Open Access. Powered by Scholars. Published by Universities.®

Digital Commons Network™

Open Access. Powered by Scholars. Published by Universities.®

Discipline
Institution
Keyword
Publication Year
Publication
Publication Type
File Type

Articles 43531 - 43560 of 1114180

Full-Text Articles in Entire DC Network

Low-Level Memory Attacks On Edge Assisted Robotic Applications, William Arnold Aug 2025

Low-Level Memory Attacks On Edge Assisted Robotic Applications, William Arnold

Master of Engineering Theses

This thesis investigates how low-level memory faults can undermine edge-assisted robotic systems that rely on memory optimization. As robots are utilized in real world applications, the ability to operate safely and successfully in mission critical deployment becomes important. To help achieve these goals, developers are increasingly starting to place computation nodes at network edges to meet latency and reliability requirements. Edge nodes, however, are resource-constrained and resources conservation techniques such as Kernel Same-page Merging (KSM) are enabled to deduplicate identical pages across processes or virtual machines. This thesis shows that this optimization technique quietly widens the attack surface and can …

Go to article

Ai In The Judiciary: The Singapore Case, Nydia Remolina Leon Aug 2025

Ai In The Judiciary: The Singapore Case, Nydia Remolina Leon

Research Collection Yong Pung How School Of Law

This paper examines the integration of Artificial Intelligence (AI) within the judicial system of Singapore. Singapore's judiciary has embraced AI not as a tool for adjudication, but as an augmentative instrument for legal research, procedural efficiency, and access to justice. It provides a detailed account of AI use cases in the courts, including case summarization, evidence review, assistance for selfrepresented litigants, and tools like the Divorce Assets Informative Division Estimator. The discussion then turns to the legal profession, exploring how law firms in Singapore are adopting AI technologies. The paper also addresses how AI implementation in the judicial system is …

Go to article

Revealing Building Operating Carbon Dynamics For Multiple Cities, Winston Yap, Abraham Noah Wu, Clayton Miller, Filip Biljecki Aug 2025

Revealing Building Operating Carbon Dynamics For Multiple Cities, Winston Yap, Abraham Noah Wu, Clayton Miller, Filip Biljecki

Research Collection College of Integrative Studies

Achieving carbon neutrality is a critical yet elusive goal for many cities, hindered by limited understanding of the relationship between building emissions and their surroundings. To address this challenge, we present a generalizable open science framework that integrates building energy-consumption data, multi-modal geospatial inputs and graph deep learning to quantify building operating emissions and their links to urban form and socio-economic factors. Applying this approach to five cities with diverse climates and planning contexts—Melbourne, New York City (Manhattan), Seattle, Singapore and Washington DC—we demonstrate that our models explain 78.4% of the variation in building operating carbon emissions across cities, achieving …

Go to article

International Comparison Of Weather And Emission Predictive Building Control, Christian Hepf, Ben Gottkehaskamp, Clayton Miller, Thomas Auer Aug 2025

International Comparison Of Weather And Emission Predictive Building Control, Christian Hepf, Ben Gottkehaskamp, Clayton Miller, Thomas Auer

Research Collection College of Integrative Studies

Building operational energy alone accounts for 28% of global carbon emissions. A sustainable building operation promises enormous savings, especially under the increasing concern of climate change and the rising trends of the digitalization and electrification of buildings. Intelligent control strategies play a crucial role in building systems and electrical energy grids to reach the EU goal of carbon neutrality in 2050 and to manage the rising availability of regenerative energy. This study aims to prove that one can create energy and emission savings with simple weather and emission predictive control (WEPC). Furthermore, this should prove that the simplicity of this …

Go to article

Health And Weather In Unfavourable Environments: Exploring The Historical Dynamics Of Colonial Medical Meteorology In Nineteenth-Century Tropical Asia, Fiona Williamson Aug 2025

Health And Weather In Unfavourable Environments: Exploring The Historical Dynamics Of Colonial Medical Meteorology In Nineteenth-Century Tropical Asia, Fiona Williamson

