Related papers: SmartFL: Semantics Based Probabilistic Fault Local…

Non-IID data distribution across clients and poisoning attacks are two main challenges in real-world federated learning (FL) systems. While both of them have attracted great research interest with specific strategies developed, no known…

We are interested in long-term deployments of autonomous robots to aid astronauts with maintenance and monitoring operations in settings such as the International Space Station. Unfortunately, such environments tend to be highly dynamic and…

Embedded controllers for cyber-physical systems are often parameterized by look-up maps representing discretizations of continuous functions on metric spaces. For example, a non-linear control action may be represented as a table of…

Large language models (LLMs) show remarkable promise for democratizing automated reasoning by generating formal specifications. However, a fundamental tension exists: LLMs are probabilistic, while formal verification demands deterministic…

As Federated Learning (FL) expands to larger and more distributed environments, consistency in training is challenged by network-induced delays, clock unsynchronicity, and variability in client updates. This combination of factors may…

The rising cost of acquiring supervised data has driven significant interest in self-improvement for large language models (LLMs). Straightforward unsupervised signals like majority voting have proven effective in generating pseudo-labels…

The goal of combining the robustness of neural networks and the expressiveness of symbolic methods has rekindled the interest in Neuro-Symbolic AI. Deep Probabilistic Programming Languages (DPPLs) have been developed for probabilistic logic…

Test-time scaling methods have seen a rapid increase in popularity for its computational efficiency and parameter-independent training to improve reasoning performance on Large Language Models. One such method is called budget forcing, a…

Semantic segmentation is an important task that helps autonomous vehicles understand their surroundings and navigate safely. During deployment, even the most mature segmentation models are vulnerable to various external factors that can…

Large Language Models (LLMs) have demonstrated remarkable performance across a broad spectrum of tasks, including natural language understanding, dialogue systems, and code generation. Despite evident progress, less attention has been paid…

Large language models exhibit systematic negation sensitivity, yet no operational framework exists to measure this vulnerability at deployment scale, especially in high-stakes decisions. We introduce Syntactic Framing Fragility (SFF), a…

Large language models (LLMs) have achieved impressive results on multi-step mathematical reasoning, yet at the cost of high computational overhead. This challenge is particularly acute for test-time scaling methods such as parallel…

We propose a computational framework to quantify (measure) and to optimize the reliability of complex systems. The approach uses a graph representation of the system that is subject to random failures of its components (nodes and edges).…

The wide availability of data coupled with the computational advances in artificial intelligence and machine learning promise to enable many future technologies such as autonomous driving. While there has been a variety of successful…

Language models have improved by orders of magnitude with the recent emergence of Transformer-based Large Language Models (LLMs). LLMs have demonstrated their ability to generate natural code that is highly similar to code written by…

In a software product line (SPL), a collection of software products is defined by their commonalities in terms of features rather than explicitly specifying all products one-by-one. Several verification techniques were adapted to establish…

Safety-critical infrastructures must operate in a safe and reliable way. Fault tree analysis is a widespread method used for risk assessment of these systems: fault trees (FTs) are required by, e.g., the Federal Aviation Administration and…

We propose Semantic Parser Localizer (SPL), a toolkit that leverages Neural Machine Translation (NMT) systems to localize a semantic parser for a new language. Our methodology is to (1) generate training data automatically in the target…

The recent advances in network management automation and Software-Defined Networking (SDN) are easing network policy management tasks. At the same time, these new technologies create a new mode of failure in the management cycle itself.…

Correctness alone is insufficient: LLM-generated programs frequently satisfy unit tests while violating contest time or memory budgets. We present SwiftSolve, a complexity-aware multi-agent system for competitive programming that couples…