Related papers: PCodeTrans: Translate Decompiled Pseudocode to Com…
GPGPU architectures have become significantly more diverse in recent years, which has led to an emergence of a variety of specialized programming models and software stacks to support them. Portable programming models exist, but they…
LLMs edit text and code by autoregressively regenerating the full output, even when most tokens appear verbatim in the input. We study Copy-as-Decode, a decoding-layer mechanism that recasts edit generation as structured decoding over a…
Code generation plays a crucial role in various tasks, such as code auto-completion and mathematical reasoning. Previous work has proposed numerous methods to enhance code generation performance, including integrating feedback from the…
Adapting billion-parameter language models to a downstream task is still costly, even with parameter-efficient fine-tuning (PEFT). We re-cast task adaptation as output-distribution alignment: the objective is to steer the output…
Large Language Models (LLMs) often hallucinate, producing unfaithful or factually incorrect outputs by misrepresenting the provided context or incorrectly recalling internal knowledge. Recent studies have identified specific attention heads…
Large Language Models for code generation frequently produce hallucinations in Fill-in-the-Middle (FIM) tasks -- plausible but incorrect completions such as invented API methods, invalid parameters, undefined variables, or non-existent…
With the growing reliance on automated code completion tools in software development, the need for comprehensive evaluation benchmarks has become critical. Existing benchmarks focus more on code completion in function and class level by…
The rapid growth of deep learning has driven exponential increases in model parameters and computational demands. NVIDIA GPUs and their CUDA-based software ecosystem provide robust support for parallel computing, significantly alleviating…
Vulnerabilities are challenging to locate and repair, especially when source code is unavailable and binary patching is required. Manual methods are time-consuming, require significant expertise, and do not scale to the rate at which new…
High-rate concatenated quantum codes offer a promising pathway toward fault-tolerant quantum computation, yet designing efficient decoders that fully exploit their error-correction capability remains a significant challenge. In this work,…
When source code or the original toolchain is unavailable, patching binaries is difficult because it requires editing low-level assembly code directly. As an alternative, one can decompile the binary, apply the patch at the source level,…
We introduce KodCode, a synthetic dataset that addresses the persistent challenge of acquiring high-quality, verifiable training data across diverse difficulties and domains for training Large Language Models for coding. Existing…
Detecting semantically similar functions -- a crucial analysis capability with broad real-world security usages including vulnerability detection, malware lineage, and forensics -- requires understanding function behaviors and intentions.…
There is increasing interest in applying verification tools to programs that have bitvector operations (eg., binaries). SMT solvers, which serve as a foundation for these tools, have thus increased support for bitvector reasoning through…
Artificial intelligence (AI) has revolutionized software engineering (SE) by enhancing software development efficiency. The advent of pre-trained models (PTMs) leveraging transfer learning has significantly advanced AI for SE. However,…
The parallel evolution of Large Language Models (LLMs) with advanced code-understanding capabilities and the increasing sophistication of malware presents a new frontier for cybersecurity research. This paper evaluates the efficacy of…
Large decoder-only language models (LMs) can be largely improved in terms of perplexity by retrieval (e.g., RETRO), but its impact on text generation quality and downstream task accuracy is unclear. Thus, it is still an open question: shall…
Achieving fault-tolerance will require a strong relationship between the hardware and the protocols used. Different approaches will therefore naturally have tailored proof-of-principle experiments to benchmark progress. Nevertheless,…
Software version migration and program translation are an important and costly part of the lifecycle of large codebases. Traditional machine translation relies on parallel corpora for supervised translation, which is not feasible for…
Binary code analysis plays an essential role in cybersecurity, facilitating reverse engineering to reveal the inner workings of programs in the absence of source code. Traditional approaches, such as static and dynamic analysis, extract…