Stay updated with the latest research and technology news
arXiv:2602.19610v1 Announce Type: new Abstract: We develop a Coordinate Ascent Variational Inference (CAVI) algorithm for Bayesian Mixed Data Sampling (MIDAS) regression with linear weight parameteri...
arXiv:2602.19611v1 Announce Type: new Abstract: Unsupervised Anomaly Detection (UAD) aims to identify abnormal regions by establishing correspondences between test images and normal templates. Existing methods...
arXiv:2602.19612v1 Announce Type: new Abstract: Machine Unlearning (MU) enables Large Language Models (LLMs) to remove unsafe or outdated information. However, existing work assumes that all...
arXiv:2602.19614v1 Announce Type: new Abstract: The adoption of large language models in safety-critical system engineering is constrained by trustworthiness, traceability, and alignment with established verification...
arXiv:2602.19615v1 Announce Type: new Abstract: Vision language models (VLMs) have achieved remarkable success in broad visual understanding, yet they remain challenged by object-centric reasoning on...
arXiv:2602.19616v1 Announce Type: new Abstract: Student engagement is a central construct in Learning Analytics, yet it is often operationalized through persistence indicators derived from logs,...
arXiv:2602.19619v1 Announce Type: new Abstract: Discrete diffusion language models (dLLMs) provide a fast and flexible alternative to autoregressive models (ARMs) via iterative denoising with parallel...
arXiv:2602.19620v1 Announce Type: new Abstract: Rules and Weights are popular XAI techniques for explaining AI decisions. Yet, it remains unclear how to choose between them,...
arXiv:2602.19622v1 Announce Type: new Abstract: Graph Transformer has demonstrated impressive capabilities in the field of graph representation learning. However, existing approaches face two critical challenges:...
arXiv:2602.19623v1 Announce Type: new Abstract: While advancements in Text-to-Video (T2V) generative AI offer a promising path toward democratizing content creation, current models are often optimized...
arXiv:2602.19624v1 Announce Type: new Abstract: We present SAM-H and WOFTSAM, novel planar trackers that combine robust long-term segmentation tracking provided by SAM 2 with 8...
arXiv:2602.19626v1 Announce Type: new Abstract: We present Nacrith, a lossless compression system that combines a 135M-parameter transformer language model (SmolLM2-135M) with an ensemble of lightweight...
arXiv:2602.19628v1 Announce Type: new Abstract: Watching training videos passively leads to superficial learning. Adding gamification can increase engagement. We study how software engineering students and...
arXiv:2602.19629v1 Announce Type: new Abstract: Generative artificial intelligence systems increasingly participate in research, law, education, media, and governance. Their fluent and adaptive outputs create an...
arXiv:2602.19631v1 Announce Type: new Abstract: Recent advances in text-to-image (T2I) diffusion models have seen rapid and widespread adoption. However, their powerful generative capabilities raise concerns...
arXiv:2602.19633v1 Announce Type: new Abstract: Language Model (LM) agents have demonstrated remarkable capabilities in solving tasks that require multiple interactions with the environment. However, they...
arXiv:2602.19634v1 Announce Type: new Abstract: The ability to plan with temporal abstractions is central to intelligent decision-making. Rather than reasoning over primitive actions, we study...
arXiv:2602.19639v1 Announce Type: new Abstract: Understanding evacuation decision-making behaviour is one of the key components for designing disaster mitigation policies. This study investigates how communications...
arXiv:2602.19641v1 Announce Type: new Abstract: With the growing importance of privacy regulations such as the General Data Protection Regulation, anonymizing visual data is becoming increasingly...
arXiv:2602.19643v1 Announce Type: new Abstract: Large Language Models (LLMs) possess a remarkable capacity to generate persuasive and intelligible language. However, coherence does not equate to...
arXiv:2602.19644v1 Announce Type: new Abstract: Quantum kernel methods are promising for near-term quantum ma- chine learning, yet their behavior under data corruption remains insuf- ficiently...
arXiv:2602.19649v1 Announce Type: new Abstract: We study the sensitivity of the Lempel-Ziv 77 compression algorithm to edits, showing how modifying a string $w$ can deteriorate...
arXiv:2602.19651v1 Announce Type: new Abstract: Learning-based methods commonly treat state estimation in robotics as a sequence modeling problem. While this paradigm can be effective at...
arXiv:2602.19653v1 Announce Type: new Abstract: Distributed Manipulator Systems, composed of arrays of robotic actuators necessitate dense actuator arrays to effectively manipulate small objects. This paper...