Research Collection College of Integrative Studies

Medical meteorology had a long precedent in medical thought across Eastern and Western traditions. This article considers the tradition of medical meteorology that was favoured by Western doctors in the nineteenth century, which was often applied within colonial contexts to the understanding of new climates and how they might impact on human health. Looking at British-held tropical and sub-tropical colonies of the Straits Settlements and Hong Kong respectively, medical meteorology was stimulated by the new pathological and atmospheric conditions that European explorers and settlers now inhabited in the name of the British Empire. They brought with them concepts of disease …

Go to article

Bibliography For "Ai 2.0: Is Ai A Tool, A Threat, Or A Teammate?", Annikah Carpio, Sally Park, Melody Madrigal Aug 2025

Bibliography For "Ai 2.0: Is Ai A Tool, A Threat, Or A Teammate?", Annikah Carpio, Sally Park, Melody Madrigal

Library Displays and Bibliographies

A bibliography created to support a display about AI 2.0 in August 2025 at the Leatherby Libraries at Chapman University.

Go to article

Shape Memory Behavior In Medium To High Entropy Shape Memory Alloys: Design, Prediction, And Experimental Analysis, Hatim Raji Aug 2025

Shape Memory Behavior In Medium To High Entropy Shape Memory Alloys: Design, Prediction, And Experimental Analysis, Hatim Raji

Theses and Dissertations

This dissertation provides a data-driven system integrating synthetic data generation and machine learning (ML) techniques to create multicomponent SMA compositions with specific transformation temperatures (TTs). Models were trained to represent the nonlinear dependencies influencing martensitic transformation behavior by using elemental, thermodynamic, and process-related aspects. The capacity of the ML models on medium entropy NiTiHfPd and high entropy NiTiHfZrCu systems accuracy was confirmed by experimental validation showing TTs closely matched with model outputs.

Go to article

Greening The Virtual: An Interdisciplinary Narrative Review On The Environmental Sustainability Of The Metaverse, Mousa Al-Kfairy Aug 2025

Greening The Virtual: An Interdisciplinary Narrative Review On The Environmental Sustainability Of The Metaverse, Mousa Al-Kfairy

All Works

As the Metaverse continues to evolve as a transformative digital ecosystem, its environmental implications remain insufficiently examined within academic discourse. Despite growing interest in its technological and societal impacts, there is a lack of comprehensive evaluations that synthesize existing knowledge on its sustainability potential. This interdisciplinary narrative review addresses this gap by critically exploring how Metaverse technologies intersect with environmental sustainability across key sectors, including education, healthcare, tourism, e-commerce, manufacturing, and urban development. Employing a narrative review methodology informed by a systematic selection of scholarly and industry sources, the study consolidates current practices, emerging opportunities, and notable trade-offs. While the …

Go to article

Properties Of A Class Of Analytic Functions Associated With Exponentially Convex Functions, K. R. Karthikeyan, Elangho Umadevi, G. Thirupathi, Dharmaraj Mohankumar Aug 2025

Properties Of A Class Of Analytic Functions Associated With Exponentially Convex Functions, K. R. Karthikeyan, Elangho Umadevi, G. Thirupathi, Dharmaraj Mohankumar

All Works

Studies in univalent function theory comprising the exponential of differential characterizations are rarely considered. The prominent study in this direction is the study of so-called α-exponentially convex functions. Here we study a class of analytic functions which satisfy an analytic characterization influenced by the definition of the multiplicative derivative and α-exponentially convex functions. Integral representation and coefficient inequalities of the defined function class are the main results of the paper.

