Current electroencephalography (EEG)-based dream detection relies on power spectral density (PSD) and statistical moment features, achieving a state-of-the-art area under the receiver operating characteristic curve (A...

The rapid progress of large foundation models has been driven predominantly by pretraining on large-scale text corpora. However, many forms of knowledge are conveyed through visual representations, where figures, type...

Vision language models (VLMs) have made remarkable progress in visual reasoning during the last decade. Most evaluations have used simple scenes (MS-COCO) that do not showcase complex human interactions or behaviors,...

Internet of Things (IoT) systems are inherently vulnerable due to constrained hardware, outdated firmware, and insecure default configurations, creating a need for scalable and adaptive security testing approaches. Wh...

Concept-based explainable artificial intelligence (AI) can make model reasoning more human-understandable, but concept-level outputs are not automatically trustworthy. We introduce ConceptSMILE, a model-agnostic pertu...

Many real-world processes can be represented as compositions of functions along a directed acyclic graph (DAG). In causal modelling, these correspond to the underlying mechanisms; in engineering, to multiple fidelity...

Financial anomaly detection suffers from extreme class imbalance, causing traditional single-objective algorithms to exhibit ``fraud collapse'', defaulting to the majority class and failing to balance anomaly interdic...

Quantum information theory (QIT) characterizes the capabilities and fundamental limits of quantum information processing, underpinning quantum communication, computation, and error correction. Formalizing its coding t...

Reliable autonomous driving requires full-scene perception that couples foreground objects with dense semantic layout. Recently, 4D millimeter-wave radar has emerged as a robust and affordable sensor, yet its sparse r...

We present our submission to the QANTA 2026 shared challenge at the ICML 2026 Workshop on Efficient Multimodal Question Answering (EMM-QA). Quanta evaluates multimodal quizbowl systems that answer pyramid-style questi...

As chip complexity increases and time-to-market pressures grow, front-end design has become a critical bottleneck in chip development. Recently, Large Language Models (LLMs) have shown great potential in Electronic De...

Most sign language understanding systems operate at the level of isolated signs, limiting their usefulness in natural communication. We study sentence-level sign language translation (SLT) with the primary goal of rea...

Enhancing the reasoning capabilities of large language model (LLM) agents requires effective orchestration of diverse expert models and tools. However, existing frameworks typically call APIs based on coarse-grained m...

Lightweight speech recognition models are critical for edge deployment, yet highly optimized architectures like Moonshine often fail on morphologically rich, non-Latin languages such as Bengali. This study identifies...

Precision industrial contact manipulation requires reliable robot policies under pose perturbations and contact-force constraints. Vision-language-action models offer broad generalization but often introduce high infe...

The proliferation of agentic AI systems across enterprise and public-sector contexts has outpaced the capacity of general-purpose AI risk frameworks to classify and govern them. In this paper, we introduce the TrustX...

We present a physics-constrained machine learning framework for accelerating the direct numerical simulation (DNS) of turbulent reacting flows. The model replaces the direct evaluation of detailed chemical source term...

Pre-demolition assessment, the regulated audit process at the heart of urban mining, is an information process in which AI support must serve qualified auditors who remain accountable for the decisions taken. The rele...

We present an interpretable network-based framework for representing idiomatic and figurative meaning across eight typologically diverse languages, totaling 160 conventional expressions, the large majority of which ar...

Decision-making is posing an increasingly formidable challenge to investors because of the growing number of alternatives available in financial markets. A hot area of research over the past few decades has been portf...

Medical Vision-Language Models (VLMs) exhibit strong zero-shot performance, yet their effectiveness still declines on out-of-distribution (OOD) data due to domain shifts and class bias inherited from large-scale pretr...

Modern AI systems are increasingly being evaluated for their ability to reason, code, prove theorems, use tools, and long-horizon research tasks. These are powerful capabilities, but they share a structural limitation...

We address the low-rank matrix completion problem by incorporating graph regularization into the existing Riemannian Trust-Region Matrix Completion (RTRMC) framework. The latter uses the geometry of the low-rank const...

Despite strong performance on many multimodal tasks, vision-language models (VLMs) still struggle with basic object counting. We investigate whether this reflects missing internal knowledge or a gap between internal r...