Related papers: KodCode: A Diverse, Challenging, and Verifiable Sy…
Large Language Models (LLMs) have recently advanced many applications on software engineering tasks, particularly the potential for code generation. Among contemporary challenges, code generated by LLMs often suffers from inaccuracies and…
Human intelligence is multimodal; we integrate visual, linguistic, and acoustic signals to maintain a holistic worldview. Most current pretraining methods, however, are limited to one or two modalities. We present i-Code, a self-supervised…
In this paper we introduce ResearchCodeAgent, a novel multi-agent system leveraging large language models (LLMs) agents to automate the codification of research methodologies described in machine learning literature. The system bridges the…
We propose CoT-Self-Instruct, a synthetic data generation method that instructs LLMs to first reason and plan via Chain-of-Thought (CoT) based on given seed tasks, and then generate a new synthetic example of similar quality and complexity.…
Many software projects implement APIs and algorithms in multiple programming languages. Maintaining such projects is tiresome, as developers have to ensure that any change (e.g., a bug fix or a new feature) is being propagated, timely and…
Understanding and reasoning about code semantics is essential for enhancing code LLMs' abilities to solve real-world software engineering (SE) tasks. Although several code reasoning benchmarks exist, most rely on synthetic datasets or…
Vision Language Models (VLMs) often struggle with chart understanding tasks, particularly in accurate chart description and complex reasoning. Synthetic data generation is a promising solution, while usually facing the challenge of noise…
Large language models (LMs) of code have recently shown tremendous promise in completing code and synthesizing code from natural language descriptions. However, the current state-of-the-art code LMs (e.g., Codex (Chen et al., 2021)) are not…
Pre-trained language models have demonstrated impressive performance in both natural language processing and program understanding, which represent the input as a token sequence without explicitly modeling its structure. Some prior works…
Developers often have questions about semantic aspects of code they are working on, e.g., "Is there a class whose parent classes declare a conflicting attribute?". Answering them requires understanding code semantics such as attributes and…
Retrieval-based code question answering seeks to match user queries in natural language to relevant code snippets. Previous approaches typically rely on pretraining models using crafted bi-modal and uni-modal datasets to align text and code…
Large Language Models (LLMs) have significantly advanced automated test generation, yet existing methods often rely on ground-truth code for verification, risking bug propagation and limiting applicability in test-driven development. We…
Certified program synthesis (aka vericoding) is the process of automatically generating a program, its formal specification, and a machine-checkable proof of their alignment from a natural-language description. Two challenges make…
Large Language Models (LLMs) have recently demonstrated remarkable coding capabilities. However, assessing code generation based on well-formed properties and aligning it with developer preferences remains challenging. In this paper, we…
Training large language models (LLMs) with chain-of-thought (CoT) supervision has proven effective for enhancing their reasoning abilities. However, obtaining reliable and accurate reasoning supervision remains a significant challenge. We…
In this paper, we propose \textbf{UniCode}, a novel approach within the domain of multimodal large language models (MLLMs) that learns a unified codebook to efficiently tokenize visual, text, and potentially other types of signals. This…
Large Language Models (LLMs) have made significant strides in code generation and problem solving. Current approaches employ external tool-based iterative debuggers that use compiler or other tool-based runtime feedback to refine coarse…
Recent development of large language models (LLMs) for code like CodeX and CodeT5+ demonstrates tremendous promise in achieving code intelligence. Their ability of synthesizing code that completes a program for performing a pre-defined task…
Large Language Models (LLMs) exhibit remarkable code generation capabilities but falter when adapting to frequent updates in external library APIs. This critical limitation, stemming from reliance on outdated API knowledge from their…
In recent years, a lot of technological advances in computer science have aided software programmers to create innovative and real-time user-friendly software. With the creation of the software and the urging interest of people to learn to…