Go to article

Regulation Of Icer Degradation And Its Role In Melanoma, Justin Wheelan Aug 2025

Regulation Of Icer Degradation And Its Role In Melanoma, Justin Wheelan

Theses, Dissertations and Culminating Projects

Melanoma is the deadliest form of skin cancer, with 100,640 new cases and 8,290 deaths estimated in the United States in 2024. While targeted therapies and immunotherapy have improved patient outcomes, resistance remains a major challenge, necessitating new therapeutic approaches. Approximately 50% of melanomas harbor BRAFⱽ⁶⁰⁰ᴱ mutations, leading to constitutive MAPK pathway activation. Targeted small molecule therapies such as BRAF and MEK inhibitors are available and initially reduce tumor burden, however resistance frequently occurs, likely through many pathways including compensatory activation of cAMP signaling. ICER (Inducible cAMP Early Repressor), a transcriptional repressor of CREB-mediated gene expression, is absent in melanoma …

Go to article

Improved Autofluorescence Lifetime Decay Analysis For Identification Of Cellular Autofluorescence Biomarkers For Label-Free, Single-Cell Assessment Of Mitochondrial Membrane Potential, Olivia Isabel Kolenc Aug 2025

Improved Autofluorescence Lifetime Decay Analysis For Identification Of Cellular Autofluorescence Biomarkers For Label-Free, Single-Cell Assessment Of Mitochondrial Membrane Potential, Olivia Isabel Kolenc

Graduate Theses and Dissertations

Optical imaging of metabolism using the autofluorescence of the metabolic cofactors NADH, NADPH, and FAD has a wide range of sensitivities and the capability to collect a great deal of metabolic information. Multiphoton microscopy (MPM) is a non-invasive, label-free optical imaging technique capable of performing fluorescence lifetime imaging (FLIM) using time correlated single photon counting (TCSPC). However, autofluorescence FLIM presents a challenge in collecting sufficient photons to provide adequate signal to noise ratios (SNR) for analysis. Additionally, the specificity of autofluorescence biomarkers of metabolism has not been well-defined. Contextualizing these autofluorescence measures using established functional biomarkers can improve interpretability of …

Go to article

Growth And Characterization Of Thin Film Gase On Si(111) And Sio2/Si(001) Substrates By Molecular Beam Epitaxy, Christopher John Hocevar Aug 2025

Growth And Characterization Of Thin Film Gase On Si(111) And Sio2/Si(001) Substrates By Molecular Beam Epitaxy, Christopher John Hocevar

Graduate Theses and Dissertations

Gallium selenide (GaSe) is a thin-film semiconducting material with promising optoelectronic properties, including a tunable bandgap, high photosensitivity, and atomic-layer scalability. These characteristics make it suitable for devices such as photodiodes, FETs, MOSFETs, Hall effect sensors, and p–n diodes. In this study, GaSe thin films were grown on SiO2 and Si(111)-7×7 substrates using molecular beam epitaxy (MBE) to compare growth behavior across different substrates. The films were characterized using Raman spectroscopy, X-ray diffraction (XRD), atomic force microscopy (AFM), photoluminescence (PL) spectroscopy, and reflection high-energy electron diffraction (RHEED). RHEED confirmed the 7×7 reconstruction of the Si(111) surface and the amorphous nature …

Go to article

Synthesis, Structural Characterization And Optical Studies Of Silver-Indium-(Zinc)-Chalcogenide Fluorescent Quantum Dots, Sujal Acharya Aug 2025

Synthesis, Structural Characterization And Optical Studies Of Silver-Indium-(Zinc)-Chalcogenide Fluorescent Quantum Dots, Sujal Acharya

Graduate Theses and Dissertations

Developing a non-toxic, high-performance fluorescent nanomaterial is crucial for overcoming the environmental and health restrictions of current cadmium, and lead based quantum dots (QDs), which limit the application of quantum dots in optoelectronics and bioimaging. In this thesis, we synthesized environmentally friendly AgInS2 QDs by a colloidal method, systematically altering the In/Ag precursor ratio from 2 to 6 to study the impact on their optical and photophysical properties. Our goals were to find the optimal stoichiometry for maximum quantum efficiency and stability. We also investigated further improving optical and photophysical properties through shelling with ZnS. The emission spectra appeared broad, …

Go to article

Structure, Thermodynamics, And Dynamics Of Acetonitrile In Titan-Like Conditions, Sagar Chandra Roy Aug 2025

