Search Results for author:
Found 13 papers, 5 papers with code
CNNSAT: Fast, Accurate Boolean Satisfiability using Convolutional Neural Networks
Boolean satisfiability (SAT) is one of the most well-known NP-complete problems and has been extensively studied.
API-guided Dataset Synthesis to Finetune Large Code Models
Inspired by APIs as high-level abstractions of code that encapsulate rich semantic information in a concise structure, we propose DataScope, an API-guided dataset synthesis framework designed to enhance the SFT process for LCMs in both general and domain-specific scenarios.
Precise and Generalized Robustness Certification for Neural Networks
We identify two key properties, independence and continuity, that convert the latent space into a precise and analysis-friendly input space representation for certification.
ShapeFlow: Dynamic Shape Interpreter for TensorFlow
We present ShapeFlow, a dynamic abstract interpreter for TensorFlow which quickly catches tensor shape incompatibility errors, one of the most common bugs in deep learning code.
Testing Machine Translation via Referential Transparency
Machine translation software has seen rapid progress in recent years due to the advancement of deep neural networks.
On the Unusual Effectiveness of Type-aware Mutations for Testing SMT Solvers
Among the 909 bugs found by OpFuzz, 130 were soundness bugs, the most critical bugs in SMT solvers, and 501 were in the default modes of the solvers.
Software Engineering Programming Languages
Metamorphic Testing for Object Detection Systems
To fill this critical gap, we introduce the design and realization of MetaOD, the first metamorphic testing system for object detectors to effectively reveal erroneous detection results by commercial object detectors.
Structure-Invariant Testing for Machine Translation
Despite its apparent importance, validating the robustness of machine translation systems is very difficult and has, therefore, been much under-explored.
Learning Blended, Precise Semantic Program Embeddings
Learning on the same set of functions (more than 170K in total), \liger significantly outperforms code2seq, the previous state-of-the-art for method name prediction.
How Training Data Affect the Accuracy and Robustness of Neural Networks for Image Classification
In light of a recent study on the mutual influence between robustness and accuracy over 18 different ImageNet models, this paper investigates how training data affect the accuracy and robustness of deep neural networks.
Dynamic Neural Program Embeddings for Program Repair
Our evaluation results show that the semantic program embeddings significantly outperform the syntactic program embeddings based on token sequences and abstract syntax trees.
Dynamic Neural Program Embedding for Program Repair
Evaluation results show that our new semantic program embedding significantly outperforms the syntactic program embeddings based on token sequences and abstract syntax trees.
Interactive, Intelligent Tutoring for Auxiliary Constructions in Geometry Proofs
Although there exist many intelligent tutoring systems proposed for geometry proofs, few teach students how to find auxiliary constructions.
