Open Access. Powered by Scholars. Published by Universities.®
- Discipline
-
- Engineering (17305)
- Computer Engineering (13034)
- Artificial Intelligence and Robotics (11140)
- Databases and Information Systems (7250)
- Numerical Analysis and Scientific Computing (6663)
-
- Electrical and Computer Engineering (5273)
- Social and Behavioral Sciences (4821)
- Operations Research, Systems Engineering and Industrial Engineering (4777)
- Information Security (4669)
- Software Engineering (4314)
- Systems Science (3920)
- Business (2515)
- Mathematics (2384)
- Graphics and Human Computer Interfaces (2371)
- Theory and Algorithms (2151)
- Education (2097)
- Life Sciences (2073)
- Programming Languages and Compilers (1844)
- Medicine and Health Sciences (1802)
- Other Computer Sciences (1793)
- OS and Networks (1759)
- Arts and Humanities (1455)
- Communication (1445)
- Law (1174)
- Data Science (1156)
- Applied Mathematics (1133)
- Statistics and Probability (1061)
- Bioinformatics (985)
- Institution
-
- Singapore Management University (9003)
- China Simulation Federation (3880)
- TÜBİTAK (3106)
- Wright State University (2694)
- Purdue University (2077)
-
- Old Dominion University (1996)
- Missouri University of Science and Technology (1938)
- University of Nebraska - Lincoln (1739)
- Edith Cowan University (1285)
- Air Force Institute of Technology (1277)
- University of Texas at El Paso (1174)
- Kennesaw State University (1161)
- Dartmouth College (1102)
- San Jose State University (1053)
- City University of New York (CUNY) (956)
- Embry-Riddle Aeronautical University (949)
- Washington University in St. Louis (830)
- Brigham Young University (823)
- Technological University Dublin (816)
- California Polytechnic State University, San Luis Obispo (788)
- Zayed University (677)
- University of Texas at Arlington (666)
- University for Business and Technology in Kosovo (637)
- Portland State University (625)
- Chulalongkorn University (618)
- Nova Southeastern University (577)
- New Jersey Institute of Technology (571)
- Syracuse University (532)
- University of Nebraska at Omaha (497)
- University of Central Florida (490)
- Keyword
-
- Machine learning (1665)
- Artificial intelligence (1019)
- Deep learning (1003)
- Machine Learning (756)
- Computer Science (702)
-
- Security (648)
- Cybersecurity (557)
- Artificial Intelligence (484)
- Deep Learning (432)
- Computer science (412)
- Privacy (410)
- Simulation (391)
- Technical Reports (390)
- UTEP Computer Science Department (389)
- Classification (375)
- Algorithms (357)
- Optimization (352)
- Computer vision (349)
- Neural networks (345)
- Data mining (337)
- AI (299)
- Natural language processing (293)
- Department of Computer Science and Engineering (291)
- Engineering (269)
- Education (268)
- Reinforcement learning (259)
- Blockchain (255)
- Cloud computing (255)
- College for Professional Studies (253)
- Software engineering (252)
- Publication Year
- Publication
-
- Research Collection School Of Computing and Information Systems (8458)
- Journal of System Simulation (3880)
- Turkish Journal of Electrical Engineering and Computer Sciences (3106)
- Theses and Dissertations (2733)
- Department of Computer Science Technical Reports (1721)
-
- Computer Science & Engineering Syllabi (1312)
- Computer Science Faculty Publications (928)
- Computer Science Faculty Research & Creative Works (919)
- Departmental Technical Reports (CS) (914)
- Master's Projects (859)
- Computer Science Technical Reports (772)
- The R Journal (708)
- All Computer Science and Engineering Research (683)
- All Works (675)
- Faculty Publications (663)
- C-Day Computing Showcase (653)
- Chulalongkorn University Theses and Dissertations (Chula ETD) (618)
- Dissertations (568)
- Electronic Theses and Dissertations (567)
- Kno.e.sis Publications (542)
- Journal of Digital Forensics, Security and Law (536)
- CCAC Theses and Dissertations (512)
- Walden Dissertations and Doctoral Studies (469)
- Computer Science Faculty Publications and Presentations (404)
- Theses (403)
- USF Tampa Graduate Theses and Dissertations (378)
- Neutrosophic Systems with Applications (375)
- Computer Science and Engineering Theses - Archive (365)
- Computer Science: Faculty Publications (364)
- Browse all Theses and Dissertations (359)
- Publication Type
Articles 781 - 810 of 63009