Structure, Thermodynamics, And Dynamics Of Acetonitrile In Titan-Like Conditions, Sagar Chandra Roy

Graduate Theses and Dissertations

Titan is one of the most interesting satellites in the solar system. It is the only other place in the solar system containing stable deposits of liquid and a hydrological cycle other than earth. The abundant existence of N2 and CH4 in Titan’s atmosphere makes nitrile formation highly likely both in the atmosphere and surface. Infrared spectrometer data from Voyager 1 expedition revealed the presence of acetonitrile (CH3CN) in the atmosphere along with several other nitriles such as hydrogen cyanide (HCN) and cyanoacetylene (HC3N). According to theoretical models nitrile formation is caused by photodisscociation of nitrogen in the tholin haze …

Go to article

Polymer-Enhanced Nanopore Sensing, Eugene Gyasi Agyemang Aug 2025

Polymer-Enhanced Nanopore Sensing, Eugene Gyasi Agyemang

Graduate Theses and Dissertations

The resistive pulse technique characterizes single analytes by detecting fluctuations in the ion current as they pass through a narrow orifice connecting two electrolyte-filled chambers, each containing a single electrode. The amplitude, shape, frequency, and duration of these fluctuations primarily provide information about the analyte’s size, shape, concentration, and net surface charge, respectively. One configuration for resistive pulse measurements is of an electrolyte-filled nanopipette immersed in a bath, where the nanopipette tip acts as the nanoscale orifice. It was previously shown that incorporating the large quantities polymer polyethylene glycol (PEG 8K, 50% w/v) into the external electrolyte bath dramatically enhanced …

Go to article

Contrastive Loss In Recommendation Systems, Maryam Aghamohammadghasem Aug 2025

Contrastive Loss In Recommendation Systems, Maryam Aghamohammadghasem

Graduate Theses and Dissertations

A recommendation system is a bridge between users and products, which is widely used in e-commerce such as Amazon and Netflix. This study investigates the use of Graph Neural Networks (GNNs), Light Graph Convolution Network(LightGCN) and Graph Sample and Aggregate (GraphSAGE), in the recommendation system on two categories of Amazon review datasets ( "All Beauty" and "Tools and Home Improvement"). The novelty of this work includes combining supervised and self-supervised learning through Weighted Approximate Rank Pairwise (WARP) and Information Noise-Contrastive Estimation (InfoNCE) losses, to optimize the embeddings of users and recommended items in the shape of a ranking list. The …

Go to article

From Stem Cells To Smooth Muscle Cells: Characterizing Secretome Profiles And Evaluating Regenerative Potentials, Christofer Baldwin Aug 2025

From Stem Cells To Smooth Muscle Cells: Characterizing Secretome Profiles And Evaluating Regenerative Potentials, Christofer Baldwin

Graduate Theses and Dissertations

This dissertation examines the role of vascular smooth muscle cells (VSMCs) in vascular disease and the potential of stem cell-derived VSMCs (SC-SMCs) for regenerative medicine. VSMCs are crucial for maintaining function; however, their dysregulation contributes to the progression of diseases like atherosclerosis, vascular calcification, and aneurysms. Disease progression is influenced by various environmental factors, prompting VSMCs to switch phenotypes, leading to adverse vascular remodeling. This research focuses on adult bone marrow mesenchymal stem cells (BM-MSCs) and adipose-derived stem cells (ADSCs) as sources for generating reparative VSMCs. Through comparative analysis, it investigates the effects of SC-SMCs on VSMC biomarker expression and …

Go to article

Classifying Advanced Persistent Threat Stages And Techniques Via Graph-Enhanced Network Flow Representations, Md Taef Uddin Nadim Aug 2025

Classifying Advanced Persistent Threat Stages And Techniques Via Graph-Enhanced Network Flow Representations, Md Taef Uddin Nadim

