2026)
- [Accelerating Diffusion LLMs via Adaptive Parallel Decoding](https://mlsanity.com/paper/2506.00413/) (2025)
- [Learning How Hard to Think: Input-Adaptive Allocation of LM Computation](https://mlsanity.com/paper/2410.04707/) (2024)
- [LLaDA2.1: Speeding Up Text Diffusion via Token Editing](https://mlsanity.com/paper/2602.08676/) (2026)
- [KLASS: KL-Guided Fast Inference in Masked Diffusion Models](https://mlsanity.com/paper/2511.05664/) (2025)
- [Accelerating Diffusion Large Language Models with SlowFast Sampling: The Three Golden Principles](https://mlsanity.com/paper/2506.10848/) (2025)
- [DSpark: Confidence-Scheduled Speculative Decoding with Semi-Autoregressive Generation](https://mlsanity.com/paper/2607.05147/) (2026)
- [Learning to Parallel: Accelerating Diffusion Large Language Models via Learnable Parallel Decoding](https://mlsanity.com/paper/2509.25188/) (2025)
- [Improving Discrete Diffusion Unmasking Policies Beyond Explicit Reference Policies](https://mlsanity.com/paper/2510.05725/) (2025)
- [CreditDecoding: Accelerating Parallel Decoding in Diffusion Large Language Models with Trace Credit](https://mlsanity.com/paper/2510.06133/) (2025)
- [Cost-Aware Diffusion Draft Trees for Speculative Decoding](https://mlsanity.com/paper/2606.01813/) (2026)
- [Dynamic-dLLM: Dynamic Cache-Budget and Adaptive Parallel Decoding for Training-Free Acceleration of Diffusion LLM](https://mlsanity.com/paper/2606.26120/) (2026)

## Abstract (arXiv)

As generative language models become more capable and widely used, inference demand grows, making efficient serving increasingly important. Discrete diffusion language models (dLLMs) offer a promising path to more efficient inference through parallel token generation. Prior dLLM decoding methods, however, focus on improving inference efficiency for individual sequences. We formulate fixed-budget dLLM batch decoding and introduce Batch-Paced, a training-free method that jointly optimizes the allocation of decoding compute across requests to improve overall batch quality. Across two dLLM backbones, five benchmarks and their representative mixtures, Batch-Paced improves batch performance under matched budgets; gains generally grow with batch size and largely persist across decoding configurations. Analysis of requests' decoding trajectories suggests that these gains arise largely by raising the committed-token confidence of lower-confidence requests. We further show that Batch-Paced's batch decode time remains competitive and that adding a decoding-depth allowance during Batch-Paced decoding can shorten it further at a modest performance cost.