Full-Text Articles in Computer Sciences
Adaptive Channel Switching For Contention Resolution, Shafqat Hasan
Adaptive Channel Switching For Contention Resolution, Shafqat Hasan
Theses and Dissertations
Contention resolution is a fundamental problem in distributed computing, where multiple devices compete to transmit over a shared channel without centralized coordination. Classical models typically assume a single always-available channel and focus on minimizing makespan. However, modern wireless systems increasingly operate under spectrum-sharing frameworks in which access to high-capacity spectrum is opportunistic and may be interrupted by higher-priority users. These settings introduce new challenges, including asymmetric channel speeds, adversarially scheduled evictions, and non-trivial switching costs. In this thesis, we study contention resolution in a dual-channel model consisting of a slow, always-available channel and a faster channel subject to adversarially scheduled …
Accelerating Defensive Cyber Operations Via Unsupervised Log Clustering And Automated Regex Template Synthesis, Charles Matthew Jones
Accelerating Defensive Cyber Operations Via Unsupervised Log Clustering And Automated Regex Template Synthesis, Charles Matthew Jones
Theses and Dissertations
Modern Security Operations Centers (SOCs) ingest millions of log entries per day, but manual parsing does not scale to the volume, heterogeneity, and rapid evolution of log formats. This dissertation investigates whether unsupervised clustering can automate the generation of candidate field-extraction templates while remaining deployable in production and feasible under realistic runtime and memory constraints. The central research question asks whether a machine-learning-assisted pipeline that proposes extraction templates for security engineer review—relative to reproducible human-authored baselines such as hand-written regular expressions—can measurably improve rule-set deployability and corpus-scale extraction quality. Improvement is quantified using four applicability metrics: Coverage Rate (CR), Exclusive …
Integrating Augmented Reality Visualizations Into Data Science Notebooks Using Microsoft Hololens 2, Derek Willis
Integrating Augmented Reality Visualizations Into Data Science Notebooks Using Microsoft Hololens 2, Derek Willis
Theses and Dissertations
Data-science notebooks support iterative analysis but are limited to two-dimensional (2D) displays. This work presents an approach to extend such environments with rapid augmented reality (AR) visualization while preserving conventional 2D workflows. An opensource R package was developed to convert notebook objects into three-dimensional (3D) models, export them in the Graphics Language Transmission Format (glTF), and transfer directly to a Microsoft HoloLens 2 via a USB connection for viewing in the native 3D Viewer application. The proposed workflow eliminates manual conversion and transfer steps required by earlier methods. A user study employing a post-session questionnaire indicated that participants found the …
A Comparative Performance Analysis Of Task Allocation Methods In Uav-Sdn Networks, Yasameen Ali Al Janabi, Ahmed Mhdi Al-Salih
A Comparative Performance Analysis Of Task Allocation Methods In Uav-Sdn Networks, Yasameen Ali Al Janabi, Ahmed Mhdi Al-Salih
Journal of Intelligent Informatics, Networking, and Cybersecurity
Task allocation is really important for how unmanned aerial vehicle-software-defined networking networks work and how much energy they use. This is especially true when the network is big or small and when things around it change. We looked at three ways to assign tasks: giving them out randomly giving them out in a manner that maintains load balance, and using something called ``particle swarm optimization'' We tried these methods in two situations: when the unmanned aerial vehicle-software-defined networking network is in open space and when it has to deal with obstacles. We used several unmanned aerial vehicles and tasks: 10 …
Phase-Preserving Machine Learning Forecasting Of Nonlinear Predator–Prey Dynamics, Saira Batool, Muhammad Imran, Brett Mckinney
Phase-Preserving Machine Learning Forecasting Of Nonlinear Predator–Prey Dynamics, Saira Batool, Muhammad Imran, Brett Mckinney
Biology and Medicine Through Mathematics Conference
No abstract provided.
