← Back to all news
arXiv AI By Xiaolong Xu, Hao Jiang, Bo Jiang, Zhiwen Deng, Ningyuan Sun, Bingzhou Chen, Jin Chen, Chenxing Wei

Diff Diffusion: Predicting Edit Paths with Diffusion Models for Efficient Code Editing

Read the original on arXiv AI →

Diff Diffusion is a diffusion-inspired large language model framework designed for efficient code editing. It predicts edit paths from an original snippet to its revised form by representing denoising as structured edit operations, and uses multi-stage training and efficient parallel decoding to focus computation on changed regions. The approach matches or outperforms autoregressive baselines while achieving up to 2.78× faster inference and a 39.0% reduction in median model latency in production.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv AI
Oct 12

AutoIndexer: Flexible-Order Decoding by Training Causal Models on Chains of Edits

AutoIndexer is a generative model that trains causal models on chains of edits, enabling flexible post‑generation modifications such as token insertions, substitutions, and deletions. It introduces marker tokens for opening and closing edits and moves a cursor through the token sequence, mimicking a text editor. By perturbing ground‑truth labels with inverse edit operations during training, AutoIndexer becomes robust to erroneous context and can perform editing tasks like code correction while maintaining performance on standard LLM benchmarks.

By Shu Ishida, Aliasghar Khani, Tianyu Zhang, The Cong Luong, James Seale Smith, Adam Gaier
llmsdiffusionbenchmarks
More like this →
arXiv AI
Jul 28

Beyond Block Boundaries: Multi-Block Editing for Diffusion Large Language Models

arXiv:2607. 22663v1 Announce Type: new Abstract: Block diffusion has emerged as the dominant paradigm for scaling discrete diffusion language models (dLLMs), because decoding text in fixed-size blocks preserves parallel generation within each block while keeping the quadratic attention cost tractable.

By Xingyu Mou, Zijin Huang, Tianze Zhang, Yuxin Ma, Lanning Wei, Zengfeng Huang, Da Zheng, Lun Du
llmsdiffusionfine-tuningefficiencybenchmarks
More like this →
arXiv AI
Sep 10

Diffs vs. Whole Files: An Empirical Comparison of Iterative Edit-Based and Direct Generation for Flutter/Dart Code Models

The paper compares two output regimes for code-editing language models: direct generation, where the model outputs the entire modified file, and iterative diff-based generation, where the model emits a sequence of localized edits. Experiments on Flutter/Dart tasks show that direct generation consistently outperforms diff-based generation across metrics such as compilation success, token efficiency, and quality judgments. However, diff-based generation can be competitive for short, spatially localized edits, particularly in refactoring and error-handling tasks with few edit steps.

By Andrej Andrejev
llmsfine-tuning
More like this →