paper-with-me

Papers

AnCoder: Anchored Code Generation via Discrete Diffusion Models

2026-02-05 · Anton Xue, Litu Rout, Constantine Caramanis, Sanjay Shakkottai arxiv

Diffusion language models offer a compelling alternative to autoregressive code generation, enabling global planning and iterative refinement of complex program logic. However, existing approaches fail to respect the rigid structure of programming languages and, as a result, often produce broken programs that fail to execute. To address this, we introduce AnchorTree, a framework that explicitly anchors the diffusion process using structured, hierarchical priors native to code. Specifically, AnchorTree uses the abstract syntax tree to prioritize resolving syntactically and semantically salient tokens, such as keywords (e.g., if, while) and identifiers (e.g., variable names), thereby establishing a structural scaffold that guides the remaining generation. We validate this framework via AnCoder, a family of models showing that structurally anchored diffusion offers a parameter-efficient path to high-quality code generation.

📄 PDF Abstract BibTeX arXiv:2602.17688

Code (0)

등록된 구현이 없습니다.

Tasks

Code Generation

Similar Papers 제목 키워드 기반

GANCoder: An Automatic Natural Language-to-Programming Language Translation Approach based on GAN

2019-12-02 · Yabing Zhu, Yanfeng Zhang, Huili Yang, Fangjing Wang

We propose GANCoder, an automatic programming approach based on Generative Adversarial Networks (GAN), which can generate the same functional and logical programming language codes conditioned on the given natural langua…

Code GenerationTranslation

Test-Time Anchoring for Discrete Diffusion Posterior Sampling

2025-10-02 · Litu Rout, Andreas Lugmayr, Yasamin Jafarian, Srivatsan Varadharajan 외 arxiv

While continuous diffusion models have achieved remarkable success, discrete diffusion offers a unified framework for jointly modeling text and images. Beyond unification, discrete diffusion provides faster inference, fi…

Question Answering

Unified Generation, Reconstruction, and Representation: Generalized Diffusion with Adaptive Latent Encoding-Decoding

2024-02-29 · Guangyi Liu, Yu Wang, Zeyu Feng, Qiyu Wu 외

The vast applications of deep generative models are anchored in three core capabilities -- generating new instances, reconstructing inputs, and learning compact representations -- across various data types, such as discr…

DecoderDenoising

Reconstruction-Anchored Diffusion Model for Text-to-Motion Generation

2026-01-21 · Yifei Liu, Changxing Ding, Ling Guo, Huaiguang Jiang 외 arxiv

Diffusion models have seen widespread adoption for text-driven human motion generation and related tasks due to their impressive generative capabilities and flexibility. However, current motion diffusion models face two …

Bring the Noise: Introducing Noise Robustness to Pretrained Automatic Speech Recognition

2023-09-05 · Patrick Eickhoff, Matthias Möller, Theresa Pekarek Rosin, Johannes Twiefel 외

In recent research, in the domain of speech processing, large End-to-End (E2E) systems for Automatic Speech Recognition (ASR) have reported state-of-the-art performance on various benchmarks. These systems intrinsically …

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)DecoderDenoising+2