Related papers: Hydra: Efficient, Correct Code Generation via Chec…

Large Language Models (LLMs) can translate natural language requirements into code, yet empirical analyses of representative models reveal that semantic errors-programs that compile but behave incorrectly-constitute the majority of observed…

Large language models (LLMs) and agentic systems have recently demonstrated potential for automating scientific workflows, including atomistic simulations. However, their deployment in high-performance computing (HPC) environments remains…

The LR(1) Parser Generation System generates full LR(1) parsers that are comparable in speed and size to those generated by LALR(1) parser generators, such as yacc [5]. LR contains a number of novel feature. This paper discusses three of…

Historically, memory management based on lock-free reference counting was very inefficient, especially for read-dominated workloads. Thus, approaches such as epoch-based reclamation (EBR), hazard pointers (HP), or a combination thereof have…

Transformer language models generate text autoregressively, making inference latency proportional to the number of tokens generated. Speculative decoding reduces this latency without sacrificing output quality, by leveraging a small draft…

Constant-time programming is a widely deployed approach to harden cryptographic programs against side channel attacks. However, modern processors often violate the underlying assumptions of standard constant-time policies by transiently…

Code generation models are not robust to small perturbations, which often lead to incorrect generations and significantly degrade the performance of these models. Although improving the robustness of code generation models is crucial to…

A fundamental limitation of Text-to-Code is that no guarantee can be obtained about the correctness of the generated code. Therefore, to ensure its correctness, the generated code still has to be reviewed, tested, and maintained by…

Current static verification techniques support a wide range of programs. However, such techniques only support complete and detailed specifications, which places an undue burden on users. To solve this problem, prior work proposed gradual…

Software documentation supports a broad set of software maintenance tasks; however, creating and maintaining high-quality, multi-level software documentation can be incredibly time-consuming and therefore many code bases suffer from a lack…

Large language models frequently commit unrecoverable reasoning errors mid-generation: once a wrong step is taken, subsequent tokens compound the mistake rather than correct it. We introduce $\textbf{Latent Phase-Shift Rollback}$ (LPSR): at…

Standard language models generate text by selecting tokens from a fixed, finite, and standalone vocabulary. We introduce a novel method that selects context-aware phrases from a collection of supporting documents. One of the most…

Assertion checking is an invaluable programmer's tool for finding many classes of errors or verifying their absence in dynamic languages such as Prolog. For Prolog programmers this means being able to have relevant properties such as modes,…

Erasure codes provide a storage efficient alternative to replication based redundancy in (networked) storage systems. They however entail high communication overhead for maintenance, when some of the encoded fragments are lost and need to…

The use of large language models (LLMs) for automated code generation has emerged as a significant focus within AI research. As these pretrained models continue to evolve, their ability to understand and generate complex code structures has…

Repairing RTL bugs is crucial for hardware design and verification. Traditional automatic program repair (APR) methods define dedicated search spaces to locate and fix bugs with program synthesis. However, they heavily rely on fixed…

The advent of large language models trained on code (code LLMs) has led to significant progress in language-to-code generation. State-of-the-art approaches in this area combine LLM decoding with sample pruning and reranking using test cases…

Training next-generation code generation models requires high-quality datasets, yet existing datasets face difficulty imbalance, format inconsistency, and data quality problems. We address these challenges through systematic data processing…

Data generation and analysis is a fundamental aspect of many industries and disciplines, from strategic decision making in business to research in the physical and social sciences. However, data generated using software and algorithms can…

Generating knowledge-intensive and comprehensive long texts, such as encyclopedia articles, remains significant challenges for Large Language Models. It requires not only the precise integration of facts but also the maintenance of thematic…