Graduate Theses and Dissertations

Advanced Persistent Threats (APTs) are complex, stealthy attacks that involve multiple stages and many attack techniques used in each stage, making them difficult to defend against. Although many solutions can detect APTs, most of them only detect the existence of attack, but cannot produce fine-grained classification over the stage of the APT and the specific attack technique used. Some existing solutions can classify the stages of APT, but few of them provide attack technique classification, and existing work do not provide interpretability for the classification or countermeasures for the attack. In this thesis work, we propose a solution named CAPTure, …

Go to article

Small Angle X-Ray Scattering Studies Of Collagenase H Mutant, Colh-E416q, Madelyn Millsap Aug 2025

Small Angle X-Ray Scattering Studies Of Collagenase H Mutant, Colh-E416q, Madelyn Millsap

Graduate Theses and Dissertations

Collagenase H (ColH) from Hathewaya histolytica plays a central role in collagen degradation through endopeptidase and carboxytripeptidase reactions. To better understand how its domain architecture supports these functions, we examined the solution structure of a catalytically inactive mutant, ColH-E416Q, using small-angle X-ray scattering (SAXS). The E416Q mutant is catalytically inactive because the glutamate residue at position 416, which normally functions as a general acid/base during catalysis, is replaced by glutamine—an amide that cannot donate or accept protons effectively, thus disabling the proton transfer steps essential for peptide bond hydrolysis. SAXS results indicate that the E416Q substitution leaves overall domain architecture …

Go to article

Advancing Point-Of-Care Diagnosis Of Joint Infection Using A Diffuse Reflectance Spectroscopy (Drs) System, Erin Elizabeth Drewke Aug 2025

Advancing Point-Of-Care Diagnosis Of Joint Infection Using A Diffuse Reflectance Spectroscopy (Drs) System, Erin Elizabeth Drewke

Graduate Theses and Dissertations

Septic arthritis is a severe joint infection that can rapidly destroy cartilage and cause lifelong disability if not diagnosed and treated promptly. Faster, bedside diagnostic tools are needed to reduce delays and support timely treatment decisions while preserving standard laboratory workflows. A syringe-mounted diffuse reflectance spectroscopy (DRS) system was developed for rapid, sterile, point-of-care measurement of synovial fluid optical properties. Broadband light (400–650 nm) was delivered and collected through the syringe barrel without contaminating the sample. An empirical lookup table (LUT) and a boundary-aware Monte Carlo (MC) model were implemented to extract absorption (μₐ) and reduced scattering (μs′) coefficients from …

Go to article

Effect Of Dietary Tryptophan Supplementation And Heat Stress On Pasture Broiler Welfare And Performance, Jaelen Matthew Cherry Aug 2025

Effect Of Dietary Tryptophan Supplementation And Heat Stress On Pasture Broiler Welfare And Performance, Jaelen Matthew Cherry

Graduate Theses and Dissertations

Pasture-raised broiler chickens face temperature extremes that can threaten welfare. In the study, we evaluated whether a 0.26 % tryptophan-supplemented diet (T) improved heat stress (HS) resilience in Ross-708 broilers raised on pasture. At D14, birds began the T or remained on the control diet (C) and were moved outdoors. On D20 and 41, half of each group underwent six-hour HS; the remainder stayed under thermoneutral (TN) conditions. Weekly body weight, feed intake on D20 and D41 were recorded, and fear was measured using the Tonic Immobility (TI) test. Neither diet nor HS affected body weight. However, tryptophan supplementation resulted …

Go to article

Multivariate Optical Imaging Of The Oxygen-Metabolism Axis, Jesse D. Ivers Aug 2025

Multivariate Optical Imaging Of The Oxygen-Metabolism Axis, Jesse D. Ivers

Graduate Theses and Dissertations

Metabolic reprogramming is a characteristic hallmark of multiple pathologies and promotes disease progression, survival, and severity. Current methods to investigate metabolic reprogramming, however, require reductions of dimensionality both because of instrumentation limitations and analysis tools. This work aims to define a blueprint for high dimensional study of the oxygen metabolism axis to enable more sensitive study metabolic reprogramming. We hypothesized (1) multivariate imaging of metabolic and oxygenation metrics in ex vivo tissue sections would elucidate differences in resistant and sensitive head and neck squamous cell carcinoma (HNSCC) xenografts that traditional uni-variate methods miss and (2) an engineered hyperspectral darkfield microscopy …

