Latest papers
In large-scale machine learning, distributed training commonly involves multiple workers evaluating the gradients of the model on different dataset partitions. A common challenge is the presence of straggling workers, which may…
Graph Neural Networks trained on heterogenous bipartite graphs form a common basis in recommendation systems. These graphs often express relations that vary in cardinality, for example, user-item preferences are one-to-many and…
As LLMs become more capable, they are increasingly deployed as collaborative agents, taking on user-delegated tasks through iterative interaction. Yet genuine interaction is inherently dynamic: users rarely specify their intent upfront,…
The library \texttt{librla} is a randomized linear algebra library that is specifically designed for the intermediate-sized matrices (of dimension up to roughly 10,000) that arise in applications such as reduced order modeling, fast direct…
Fuzzy-rule-based scalar objective functions provide a flexible way to encode qualitative preferences, reference regions, and interactions between criteria in multi-criteria optimization and decision making. However, the scalar preference…
Large language models increasingly use search tools to retrieve up-to-date information, introducing a new attack surface in which retrieved documents can be manipulated. This risk is amplified by the development of generative engine…
A record system declares when two records refer to the same entity, occurrence, scope, or rule. Its disclosed implementation mechanisms induce a corresponding operational identity relation. The declared and implemented relations may diverge…
Differential privacy under Continual Observation (CO) quantifies the loss in privacy that occurs when outputs generated using a stream of sensitive input data are published in the online setting. In this paper, we consider a more stringent…
This work presents LeakyLMs, a set of attacks that leak proprietary model, architecture, and deployment information from production language models. LeakyLMs is the first to demonstrate that key model and deployment details can be inferred…
Large language models trained and aligned within different linguistic and regional ecosystems may frame the same political, cultural, and geopolitical entities in different ways. Such differences are often evaluated through sentiment,…
Harnessing the potential of electroencephalography (EEG) for brain research is fundamentally limited by intrinsic noise and the diffuse projection of brain-generated activity over the scalp. The standard event-related potential (ERP)…
The stochastic block model is a widely studied model of community structure in networks. Here we study the component structure and percolation properties of networks generated from this model and its variants, using exact methods based on…
LLM-based coding tools enable non-expert users to generate routine automation scripts that may enter enterprise workflows without meaningful security review. This study examines that risk directly. Code was collected from ChatGPT, Microsoft…
Security protocol verification relies on formal tools such as ProVerif and OFMC. This study evaluates whether Large Language Models (LLMs) can perform comparable analysis. We test GPT and DeepSeek in chat and reasoning modes over three runs…
The presence of UAVs in military operations has recently increased, also increasing the demand for defense systems against UAV attacks. UAVs can also be used as countermeasures. Most available methods rely on UAV-to-UAV communication and…
Traditional agent development is split across prompt templates, tool schemas, callback code, and workflow graphs. We present NVIDIA Object-Oriented Agents (NOOA), a model-agnostic Python framework for building reliable AI agents. NOOA takes…
A recent line of work measures causal emergence in reinforcement learning agents through Integrated Information Decomposition, reporting that $\Phi_r$ grows with training and tracks reward improvement. For active inference, this raises the…
The growing need for secure and convenient authentication methods has led to the increasing popularity of biometric solutions. In addition to traditional and popular methods, such as fingerprint or iris scanning, voice-based approaches are…
Interactive image segmentation is critical for efficient image annotation; however, existing methods often require many corrective clicks or rely on passive refinement schemes that converge slowly. We propose Uncertainty-Guided Cascade…
The operation of blockchain is governed by consensus algorithms (CA). Several consensus mechanisms require significant computational power, while others necessitate high amounts of stakes to select the participant to validate and verify the…