Search Results for author:
Found 29 papers, 20 papers with code
KNighter: Transforming Static Analysis with LLM-Synthesized Checkers
Our evaluation on the Linux kernel demonstrates that KNighter generates high-precision checkers capable of detecting diverse bug patterns overlooked by existing human-written analyzers.
SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution
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
In our primary experiments, we use SelfCodeAlign with CodeQwen1. 5-7B to generate a dataset of 74k instruction-response pairs.
Large Language Model-Based Agents for Software Engineering: A Survey
The recent advance in Large Language Models (LLMs) has shaped a new paradigm of AI agents, i. e., LLM-based agents.
Evaluating Language Models for Efficient Code Generation
We introduce Differential Performance Evaluation (DPE), a framework designed to reliably evaluate Large Language Models (LLMs) for efficient code generation.
Agentless: Demystifying LLM-based Software Engineering Agents
However, the complexity of these agent-based approaches, together with the limited abilities of current LLMs, raises the following question: Do we really have to employ complex autonomous software agents?
RepoQA: Evaluating Long Context Code Understanding
Recent advances have been improving the context windows of Large Language Models (LLMs).
XFT: Unlocking the Power of Code Instruction Tuning by Simply Merging Upcycled Mixture-of-Experts
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 Language Models (LLMs).
Productively Deploying Emerging Models on Emerging Platforms: A Top-Down Approach for Testing and Debugging
However, this traditional development approach fails to meet the productivity requirements when deploying emerging ML applications, with the testing and debugging part as a bottleneck.
Top Leaderboard Ranking = Top Coding Proficiency, Always? EvoEval: Evolving Coding Benchmarks via LLM
Such limitations inevitably lead us to inquire: Is the leaderboard performance on existing benchmarks reliable and comprehensive enough to measure the program synthesis ability of LLMs?
StarCoder 2 and The Stack v2: The Next Generation
Our large model, StarCoder2- 15B, significantly outperforms other models of comparable size.
Ranked #35 on
Code Generation
on MBPP
KernelGPT: Enhanced Kernel Fuzzing via Large Language Models
As a result, a large body of research has been focused on kernel fuzzing, i. e., automatically generating syscall (system call) sequences to detect potential kernel bugs or vulnerabilities.
Magicoder: Empowering Code Generation with OSS-Instruct
Magicoder models are trained on 75K synthetic instruction data using OSS-Instruct, a novel approach to enlightening LLMs with open-source code snippets to generate diverse instruction data for code.
WhiteFox: White-Box Compiler Fuzzing Empowered by Large Language Models
To this end, we propose WhiteFox, the first white-box compiler fuzzer using LLMs with source-code information to test compiler optimization, with a spotlight on detecting deep logic bugs in the deep learning (DL) compilers.
Copiloting the Copilots: Fusing Large Language Models with Completion Engines for Automated Program Repair
Therefore, we propose Repilot, a general code generation framework to further copilot the AI "copilots" (i. e., LLMs) by synthesizing more valid patches during the repair process.
Fuzz4All: Universal Fuzzing with Large Language Models
Moreover, the inputs generated by existing fuzzers are often limited to specific features of the input language, and thus can hardly reveal bugs related to other or new features.
Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation
While EvalPlus is general, we extend the test-cases of the popular HumanEval benchmark by 80x to build HumanEval+.
Keep the Conversation Going: Fixing 162 out of 337 bugs for $0.42 each using ChatGPT
For earlier patches that failed to pass all tests, we combine the incorrect patches with their corresponding relevant test failure information to construct a new prompt for the LLM to generate the next patch.
Revisiting the Plastic Surgery Hypothesis via Large Language Models
Traditional APR tools have largely leveraged the plastic surgery hypothesis by designing manual or heuristic-based approaches to exploit such existing code ingredients.
NeuRI: Diversifying DNN Generation via Inductive Rule Inference
NeuRI finds 100 new bugs for PyTorch and TensorFlow in four months, with 81 already fixed or confirmed.
Conversational Automated Program Repair
As such, we leverage the long-term context window of LLMs to not only avoid generating previously incorrect patches but also incorporate validation feedback to help the model understand the semantic meaning of the program under test.
NNSmith: Generating Diverse and Valid Test Cases for Deep Learning Compilers
In this work, we propose a new fuzz testing approach for finding bugs in deep-learning compilers.
Two-Stream Graph Convolutional Network for Intra-oral Scanner Image Segmentation
The state-of-the-art deep learning-based methods often simply concatenate the raw geometric attributes (i. e., coordinates and normal vectors) of mesh cells to train a single-stream network for automatic intra-oral scanner image segmentation.
Coverage-Guided Tensor Compiler Fuzzing with Joint IR-Pass Mutation
Our results show that Tzer substantially outperforms existing fuzzing techniques on tensor compiler testing, with 75% higher coverage and 50% more valuable tests than the 2nd-best technique.
3D Dental model segmentation with graph attentional convolution network
We have evaluated our network on a real-patient dataset of dental models acquired through 3D intraoral scanners, and experimental results show that our method outperforms state-of-the-art deep learning methods for 3D shape segmentation.
TSGCNet: Discriminative Geometric Feature Learning With Two-Stream Graph Convolutional Network for 3D Dental Model Segmentation
State-of-the-art methods directly concatenate the raw attributes of 3D inputs, namely coordinates and normal vectors of mesh cells, to train a single-stream network for fully-automated tooth segmentation.
TSGCNet: Discriminative Geometric Feature Learning with Two-Stream GraphConvolutional Network for 3D Dental Model Segmentation
State-of-the-art methods directly concatenate the raw attributes of 3D inputs, namely coordinates and normal vectors of mesh cells, to train a single-stream network for fully-automated tooth segmentation.
DeepBillboard: Systematic Physical-World Testing of Autonomous Driving Systems
Furthermore, DeepBillboard is sufficiently robust and resilient for generating physical-world adversarial billboard tests for real-world driving under various weather conditions.
DeepRoad: GAN-based Metamorphic Autonomous Driving System Testing
In this paper, we propose DeepRoad, an unsupervised framework to automatically generate large amounts of accurate driving scenes to test the consistency of DNN-based autonomous driving systems across different scenes.
Software Engineering
