67 citations · 139 across the 12 of their papers we have counts for
12 papers
The Best Programming Language for Tokenmaxxing: An Investigation of Coding Agent Behavior Across Programming Languages
Zixuan Wu, Carolyn Jane Anderson, Arjun Guha
Although coding agents are now very effective in a variety of programming languages, this paper first shows that the cost (in tokens) can very significantly by programming language…
Learning Reasoning World Models for Parallel Code
Gautam Singh, Arjun Guha, Bhavya Kailkhura +1
Large language models have shown remarkable ability in serial code generation, but they still struggle with parallel code for which training data is comparatively scarce. A common…
The HyperFrog Cryptosystem: High-Genus Voxel Topology as a Trapdoor for Post-Quantum KEMs
Victor Duarte Melo
HyperFrog is an experimental post-quantum Key Encapsulation Mechanism that explores a variant of the Learning With Errors (LWE) design space in which the secret is not sampled from…
AgentPack: A Dataset of Code Changes, Co-Authored by Agents and Humans
Yangtian Zi, Zixuan Wu, Aleksander Boruch-Gruszecki +2
Fine-tuning large language models for code editing has typically relied on mining commits and pull requests. The working hypothesis has been that commit messages describe human int…
Agnostics: Learning to Code in Any Programming Language via Reinforcement with a Universal Learning Environment
Aleksander Boruch-Gruszecki, Yangtian Zi, Zixuan Wu +4
Large language models (LLMs) already excel at writing code in high-resource languages such as Python and JavaScript, yet stumble on low-resource languages that remain essential to…
"I Would Have Written My Code Differently'': Beginners Struggle to Understand LLM-Generated Code
Yangtian Zi, Luisa Li, Arjun Guha +2
Large language models (LLMs) are being increasingly adopted for programming work. Prior work shows that while LLMs accelerate task completion for professional programmers, beginnin…
ReasoningWeekly: A General Knowledge and Verbal Reasoning Challenge for Large Language Models
Zixuan Wu, Francesca Lucchetti, Aleksander Boruch-Gruszecki +5
Existing benchmarks for frontier models often test specialized, "PhD-level" knowledge that is difficult for non-experts to grasp. In contrast, we present a benchmark with 613 probl…
SelfCodeAlign: Self-Alignment for Code Generation
Yuxiang Wei, Federico Cassano, Jiawei Liu +7
Instruction tuning is a supervised fine-tuning approach that significantly improves the ability of large language models (LLMs) to follow human instructions. We propose SelfCodeAli…
Substance Beats Style: Why Beginning Students Fail to Code with LLMs
Francesca Lucchetti, Zixuan Wu, Arjun Guha +2
Although LLMs are increasing the productivity of professional programmers, existing work shows that beginners struggle to prompt LLMs to solve text-to-code tasks. Why is this the c…
StarCoder 2 and The Stack v2: The Next Generation
Anton Lozhkov, Raymond Li, Loubna Ben Allal +63
The BigCode project, an open-scientific collaboration focused on the responsible development of Large Language Models for Code (Code LLMs), introduces StarCoder2. In partnership wi…
How Beginning Programmers and Code LLMs (Mis)read Each Other
Sydney Nguyen, Hannah McLean Babe, Yangtian Zi +3
Generative AI models, specifically large language models (LLMs), have made strides towards the long-standing goal of text-to-code generation. This progress has invited numerous stu…
Can It Edit? Evaluating the Ability of Large Language Models to Follow Code Editing Instructions
Federico Cassano, Luisa Li, Akul Sethi +8
A significant amount of research is focused on developing and evaluating large language models for a variety of code synthesis tasks. These include synthesizing code from natural l…