Related papers: Latent Execution for Neural Program Synthesis

Symbolic execution detects vulnerabilities with precision, but applying it to large codebases requires harnesses that set up symbolic state, model dependencies, and specify assertions. Writing these harnesses has traditionally been a manual…

Large Language Models (LLMs) have exhibited exceptional performance in software engineering yet face challenges in adapting to continually evolving code knowledge, particularly regarding the frequent updates of third-party library APIs.…

The goal of active learning for program synthesis is to synthesize the desired program by asking targeted questions that minimize user interaction. While prior work has explored active learning in the purely symbolic setting, such…

Recently, deep reinforcement learning (DRL) methods have achieved impressive performance on tasks in a variety of domains. However, neural network policies produced with DRL methods are not human-interpretable and often have difficulty…

To be practically useful, modern static analyzers must precisely model the effect of both, statements in the programming language as well as frameworks used by the program under analysis. While important, manually addressing these…

We train hierarchical Transformers on the task of synthesizing hardware circuits directly out of high-level logical specifications in linear-time temporal logic (LTL). The LTL synthesis problem is a well-known algorithmic challenge with a…

Neural Algorithmic Reasoning (NAR) is a research area focused on designing neural architectures that can reliably capture classical computation, usually by learning to execute algorithms. A typical approach is to rely on Graph Neural…

High-level synthesis (HLS) allows hardware designers to create hardware designs with high-level programming languages like C/C++/OpenCL, which greatly improves hardware design productivity. However, existing HLS flows require programmers'…

Static program analysis plays an essential role in program optimization, bug detection, and debugging. However, reliance on compilation and limited customization hinder its adoption in the real world. This paper presents a compositional…

Recent advances in large language models (LLMs) for code applications have demonstrated remarkable zero-shot fluency and instruction following on challenging code related tasks ranging from test case generation to self-repair.…

The widespread use of Large Language Models (LLMs) in software engineering has intensified the need for improved model and resource efficiency. In particular, for neural code generation, LLMs are used to translate function/method signature…

For deterministic and probabilistic programs we investigate the problem of program synthesis and program optimisation (with respect to non-functional properties) in the general setting of global optimisation. This approach is based on the…

Generative models have become a powerful tool for synthesizing training data in computer vision tasks. Current approaches solely focus on aligning generated images with the target dataset distribution. As a result, they capture only the…

When a model makes a consequential decision, e.g., denying someone a loan, it needs to additionally generate actionable, realistic feedback on what the person can do to favorably change the decision. We cast this problem through the lens of…

Logic synthesis is a fundamental step in hardware design whose goal is to find structural representations of Boolean functions while minimizing delay and area. If the function is completely-specified, the implementation accurately…

Dataset distillation (DD) is a newly emerging research area aiming at alleviating the heavy computational load in training models on large datasets. It tries to distill a large dataset into a small and condensed one so that models trained…

Large language models (LLMs) suffer from catastrophic forgetting during continual learning. Conventional rehearsal-based methods rely on previous training data to retain the model's ability, which may not be feasible in real-world…

A common and effective means for improving language model capabilities involves finetuning a ``student'' language model's parameters on generations from a more proficient ``teacher'' model. Termed ``synthetic data'', these generations are…

We introduce and formalize the Synthetic Dataset Quality Estimation (SynQuE) problem: ranking synthetic datasets by their expected real-world task performance using only limited unannotated real data. This addresses a critical and open…

Compute scaling for language model (LM) pretraining has outpaced the growth of human-written texts, leading to concerns that data will become the bottleneck to LM scaling. To continue scaling pretraining in this data-constrained regime, we…