The Making Of An Extremist: How Do We Become Someone Else’S Nightmare?, María Paula Morales
The Making Of An Extremist: How Do We Become Someone Else’S Nightmare?, María Paula Morales
The Confluence
This article explores how ordinary people can be pulled into extremist movements and what psychological forces drive that process. It looks at three perspectives: social identity theory, which explains how group belonging shapes behavior, identity development, which shows how people searching for meaning may find it in extremist causes; and social neuroscience, which connects radicalization to brain activity linked to fear, loyalty, and moral judgement. Together, these approaches show that radicalization is not simply about ideology but about identity, emotion, and belonging. By understanding these dynamics, we can find better ways to prevent extremism and promote healthier, more inclusive communities.
Automatically Constructed Preference Pairs For Chain-Of-Thought: Consistency Gains With Accuracy Tradeoffs, Cameron Scolari, Lanyu Shang
Automatically Constructed Preference Pairs For Chain-Of-Thought: Consistency Gains With Accuracy Tradeoffs, Cameron Scolari, Lanyu Shang
Honors Thesis
We investigate preference optimization over chain-of-thought (CoT) reasoning using automatically constructed preference signals derived from the accuracy and internal consistency of a model. Our results show that framing reasoning as a preference learning problem improves both the accuracy of the final answer and the structure of the model outputs. We observe a non-monotonic relationship between performance and the Direct Preference Optimization (DPO) scaling parameter β, where moderate values maximize accuracy while lower values improve stability, highlighting a tradeoff between optimization strength and reliable generation. We further identify a tradeoff between reasoning consistency and accuracy. Increasing the consistency weight improves agreement …
Ai Shell, Jacqueline Roebuck Sakho
Ai Shell, Jacqueline Roebuck Sakho
Books
An AI Configuration Shell to train and deploy an Argumentation Coach. Presented and distributed to the UNC Commons Collective in May 2026.
Agentic Synthetic Data Generation For Automated Model Development, Frederick Eugene Diehl
Agentic Synthetic Data Generation For Automated Model Development, Frederick Eugene Diehl
Theses and Dissertations
Large Language Model research has made large strides in capabilities from sentiment analysis to writing code. These advancements have been realized thanks to research into specific capabilities such as prompting techniques. Language models today have demonstrated the ability to create content, transform, and classify. These capabilities are not limited to academic exploration but also found in commercial products that are positioning themselves from application augmentation to personal assistants. These commercial products tend to steer towards single actions such as “summarize this article” or “write a function that performs action...” In parallel research has continued to advance towards more advanced constructs …
Pwnagotchi: Deauthentication Attacks, Wpa Handshakes, And Wireless Network Security, Emily Musgrove
Pwnagotchi: Deauthentication Attacks, Wpa Handshakes, And Wireless Network Security, Emily Musgrove
Computer Science Honors Papers
Wireless networks are the foundation of modern device communication infrastructure. This project examines the security implications of automated WPA/WPA2 handshake collection using the Pwnagotchi, a portable Wi-Fi network auditing and penetration testing device. The paper provides a technical analysis of WPA and WPA2 authentication mechanisms, including the structure of the 4-way handshake, the creation of cryptographic keys, and the role of deauthentication attacks in forcing reconnections for handshake capture. Additionally, the project explores the vulnerabilities associated with using legacy wireless security protocols such as WEP and TKIP to allow for older technologies that continue to require such encryption methods. This …
Agentic Scientific Machine Learning For Autonomous Model Discovery In Systems Pharmacology, Nazanin Ahmadi, George Karniadakis
Agentic Scientific Machine Learning For Autonomous Model Discovery In Systems Pharmacology, Nazanin Ahmadi, George Karniadakis
Biology and Medicine Through Mathematics Conference
No abstract provided.
