Related papers: PSD2Code: Automated Front-End Code Generation from…

The task of generating code from a natural language description, or NL2Code, is considered a pressing and significant challenge in code intelligence. Thanks to the rapid development of pre-training techniques, surging large language models…

We present Real2Code, a novel approach to reconstructing articulated objects via code generation. Given visual observations of an object, we first reconstruct its part geometry using an image segmentation model and a shape completion model.…

Multimodal geometry reasoning requires models to jointly understand visual diagrams and perform structured symbolic inference, yet current vision--language models struggle with complex geometric constructions due to limited training data…

Large language models (LLMs) have achieved notable success in code generation. However, they still frequently produce uncompilable output because their next-token inference procedure does not model formal aspects of code. Although…

Chart-to-code generation converts a chart image into an executable plotting script, enabling faithful reproduction and editable visualizations. Existing methods are largely Python-centric, limiting practical use and overlooking a critical…

Layout is a fundamental component of any graphic design. Creating large varieties of plausible document layouts can be a tedious task, requiring numerous constraints to be satisfied, including local ones relating different semantic elements…

Programming often involves converting detailed and complex specifications into code, a process during which developers typically utilize visual aids to more effectively convey concepts. While recent developments in Large Multimodal Models…

Generative models for source code are an interesting structured prediction problem, requiring to reason about both hard syntactic and semantic constraints as well as about natural, likely programs. We present a novel model for this problem…

Code completion models have made significant progress in recent years. Recently, repository-level code completion has drawn more attention in modern software development, and several baseline methods and benchmarks have been proposed.…

Code generation is increasingly critical for real-world applications. Still, diffusion-based large language models continue to struggle with this demand. Unlike free-form text, code requires syntactic precision; even minor structural…

Identifying which design patterns already exist in source code can help maintenance engineers gain a better understanding of the source code and determine if new requirements can be satisfied. There are current techniques for mining design…

Code generation models have shown significant potential for programming tasks. However, existing training methods like supervised fine-tuning face key limitations: they do not effectively teach models to prioritize correct over incorrect…

Developing safety-critical automotive software presents significant challenges due to increasing system complexity and strict regulatory demands. This paper proposes a novel framework integrating Generative Artificial Intelligence (GenAI)…

We propose a method for program generation based on semantic scaffolds, lightweight structures representing the high-level semantic and syntactic composition of a program. By first searching over plausible scaffolds then using these as…

Autoregressive decoding strategy is a commonly used method for text generation tasks with pre-trained language models, while early-exiting is an effective approach to speedup the inference stage. In this work, we propose a novel decoding…

Code completion is a prominent application of Large Language Models (LLMs) in software engineering. Due to the near real-time response requirements of this task, base models with small to medium-sized parameters are typically employed,…

Generating high-quality and diverse human images is an important yet challenging task in vision and graphics. However, existing generative models often fall short under the high diversity of clothing shapes and textures. Furthermore, the…

Recent advances in large language models (LLMs) have demonstrated impressive capabilities in code-related tasks, such as code generation and automated program repair. Despite their promising performance, most existing approaches for code…

We approach the important challenge of code autocompletion as an open-domain task, in which a sequence-to-sequence code generator model is enhanced with the ability to attend to reference code snippets supplied by a semantic code search…

Computer-aided design (CAD) is fundamental to modern engineering and manufacturing, but creating CAD models still requires expert knowledge and specialized software. Recent advances in large language models (LLMs) open up the possibility of…