With the accelerating development of quantum technologies and their growing computational potential, quantum systems are being adapted for simulations and other...
Developers create modern software applications (Apps) on top of third-party libraries (Libs). When library vulnerabilities are reachable through application cod...
Several recent Transformer architectures expose later layers to representations computed in the earliest layers, motivated by the observation that low-level fea...
Coding agents often pass per-prompt safety review yet ship exploitable code when their tasks are decomposed into routine engineering tickets. The challenge is s...
Although recent LMMs have become much stronger at visual perception, they remain unreliable on problems that require multi-step reasoning over visual evidence. ...
Standard differential privacy imposes uniform privacy constraints across all features, overlooking the inherent distinction between sensitive and insensitive fe...
As quantum computing transitions from theoretical experimentation to its practical application, the reliability of quantum software has become a critical bottle...
Reservoir characterization workflows increasingly rely on image-based and machine-learning/deep learning or even generative AI approaches, but openly available ...
Conceptual analysis -- proposing definitions and refining them through counterexamples -- is central to philosophical methodology. We study whether language mod...
Question: Does atomic fact-checking, which decomposes AI treatment recommendations into individually verifiable claims linked to source guideline documents, inc...
Large language models can be steered at inference time through prompting or activation interventions, but activation steering methods often underperform compare...
This paper presents a reproducible and process-aware pipeline for predictive monitoring of clinical pathways. The approach integrates data lifting, temporal rec...
Motivated by the growing proliferation of federated learning (FL) in edge environments, we present the first systematic characterization of transport-layer brea...
Formal verification provides the highest assurance of software correctness and security, but its application to large-scale, evolving systems remains a major ch...
This paper analyzes the strategic education process aimed at transitioning traditional software development squads into hybrid structures centered on collaborat...
ASIC cryptocurrency miners are a core component of blockchain infrastructures, directly converting computation and energy into monetary value. Despite their eco...
We address day-ahead transmission topology planning and congestion management as a sequential, multi-objective optimization problem and develop two complementar...
Human involvement is critical in training and deploying AI systems in high-stakes defence and security contexts. However, real-time interaction is impractical i...
Understanding how biological and artificial neural networks implement computation from connectivity is a central problem in neuroscience and machine learning. I...
Understanding how biological and artificial neural networks implement computation from connectivity is a central problem in neuroscience and machine learning. I...
It has been demonstrated that specialised architectures, such as FPGAs and AMD's AI Engines (AIEs), have the potential to deliver energy and performance advanta...
As exascale systems reach unprecedented concurrency, traditional performance analysis tools struggle with the overhead of massive-scale telemetry. We present an...
We study the possibility of designing N^{o(1)}-round protocols for problems of substantially super-linear polynomial-time (sequential) complexity in the model o...
Recurrent networks that store position, phase, or other continuous variables need state-space directions that remain neutral over long horizons. We give a symme...
Modern GPUs increasingly rely on specialized and asynchronous hardware units to deliver high performance. Yet these units are often underutilized because today'...
Recent advances in large language models have led to the rise of software systems (i.e. agents) that execute with increasing autonomy on behalf of users in open...
For over a century, the electric grid has relied on a single statistical assumption: load diversity, the principle that the uncorrelated demands of millions of ...
Personalized image completion aims to restore occluded regions in personal photos while preserving identity and appearance. Existing methods either rely on gene...
Speculative decoding accelerates large language model (LLM) inference by using a small draft model to propose candidate tokens that a larger target model verifi...
Speculative decoding accelerates large language model (LLM) inference by using a small draft model to propose candidate tokens that a larger target model verifi...
Ensuring the coherence of regional socio-economic statistics is a central task for national statistical institutes. Traditional validation tools, such as range ...
Composite materials exhibit strongly hierarchical and anisotropic properties governed by coupled mechanisms spanning constituents, plies, laminates, structures,...
Smart contract vulnerabilities in Decentralized Finance caused over billions of dollars losses every year, yet the security community faces a critical bottlenec...
Despite significant advances in Reinforcement Learning (RL), model performance remains highly sensitive to algorithm and hyperparameter configurations, while ge...
Rural thematic road network construction aims to extract topological road structures from movement trajectory images of agricultural machinery. However, this ta...
Traditional image quality assessment (IQA) methods rely on mean opinion scores (MOS), which are resource-intensive to collect and fail to provide interpretable,...
Cross-language code clone detection (X-CCD) is challenging because semantically equivalent programs written in different languages often share little surface si...
Scientists increasingly rely on sensor-based data, yet transforming raw streams into insights across the edge-to-cloud continuum remains difficult. Provisioning...
Understanding whether deep neural networks are effectively optimized remains challenging, as training occurs in highly nonconvex landscapes and standard metrics...
Diffusion models provide a powerful generative prior for perceptual reconstruction at ultra-low bitrates, but effective video compression requires controlling t...
Scientists increasingly rely on sensor-based data; however transforming raw streams into insights across the edge-to-cloud continuum remains difficult due to th...
We introduce PLACE (Persistence-Landmark Analytic Classification Engine), a closed-form pipeline for classifying point clouds and graphs through their persisten...
Videos are unique in their ability to capture actions which transcend multiple frames. Accordingly, for many years action recognition was the quintessential tas...
Deciding how to distribute work between humans and AI systems is a central challenge in organisational design. Most approaches treat this as a binary choice, ye...
Adapting large pretrained models to diverse tasks is now routine, yet the two dominant strategies of parameter-efficient fine-tuning (PEFT) and low-rank compres...
Probabilistic values, including Shapley values and semivalues, provide a model-agnostic framework to attribute the behavior of a black-box model to data points ...
Large language models excel at complex reasoning, yet evaluating their intermediate steps remains challenging. Although process reward models provide step-wise ...
Text-to-SQL over large analytical databases requires navigating complex schemas, resolving ambiguous queries, and grounding decisions in actual data. Most curre...
