67 citations · 99 across the 13 of their papers we have counts for
15 papers
Humans are Missing from AI Coding Agent Research
Zora Z. Wang, John Yang, Kilian Lieret +10
Recent progress in AI coding agent research has led to rapid improvements in agents' ability to autonomously perform complex software engineering tasks, from editing large codebase…
CAPTCHA Solving for Native GUI Agents: Automated Reasoning-Action Data Generation and Self-Corrective Training
Yuxi Chen, Haoyu Zhai, Chenkai Wang +4
GUI agents are rapidly shifting from multi-module pipelines to end-to-end, native vision-language models (VLMs) that perceive raw screenshots and directly interact with digital dev…
SWE-Replay: Efficient Test-Time Scaling for Software Engineering Agents
Yifeng Ding, Lingming Zhang
Test-time scaling has been widely adopted to enhance the capabilities of Large Language Model (LLM) agents in software engineering (SWE) tasks. However, the standard approach of re…
InfiniteVGGT: Visual Geometry Grounded Transformer for Endless Streams
Shuai Yuan, Yantai Yang, Xiaotian Yang +4
The grand vision of enabling persistent, large-scale 3D visual geometry understanding is shackled by the irreconcilable demands of scalability and long-term stability. While offlin…
Toward Training Superintelligent Software Agents through Self-Play SWE-RL
Yuxiang Wei, Zhiqing Sun, Emily McMilin +6
While current software agents powered by large language models (LLMs) and agentic reinforcement learning (RL) can boost programmer productivity, their training data (e.g., GitHub i…
CWM: An Open-Weights LLM for Research on Code Generation with World Models
FAIR CodeGen team, Jade Copet, Quentin Carbonneaux +48
We release Code World Model (CWM), a 32-billion-parameter open-weights LLM, to advance research on code generation with world models. To improve code understanding beyond what can…
PurpCode: Reasoning for Safer Code Generation
Jiawei Liu, Nirav Diwan, Zhe Wang +11
We introduce PurpCode, the first post-training recipe for training safe code reasoning models towards generating secure code and defending against malicious cyberactivities. PurpCo…
SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution
Yuxiang Wei, Olivier Duchenne, Jade Copet +6
The recent DeepSeek-R1 release has demonstrated the immense potential of reinforcement learning (RL) in enhancing the general reasoning capabilities of large language models (LLMs)…
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…
Evaluating Language Models for Efficient Code Generation
Jiawei Liu, Songrun Xie, Junhao Wang +3
We introduce Differential Performance Evaluation (DPE), a framework designed to reliably evaluate Large Language Models (LLMs) for efficient code generation. Traditional coding ben…
RepoQA: Evaluating Long Context Code Understanding
Jiawei Liu, Jia Le Tian, Vijay Daita +5
Recent advances have been improving the context windows of Large Language Models (LLMs). To quantify the real long-context capabilities of LLMs, evaluators such as the popular Need…
XFT: Unlocking the Power of Code Instruction Tuning by Simply Merging Upcycled Mixture-of-Experts
Yifeng Ding, Jiawei Liu, Yuxiang Wei +2
We introduce XFT, a simple yet powerful training scheme, by simply merging upcycled Mixture-of-Experts (MoE) to unleash the performance limit of instruction-tuned code Large Langua…
Productively Deploying Emerging Models on Emerging Platforms: A Top-Down Approach for Testing and Debugging
Siyuan Feng, Jiawei Liu, Ruihang Lai +4
While existing machine learning (ML) frameworks focus on established platforms, like running CUDA on server-grade GPUs, there have been growing demands to enable emerging AI applic…
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…
Magicoder: Empowering Code Generation with OSS-Instruct
Yuxiang Wei, Zhe Wang, Jiawei Liu +2
We introduce Magicoder, a series of fully open-source (code, weights, and data) Large Language Models (LLMs) for code that significantly closes the gap with top code models while h…