Related papers: SLICET5: Static Program Slicing using Language Mod…

Long chain-of-thought (Long CoT) reasoning improves performance on multi-step problems, but it also induces overthinking: models often generate low-yield reasoning that increases inference cost and latency. This inefficiency is especially…

This work introduces (1) a technique that allows large language models (LLMs) to leverage user-provided code when solving programming tasks and (2) a method to iteratively generate modular sub-functions that can aid future code generation…

Static analyzers are tool sets which are proving to be indispensable to modern programmers. These enable the programmers to detect possible errors and security defects present in the current code base within the implementation phase of the…

Source code reviews are manual, time-consuming, and expensive. Human involvement should be focused on analyzing the most relevant aspects of the program, such as logic and maintainability, rather than amending style, syntax, or formatting…

Addressing Out-Of-Distribution (OOD) Segmentation and Zero-Shot Semantic Segmentation (ZS3) is challenging, necessitating segmenting unseen classes. Existing strategies adapt the class-agnostic Mask2Former (CA-M2F) tailored to specific…

Real-time tool segmentation from endoscopic videos is an essential part of many computer-assisted robotic surgical systems and of critical importance in robotic surgical data science. We propose two novel deep learning architectures for…

Identifying dependency call graphs of multilanguage software systems using static code analysis is challenging. The different languages used in developing today's systems often have different lexical, syntactical, and semantic rules that…

A major bottleneck in search-based program synthesis is the exponentially growing search space which makes learning large programs intractable. Humans mitigate this problem by leveraging the compositional nature of the real world: In…

Speculative Decoding has emerged as a popular technique for accelerating inference in Large Language Models. However, most existing approaches yield only modest improvements in production serving systems. Methods that achieve substantial…

Deep learning techniques applied to program analysis tasks such as code classification, summarization, and bug detection have seen widespread interest. Traditional approaches, however, treat programming source code as natural language text,…

Code generation aims to automatically generate code snippets of specific programming language according to natural language descriptions. The continuous advancements in deep learning, particularly pre-trained models, have empowered the code…

Motivated by the increasing popularity of transformers in computer vision, in recent times there has been a rapid development of novel architectures. While in-domain performance follows a constant, upward trend, properties like robustness…

Concurrent programs are difficult to test due to their inherent non-determinism. To address this problem, testing often requires the exploration of thread schedules of a program; this can be time-consuming when applied to real-world…

Code cloning is a common practice in software development, but it poses significant security risks by propagating vulnerabilities across cloned segments. To address this challenge, we introduce srcVul, a scalable, precise detection approach…

Code super-optimization is the task of transforming any given program to a more efficient version while preserving its input-output behaviour. In some sense, it is similar to the paraphrase problem from natural language processing where the…

The forthcoming 6G networks will embrace a new realm of AI-driven services that requires innovative network slicing strategies, namely slicing for AI, which involves the creation of customized network slices to meet Quality of service (QoS)…

Fine-tuning over large pretrained language models (PLMs) has established many state-of-the-art results. Despite its superior performance, such fine-tuning can be unstable, resulting in significant variance in performance and potential risks…

Unsupervised online 3D instance segmentation is a fundamental yet challenging task, as it requires maintaining consistent object identities across LiDAR scans without relying on annotated training data. Existing methods, such as UNIT, have…

Program slicing reduces a program to a smaller version that retains a chosen computation, referred to as a slicing criterion. One recent multi-lingual slicing approach, observation-based slicing (ORBS), speculatively deletes parts of the…

Large language models (LLMs) have shown remarkable ability to generate code, yet their outputs often violate syntactic or semantic constraints when guided only through natural language prompts. We introduce TreeCoder, the most general and…