Go to article

Strain Induced Quantum Emitters In Monolayer Wse₂: Fabrication And Characterization Of Dimple Dot Devices, Garrett Maxwell Kitterman Aug 2025

Strain Induced Quantum Emitters In Monolayer Wse₂: Fabrication And Characterization Of Dimple Dot Devices, Garrett Maxwell Kitterman

Graduate Theses and Dissertations

Strain induced defects in monolayer tungsten diselenide (WSe₂) give rise to localized exciton funnels, offering a promising approach for the development of tunable quantum emitters. The quantum devices fabricated for this thesis used a modified dimple dot geometry, in which nano indentation creates a strain profile on the monolayer WSe₂. This allows for the funneling of excitons to a confined region. These strain induced funnels enable localized emission from single excitons in WSe₂. Device fabrication was carried out through mechanical exfoliation, dry transfer, and electron beam lithography of Cr/Au gates on a SiO₂ substrate. These devices were then characterized using …

Go to article

Kinematic Representations Of Viscoelastic Postseismic Deformation, John Loveless, Brendan J. Meade Aug 2025

Kinematic Representations Of Viscoelastic Postseismic Deformation, John Loveless, Brendan J. Meade

Geosciences: Faculty Publications

Abstract Following large earthquakes, viscoelastic stress relaxation may contribute to postseismic deformation observed at Earth's surface. Mechanical representations of viscoelastic deformation require a constitutive relationship for the lower crust/upper mantle material where stresses are diffused and, for non‐linear rheologies, knowledge of absolute stress level. Here, we describe a kinematic approach to representing
geodetically observed postseismic motions that does not require an assumed viscoelastic rheology. The core idea is to use observed surface motions to constrain time‐dependent displacement boundary conditions applied at the base of the elastic upper crust by viscoelastic motions in the lower crust/upper mantle, approximating
these displacements as …

Go to article

Understanding The Experiences And Perceptions Of Faculty Supporting Undergraduate Students With Mental Health Challenges, Jenna Ranee Parbati Jamieson Aug 2025

Understanding The Experiences And Perceptions Of Faculty Supporting Undergraduate Students With Mental Health Challenges, Jenna Ranee Parbati Jamieson

Dissertations

College is a big adjustment for students, and it doesn't come without its challenges, including being in a new place with new responsibilities. This is a stressful time that presents new obstacles and frustrations that can lead to increased stress, anxiety, depression, and mental health challenges that may cause faculty to engage and support undergraduate students with mental health challenges. As students adjust and transition to college, it is vital for university faculty to feel confident and comfortable supporting students from diverse backgrounds with varying levels of distress. By interviewing faculty, a better understanding of their lived experiences and perceptions …

Go to article

Spatial Distributions And Occupancy Dynamics Of Carnivores In A Central Hardwood Forest, Maximillian Larreur Aug 2025

Spatial Distributions And Occupancy Dynamics Of Carnivores In A Central Hardwood Forest, Maximillian Larreur

Dissertations

Extirpation of apex predators, caused primarily by anthropogenic alterations to natural environments and persecution, has led to mesocarnivore release in these areas. Mesocarnivore release is an ecological phenomenon in which mesocarnivores thrive in the absence of apex predator dominance within the carnivore hierarchy. Mesopredators fill this dominant role on the landscape as de facto apex predators, however, this can lead to changes in inter-guild species space use, predator-prey dynamics, activity patterns, and interspecific competition. Understanding patterns in wildlife spatial distributions, which indicate variability in habitat space use across spatiotemporal scales, is critical for developing effective management and conservation plans and …

Go to article

Focus: Evaluating Pre-Trained Vision-Language Models On Underspecification Reasoning, Kankan Zhou, Yibin Lai, Kyriakos Mouratidis, Jing Jiang Aug 2025

Focus: Evaluating Pre-Trained Vision-Language Models On Underspecification Reasoning, Kankan Zhou, Yibin Lai, Kyriakos Mouratidis, Jing Jiang

