arXiv preprints from January 1, 2026 through July 20, 2026 — 07:02:00 EST
Large language models and agents have achieved remarkable progress in code generation. However, existing benchmarks focus on isolated function/class-level generation (e.g., ClassEval) or modifications to existing codebases (e.g., SWE-Bench), neglecting complete microservice repository generation that reflects real-world 0-to-1...
Large Multimodal Models (LMMs) have achieved remarkable success in visual understanding, yet they struggle with knowledge-intensive queries involving long-tail entities or evolving information due to static parametric knowledge. Recent search-augmented approaches attempt to address this limitation, but existing methods rely on...
Standard protocols such as the Model Context Protocol (MCP) that allow LLMs to connect to tools have recently boosted "agentic" AI applications, which, powered by LLMs' planning capabilities, promise to solve complex tasks with the access of external tools and data sources. In this context, publicly available SPARQL endpoints offer a...
As Generative Engines revolutionize information retrieval by synthesizing direct answers from retrieved sources, ensuring source visibility becomes a significant challenge. Improving it through targeted content revisions is a practical strategy termed Generative Engine Optimization (GEO). However, optimizing a document for diverse...
The overall rapid increase of artificial intelligence (AI) use is linked to various initiatives that propose AI 'for good'. However, there is a lack of transparency in the goals of such projects, as well as a missing evaluation of their actual impacts on society and the planet. We close this gap by proposing public interest and...
White Matter Tract Segmentation is imperative for studying brain structural connectivity, neurological disorders and neurosurgery. This task remains complex, as tracts differ among themselves, across subjects and conditions, yet have similar 3D structure across hemispheres and subjects. To address these challenges, we propose...
As software systems grow in complexity, security vulnerabilities have become increasingly prevalent, posing serious risks and economic costs. Although automated detection tools such as fuzzers have advanced considerably, effective resolution still often depends on human expertise. Existing automated vulnerability repair (AVR) methods...
Joint audio-text models are widely used for music retrieval, yet they struggle with semantic phenomena such as negation. Negation is fundamental for distinguishing the absence (or presence) of musical elements (e.g., "with vocals" vs. "without vocals"), but current systems fail to represent this reliably. In this work, we investigate...
Coded caching and device-to-device (D2D) communication are two effective techniques for alleviating network traffic. Secure transmission and file privacy have also become critical concerns in these domains. However, prevailing coded caching schemes typically assume that a user's cached content is inaccessible to others, overlooking...
Although artificial intelligence (AI) shows growing promise for mental health care, current approaches to evaluating AI tools in this domain remain fragmented and poorly aligned with clinical practice, social context, and first-hand user experience. This paper argues for a rethinking of responsible evaluation -- what is measured, by...
Feature extraction from unstructured text is a critical step in many downstream classification pipelines, yet current approaches largely rely on hand-crafted prompts or fixed feature schemas. We formulate feature discovery as a dataset-level prompt optimization problem: given a labelled text corpus, the goal is to induce a global set...
We formulate the training of generative adversarial networks (GANs) as a Nash equilibrium seeking problem. To stabilize the training process and find a Nash equilibrium, we propose an asymmetric regularization mechanism based on the classic Tikhonov step and on a novel zero-centered gradient penalty. Under smoothness and a local...
Automated clinical diagnosis remains a core challenge in medical AI, which usually requires models to integrate multi-modal data and reason across complex, case-specific contexts. Although recent methods have advanced medical report generation (MRG) and visual question answering (VQA) with medical vision-language models (VLMs), these...
Large Language Models have demonstrated profound utility in the medical domain. However, their application to autonomous Electronic Health Records~(EHRs) navigation remains constrained by a reliance on curated inputs and simplified retrieval tasks. To bridge the gap between idealized experimental settings and realistic clinical...
Estimating 3D from 2D is one of the central tasks in computer vision. In this work, we consider the monocular setting, i.e. single-view input, for 3D human pose estimation (HPE), where the goal is to predict a 3D point set of human skeletal joints from a single 2D image, typically via 2D keypoint detection followed by 2D-to-3D...
Traditional paper-based document management has long posed challenges related to security, authenticity, and efficiency. Despite advances in digitalization, official documents remain vulnerable to forgery, loss, and unauthorized access. This thesis proposes a decentralized infrastructure for digital notarization, signing, and sharing...
Graph Neural Networks (GNNs) are sensitive to structural noise from adversarial attacks or imperfections. Existing graph contrastive learning (GCL) methods typically rely on either random perturbations (e.g., edge dropping) for diversity or spectral augmentations (e.g., SVD) to preserve structural priors. However, random perturbations...
As deep learning models are widely used in software systems, test generation plays a crucial role in assessing the quality of such models before deployment. To date, the most advanced test generators rely on generative AI to synthesize inputs; however, these approaches remain limited in providing semantic insight into the causes of...
Inverse rendering is an ill-posed problem, but priors such as illumination priors can help simplify it. Existing work either disregards the spherical and rotation-equivariant nature of illumination environments or does not provide a well-behaved latent space. We propose a rotation-equivariant variational autoencoder that models...
We revisit constructions for distribution and synthesis of Zielonka's asynchronous automata in restricted settings. We show first a simple, quadratic, distribution construction for asynchronous automata, where the process architecture is tree-like. An architecture is tree-like if there is an underlying spanning tree of the...
Query-based sampling has become an increasingly popular technique for monitoring Markov sources in pull-based update systems. However, most of the contemporary literature on this assumes an exponential distribution for query delay and often relies on the assumption that the feedback or replies to the queries are instantaneous. In this...
Unsupervised video class incremental learning (uVCIL) represents an important learning paradigm for learning video information without forgetting, and without considering any data labels. Prior approaches have focused on supervised class-incremental learning, relying on using the knowledge of labels and task boundaries, which is...
Infinite-state games provide a framework for the synthesis of reactive systems with unbounded data domains. Solving such games typically relies on computing symbolic fixpoints, particularly symbolic attractors. However, these computations may not terminate, and while recent acceleration techniques have been proposed to address this...
The human spine commonly consists of seven cervical, twelve thoracic, and five lumbar vertebrae. However, enumeration anomalies may result in individuals having eleven or thirteen thoracic vertebrae and four or six lumbar vertebrae. Although the identification of enumeration anomalies has potential clinical implications for chronic...
Cross-cultural competence in large language models (LLMs) requires understanding and adapting Culture-Specific Items (CSIs) across varying cultural contexts. However, progress in evaluating this capability remains limited by the lack of high-quality CSI-annotated corpora with parallel cross-cultural sentence pairs. We introduce...