Related papers: Static Analysis Driven Enhancements for Comprehens…
Current autoregressive language models couple high-level reasoning and low-level token generation into a single sequential process, making the reasoning trajectory vulnerable to compounding expression errors. We propose JEPA-Reasoner, a…
Code large language models (LLMs) face limitations in repository-level code generation due to their lack of awareness of repository-level dependencies (e.g., user-defined attributes), resulting in dependency errors such as…
Deep learning has demonstrated great abilities in various code generation tasks. However, despite the great convenience for some developers, many are concerned that the code generators may recite or closely mimic copyrighted training data…
Despite the efficiency of prompt learning in transferring vision-language models (VLMs) to downstream tasks, existing methods mainly learn the prompts in a coarse-grained manner where the learned prompt vectors are shared across all…
Literate computing has emerged as an important tool for computational studies and open science, with growing folklore of best practices. In this work, we report two case studies - one in computational magnetism and another in computational…
Pointer analysis is foundational for many static analysis tasks, yet its effectiveness is often hindered by imprecise modeling of heap allocations, particularly in C/C++ programs where custom allocation functions (CAFs) are pervasive.…
Handwritten mathematical expression recognition (HMER) is a challenging task that has many potential applications. Recent methods for HMER have achieved outstanding performance with an encoder-decoder architecture. However, these methods…
Active learning (AL) has demonstrated remarkable potential in reducing the annotation effort required for training machine learning models. However, despite the surging popularity of natural language generation (NLG) tasks in recent years,…
Dynamically typed languages such as JavaScript and Python have emerged as the most popular programming languages in use. Important benefits can accrue from including type annotations in dynamically typed programs. This approach to gradual…
Despite significant advances in graph representation learning, little attention has been paid to the more practical continual learning scenario in which new categories of nodes (e.g., new research areas in citation networks, or new types of…
Automatic generation of high-quality commit messages for code commits can substantially facilitate software developers' works and coordination. However, the semantic gap between source code and natural language poses a major challenge for…
With their high information density and intuitive readability, charts have become the de facto medium for data analysis and communication across disciplines. Recent multimodal large language models (MLLMs) have made notable progress in…
Code search is an important and frequent activity for developers using computational notebooks (e.g., Jupyter). The flexibility of notebooks brings challenges for effective code search, where classic search interfaces for traditional…
One of the most time-consuming tasks for developers is the comprehension of new code bases. An effective approach to aid this process is to label source code files with meaningful annotations, which can help developers understand the…
Large language models (LLMs) have shown that generative pretraining can distill vast world knowledge into compact token representations. While LLMs encapsulate extensive world knowledge, they remain limited in modeling the behavioral…
To enhance developer productivity, all modern integrated development environments (IDEs) include code suggestion functionality that proposes likely next tokens at the cursor. While current IDEs work well for statically-typed languages,…
Graph-based computations are crucial in a wide range of applications, where graphs can scale to trillions of edges. To enable efficient training on such large graphs, mini-batch subgraph sampling is commonly used, which allows training…
The ability to automatically estimate the quality and coverage of the samples produced by a generative model is a vital requirement for driving algorithm research. We present an evaluation metric that can separately and reliably measure…
Computational notebooks (e.g., Jupyter, Google Colab) are widely used by data scientists. A key feature of notebooks is the interactive computing model of iteratively executing cells (i.e., a set of statements) and observing the result…
The ability to research and synthesize knowledge is central to human expertise and progress. A new class of AI systems--designed for generative research synthesis--aims to automate this process by retrieving information from the live web…