Research Collection School Of Computing and Information Systems

Humans possess a remarkable ability to interpret underspecified ambiguous statements by inferring their meanings from contexts such as visual inputs. This ability, however, may not be as developed in recent pre-trained visionlanguage models (VLMs). In this paper, we introduce a novel probing dataset called FOCUS to evaluate whether state-of-the-art VLMs have this ability. FOCUS consists of underspecified sentences paired with image contexts and carefully designed probing questions. Our experiments reveal that VLMs still fall short in handling underspecification even when visual inputs that can help resolve the ambiguities are available. To further support research in underspecification, FOCUS will be released …

Go to article

Non-Homophilic Graph Pre-Training And Prompt Learning, Xingtong Yu, Jie Zhang, Yuan Fang, Renhe Jiang Aug 2025

Non-Homophilic Graph Pre-Training And Prompt Learning, Xingtong Yu, Jie Zhang, Yuan Fang, Renhe Jiang

Research Collection School Of Computing and Information Systems

Graphs are ubiquitous for modeling complex relationships between objects across various fields. Graph neural networks (GNNs) have become a mainstream technique for graph-based applications, but their performance heavily relies on abundant labeled data. To reduce labeling requirement, pre-training and prompt learning has become a popular alternative. However, most existing prompt methods do not distinguish between homophilic and heterophilic characteristics in graphs. In particular, many real-world graphs are non-homophilic-neither strictly nor uniformly homophilic-as they exhibit varying homophilic and heterophilic patterns across graphs and nodes. In this paper, we propose ProNoG, a novel pre-training and prompt learning framework for such non-homophilic graphs. …

Go to article

Coleclip: Open-Domain Continual Learning Via Joint Task Prompt And Vocabulary Learning, Yukun Li, Guansong Pang, Wei Suo, Chenchen Chen, Yuling Xi, Lingqiao Liu, Hao Chen, Guoqiang Liang, Peng Wang Aug 2025

Coleclip: Open-Domain Continual Learning Via Joint Task Prompt And Vocabulary Learning, Yukun Li, Guansong Pang, Wei Suo, Chenchen Chen, Yuling Xi, Lingqiao Liu, Hao Chen, Guoqiang Liang, Peng Wang

Research Collection School Of Computing and Information Systems

This article investigates the problem of continual learning (CL) of vision-language models (VLMs) in open domains, where models are required to perform continual updating and inference on a stream of datasets from diverse seen and unseen domains with novel classes. Such a capability is crucial for various applications in open environments, e.g., AI assistants, autonomous driving systems, and robotics. Current CL studies mostly focus on closed-set scenarios in a single domain with known classes. Large pretrained VLMs such as CLIP have showcased exceptional zero-shot recognition capabilities, and several recent studies have leveraged the unique characteristics of VLMs to mitigate catastrophic …

Go to article

Freqllm: Frequency-Aware Large Language Models For Time Series Forecasting, Shunan Wang, Min Gao, Zongwei Wang, Yibing Bai, Feng Jiang, Guansong Pang Aug 2025

Freqllm: Frequency-Aware Large Language Models For Time Series Forecasting, Shunan Wang, Min Gao, Zongwei Wang, Yibing Bai, Feng Jiang, Guansong Pang

Research Collection School Of Computing and Information Systems

Large Language Models (LLMs) have recently shown promise in Time Series Forecasting (TSF) by effectively capturing intricate time-domain dependencies. However, our preliminary experiments reveal that standard LLM-based approaches often fail to capture global correlations, limiting predictive performance. We found that embedding frequency-domain signals smooths weight distributions and enhances structured correlations by clearly separating global trends (low-frequency components) from local variations (high-frequency components). Building on these insights, we propose FreqLLM, a novel framework that integrates frequency-domain semantic alignment into LLMs to refine prompts for improved time series analysis. By bridging the gap between frequency signals and textual embeddings, FreqLLM effectively captures …

Go to article

First Prev Next Last