Search Results for author:
Found 21 papers, 11 papers with code
Emerging Platforms Meet Emerging LLMs: A Year-Long Journey of Top-Down Development
While a traditional bottom-up development pipeline fails to close the gap timely, we introduce TapML, a top-down approach and tooling designed to streamline the deployment of ML systems on diverse platforms, optimized for developer productivity.
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 #24 on
Code Generation
on MBPP
KernelGPT: Enhanced Kernel Fuzzing via Large Language Models
Bugs in operating system kernels can affect billions of devices and users all over the world.
Magicoder: Source Code Is All You Need
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 high-quality instruction data for code.
White-box Compiler Fuzzing Empowered by Large Language Models
Nonetheless, prompting LLMs with compiler source-code information remains a missing piece of research in compiler testing.
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
