arXiv preprints from January 1, 2026 through September 10, 2026 — 09:01:47 EST
We propose Map2Thought, a framework that enables explicit and interpretable spatial reasoning for 3D VLMs. The framework is grounded in two key components: Metric Cognitive Map (Metric-CogMap) and Cognitive Chain-of-Thought (Cog-CoT). Metric-CogMap provides a unified spatial representation by integrating a discrete grid for relational...
The widespread availability of generative artificial intelligence (GenAI) has created a pressing challenge in computer science (CS) education: how to incorporate powerful AI tools into programming coursework without undermining student learning through cognitive offloading. This paper presents an assessment model that permits the use...
Large language models (LLMs) exhibit exceptional performance across various domains, yet they face critical safety concerns. Model editing has emerged as an effective approach to mitigate these issues. Existing model editing methods often focus on optimizing an information matrix that blends new and old knowledge. While effective,...
Urban wind flow reconstruction is essential for assessing air quality, heat dispersion, and pedestrian comfort, yet remains challenging when only sparse sensor data are available. We propose GenDA, a generative data assimilation framework that reconstructs high-resolution wind fields on unstructured meshes from limited observations....
The study of system complexity primarily has two objectives: to explore underlying patterns and to develop theoretical explanations. Pattern exploration seeks to clarify the mechanisms behind the emergence of system complexity, while theoretical explanations aim to identify the fundamental causes of this complexity. Laws are generally...
Deep Differentiable Logic Gate Networks (LGNs) and Lookup Table Networks (LUTNs) are demonstrated to be suitable for the automatic classification of electrocardiograms (ECGs) using the inter-patient paradigm. The methods are benchmarked using the MIT-BIH arrhythmia data set, achieving up to 94.28% accuracy and a $jκ$ index of 0.683 on...
Career decision-making is a socio-technical problem: individuals exercise bounded agency while navigating labor market institutions, organizational incentive structures, and information asymmetries that shape feasible trajectories. Existing frameworks optimize along single dimensions - financial returns, work-life balance, or mission...
We report on an astonishing ability of large language models (LLMs) to make sense of "Jabberwocky" language in which most or all content words have been randomly replaced by nonsense strings, e.g., translating "He dwushed a ghanc zawk" to "He dragged a spare chair". This result addresses ongoing controversies regarding how to best...
This white paper provides an overview of the topic of "technical debt" and presents an approach for managing technical debt in teams. The white paper is based on the results of my dissertation, which aimed to translate scientific findings into practical guidance. To this end, I collaborated with other researchers to support three...
Hallucination is a central failure mode of language models (LMs). We focus on hallucinations in response to questions like: "Which instrument did Glenn Gould play?", but we ask these questions for synthetic entities designed to be unknown to the model. We find that LMs like Gemma-7B-IT frequently hallucinate, i.e., they have...
Neural PDE solvers are increasingly used as learned surrogates for families of partial differential equations, where the key machine learning challenge is not only interpolation on a fixed benchmark distribution but generalization under structured shifts in coefficients, boundary conditions, discretization, and rollout horizon. Yet...
This paper presents a semantic course recommendation system for students using a self-supervised contrastive learning approach built upon BERT (Bidirectional Encoder Representations from Transformers). Traditional BERT embeddings suffer from anisotropic representation spaces, where course descriptions exhibit high cosine similarities...
PubMed-OCR is an OCR-centric corpus of scientific articles derived from PubMed Central Open Access PDFs. Each page image is annotated with Google Cloud Vision and released in a compact JSON schema with word-, line-, and paragraph-level bounding boxes. The corpus spans 209.5K articles (1.5M pages; ~1.3B words) and supports layout-aware...
Recently, with the rapid development of robot learning and imitation learning, numerous datasets and methods have emerged. However, these datasets and their task designs often lack systematic consideration and principles. This raises important questions: Do the current datasets and task designs truly advance the capabilities of...
We initiate the polyhedral study of the Virtual Network Embedding (VNE) problem, which arises in modern telecommunication networks. We propose new valid inequalities for the so-called flow formulation. We then prove, through a dedicated flow decomposition algorithm, that these inequalities characterize the VNE polytope in the case of...
Personalized education systems increasingly rely on structured knowledge representations to support adaptive learning and question generation. However, existing approaches face two fundamental limitations. First, constructing and maintaining knowledge graphs for educational content largely depends on manual curation, resulting in high...
Sociotechnical challenges of machine learning in healthcare and social welfare are mismatches between how a machine learning tool functions and the structure of care practices. While prior research has documented many such issues, existing accounts often attribute them either to designers' limited social understanding or to inherent...
Adaptive Large Neighborhood Search (ALNS) is a widely used heuristic method for solving combinatorial optimization problems. ALNS explores the solution space by iteratively using destroy and repair operators with probabilities, which are adjusted by an adaptive mechanism to find optimal solutions. However, the classic ALNS adaptive...
Assessing the validity of user simulators when used for the evaluation of information retrieval systems remains an open question, constraining their effective use and the reliability of simulation-based results. To address this issue, we conduct a comprehensive literature review with a particular focus on methods for the validation of...
Oculomics - the concept of predicting systemic diseases, such as cardiovascular disease and dementia, through retinal imaging - has advanced rapidly due to the data efficiency of transformer-based foundation models like RETFound. Image-level mixed sample data augmentations, such as CutMix and MixUp, are frequently used for training...
Existing research highlights the crucial role of topological priors in image segmentation, particularly in preserving essential structures such as connectivity and genus. Accurately capturing these topological features often requires incorporating width-related information, including the thickness and length inherent to the image...
Context: Technical lag accumulates when software systems fail to keep pace with technological advancements, leading to a deterioration in software quality. Objective: This paper aims to consolidate existing research on technical lag, clarify definitions, explore its detection and quantification methods, examine underlying causes and...
In the past decades, static analysis has thrived in software, facilitating applications in bug detection, security, and program understanding. These advanced analyses are largely underpinned by general-purpose static analysis frameworks, which offer essential infrastructure to streamline their development. Conversely, hardware lacks...
This paper investigates how end-to-end (E2E) channel autoencoders (AEs) can achieve energy-efficient wideband communications by leveraging Walsh-Hadamard (WH) interleaved converters. WH interleaving enables high sampling rate analog-digital conversion with reduced power consumption using an analog WH transformation. We demonstrate...
Vision-Language-Action models have emerged as essential generalist robot policies for diverse manipulation tasks, conventionally relying on directly translating multimodal inputs into actions via Vision-Language Model embeddings. Recent advancements have introduced explicit intermediary reasoning-such as sub-task prediction (language)...