arXiv preprints from January 1, 2026 through July 21, 2026 — 15:39:21 EST
Diffusion Large Language Models (dLLMs) break the rigid left-to-right constraint of traditional LLMs, enabling token generation in arbitrary orders. Intuitively, this flexibility implies a solution space that strictly supersets the fixed autoregressive trajectory, theoretically unlocking superior reasoning potential. However, in this...
Learning long-horizon embodied behaviors from synthetic data remains challenging because generated scenes are often physically implausible, language-driven programs frequently "succeed" without satisfying task semantics, and high-level instructions require grounding into executable action sequences. To address these limitations, we...
Governments are the primary providers of essential public services and are responsible for delivering them effectively. In high-stakes decision-making domains such as child welfare (CW), agencies must protect children without unnecessarily prolonging a family's engagement with the system. With growing optimism around AI, governments...
Large Language Models (LLMs) are increasingly used for clinical decision support, where hallucinations and unsafe suggestions may pose direct risks to patient safety. These risks are hard to assess: subtle clinical errors are often missed by generic metrics and LLM judges using general criteria, while expert-authored fine-grained...
Large language models have achieved near-expert performance in structured reasoning domains like mathematics and programming, yet their ability to perform compositional multi-hop reasoning in specialized scientific fields remains limited. We propose a bottom-up learning paradigm in which models are grounded in axiomatic domain facts...
Transformers trained via Reinforcement Learning (RL) with outcome-based supervision can spontaneously develop the ability to generate intermediate reasoning steps (Chain-of-Thought). Yet the mechanism by which sparse rewards drive policy gradient to discover such systematic reasoning remains poorly understood. We address this by...
Culverts and sewer pipes are critical components of drainage systems, and their failure can lead to serious risks to public safety and the environment. In this thesis, we explore methods to improve automated defect segmentation in culverts and sewer pipes. Collecting and annotating data in this field is cumbersome and requires domain...
We show how conformance arguments can be used by organisations to substantiate claims of conformance to data protection principles. Use of conformance arguments can improve the rigour and consistency with which these organisations, supervisory authorities, certification bodies and data subjects can assess the truth of these claims.
Python is one of the most popular programming languages; as such, projects written in Python involve an increasing number of diverse security vulnerabilities. However, existing state-of-the-art analysis tools for Python only support a few vulnerability types. Hence, there is a need to detect a large variety of vulnerabilities in...
Critical domain knowledge typically resides with few experts, creating organizational bottlenecks in scalability and decision-making. Non-experts struggle to create effective visualizations, leading to suboptimal insights and diverting expert time. This paper investigates how to capture and embed human domain knowledge into AI agent...
In a context of ever-growing worldwide communication traffic, cloud service providers aim at deploying scalable infrastructures to address heterogeneous needs. Part of the network infrastructure, FPGAs are tailored to guarantee low-latency and high-throughput packet processing. However, slowness of the hardware design process impairs...
We consider a game-theoretic variant of an interval scheduling problem. Every job is associated with a length, a weight, and a color. Each player controls all the jobs of a specific color, and needs to decide on a processing interval for each of its jobs. Jobs of the same color can be processed simultaneously by the machine. A job is...
Gaze-based interaction enables intuitive, hands-free control in immersive environments, but remains susceptible to unintended inputs. We present a real-time error prevention system (EPS) that uses a temporal convolutional network autoencoder (TCNAE) to detect anomalies in gaze dynamics during selection tasks. In a visual search task...
Agentic Reinforcement Learning (RL) has empowered Large Language Models (LLMs) to utilize tools like Python interpreters for complex problem-solving. However, for parameter-constrained models (e.g., 4B--7B), the exploration phase is often plagued by frequent execution failures, creating noisy trajectories that hinder policy...
Background: Open source software (OSS) libraries are critical components of modern software systems, yet their metadata-particularly links to source code repositories and donation platforms-is often incomplete, outdated, or inconsistent. Such deficiencies hinder dependency monitoring, security assessment, and the sustainability of OSS...
The integration of Conversational Agents (CAs) into daily life offers opportunities to tackle global challenges, leading to the emergence of Conversational AI for Social Good (CAI4SG). This paper examines the advancements of CAI4SG using a role-based framework that categorizes systems according to their AI autonomy and emotional...
Recent years have seen substantial progress in neural generation of text, images, and audio, supported by mature training pipelines and large-scale optimization. For graphs, however, comparable progress has been more limited. We attribute this gap to graph-specific optimization and representation challenges that undermine the...
In this paper, we study the vehicle routing problem with a finite time horizon. In this routing problem, the objective is to maximize the number of customer requests served within a finite time horizon. We present a novel routing network embedding module which creates local node embedding vectors and a context-aware global graph...
The ubiquity of Large Language Models (LLMs) is driving a paradigm shift where user convenience supersedes computational efficiency. This article defines the "Plausibility Trap": a phenomenon where individuals with access to Artificial Intelligence (AI) models deploy expensive probabilistic engines for simple deterministic tasks-such...
Multimodal large language models have demonstrated comparable performance to that of radiology trainees on multiple-choice board-style exams. However, to develop clinically useful multimodal LLM tools, high-quality benchmarks curated by domain experts are essential. To curate released and holdout datasets of 100 chest radiographic...
Deploying federated learning across heterogeneous IoT device fleets requires tailored neural network architectures for each device class, yet existing Federated Neural Architecture Search (FedNAS) methods suffer from unguided supernet training and prohibitively costly post-training search pipelines that demand over 20 GPU-hours per...
Graph Foundation Models (GFMs) have emerged as a frontier in graph learning, which are expected to deliver transferable representations across diverse tasks. However, GFMs remain constrained by in-memory bottlenecks: they attempt to encode knowledge into model parameters, which limits semantic capacity, introduces heavy lossy...
Promptable segmentation models such as SAM have established a powerful paradigm, enabling strong generalization to unseen objects and domains with minimal user input, including points, bounding boxes, and text prompts. Among these, bounding boxes stand out as particularly effective, often outperforming points while significantly...
Popularity bias is a pervasive challenge in recommender systems, where a few popular items dominate attention while the majority of less popular items remain underexposed. This imbalance can reduce recommendation quality and lead to unfair item exposure. Although existing mitigation methods address this issue to some extent, they...
LLMs have advanced tool-using agents for real-world applications, yet they often lead to unexpected behaviors or results. Beyond obvious failures, the subtle issue of "intent deviation" severely hinders reliable evaluation and performance improvement. Existing post-training methods generally leverage either real system samples or...