Synthergy: Social Deduction And Deception In Llm-Powered Agents, Lauren Campbell, Andrew Forney
Synthergy: Social Deduction And Deception In Llm-Powered Agents, Lauren Campbell, Andrew Forney
Honors Thesis
Synthergy is an online social deduction game designed to enable comparative analysis of how large language model-powered agents engage in social deduction and deception under conditions of asymmetric information. Inspired by social deduction games such as Town of Salem, Throne of Lies, and Mafia, the game consists of two factions, Harmony and Discord, to which agents are secretly assigned. Agents must infer others’ affiliations through dialogue, in-game abilities, and voting behavior. To evaluate agent behavior, we conducted 100 simulated games across six agent types: a random baseline agent (RandomSynth), an LLM-based agent (Synth), a chain-of-thought agent (CoT Synth), a Bayesian …
A Gis Analysis Of The Relationship Between Ndvi Value, Slope, And Aspect Of The Terrain Of The Prairie Restoration Project, Basil Lund
2026 Symposium
The Prairie Restoration Project (PRP) encompasses 115 acres of land on the west side of the EWU campus. The goal of the PRP is to restore what was once a section of wheat farm back to its original Palouse prairie state. Here, I am using publicly available satellite data to examine some potential variables affecting the health of wheat plants planted in the years 2009 to 2017. I have used 4-band aerial imagery to create a map of NDVI values within the bounds of the PRP, which visualizes the near-infrared wavelengths that are reflected by healthy, chlorophyll-rich plants. I have …
A Governance-Aware Multi-Agent Framework For Enhancing Fairness & Temporal Accuracy In Disaster Response Systems, Md. Ashfaqur Rahman
A Governance-Aware Multi-Agent Framework For Enhancing Fairness & Temporal Accuracy In Disaster Response Systems, Md. Ashfaqur Rahman
Theses and Dissertations
Large Language Models (LLMs) have demonstrated significant potential in disaster-response decision support, however, their deployment in high-stakes humanitarian settings raises critical concerns regarding factual reliability, fairness, temporal validity, and governance compliance. Hallucinated outputs, demographic bias, and outdated recommendations can directly impact vulnerable populations and undermine public trust. This dissertation proposes a governance-aware multi-agent framework designed to enhance fairness and temporal accuracy in disaster-response systems through structured Retrieval-Augmented Generation (RAG), verification-driven orchestration, and adaptive correction mechanisms.The proposed architecture decomposes response generation into specialized agents responsible for real-time retrieval, fact-checking, bias auditing, temporal validation, threshold-based correction, and monitoring. By embedding governance constraints …
Deep Learning Compilers, Raffi Khatchadourian
Deep Learning Compilers, Raffi Khatchadourian
Open Educational Resources
These lecture slides introduce deep learning compilers for a graduate compiler-construction course (CSc 81010). Building on the classical compiler pipeline, they show how modern machine-learning systems compile tensor programs: static tensor and type analysis (illustrated by a WALA/Ariadne-based refactoring of imperative TensorFlow code to graph mode), MLIR-based end-to-end compilation with IREE, and the PyTorch 2.x stack—TorchDynamo graph capture, AOTAutograd, PrimTorch operator decomposition, and TorchInductor lowering to Triton (GPU) and C++/OpenMP (CPU). The slides are a self-contained HTML (W3C Slidy) deck with editable Pandoc Markdown source. Part of a two-session unit on advanced compiler topics; see also "LLMs in Compiler Construction."
Llms In Compiler Construction, Raffi Khatchadourian
Llms In Compiler Construction, Raffi Khatchadourian
Open Educational Resources
These lecture slides survey the use of large language models (LLMs) in compiler construction for a graduate compiler course (CSc 81010). They situate LLMs across the compiler pipeline and examine representative work: foundation models trained on LLVM IR and assembly (Meta's LLM Compiler), LLM-driven code optimization, binary decompilation (LLM4Decompile), and LLM-assisted automated refactoring—alongside the challenges of applying probabilistic models to tasks that demand correctness. The slides are a self-contained HTML (W3C Slidy) deck with editable Pandoc Markdown source. Part of a two-session unit on advanced compiler topics; see also "Deep Learning Compilers."
Uncovering The Impact Of Youtube's Hidden Algorithm On Its Users, Oscar Perez
Uncovering The Impact Of Youtube's Hidden Algorithm On Its Users, Oscar Perez
COD Library Student Research and Award Symposium
YouTube is a well-known platform that offers users endless hours of news, entertainment, and education. This research seeks to understand how the algorithm functions and uncover the effects of allowing a system to curate content for viewers. The research combines academic sources with fieldwork to understand the impact of YouTube's algorithm.
Faculty Sponsor: Professor Jacqueline McGrath
Shaped By The Feed: Big Data, Identity And Power, Ana Paula Andrada
Shaped By The Feed: Big Data, Identity And Power, Ana Paula Andrada
COD Library Student Research and Award Symposium
I explored how big data and algorithms shape the way we think and interact at an individual and societal level. This started from things I kept noticing in everyday life. Through my research, I learned how the personalization and predictability in feeds can reinforce beliefs, limit our critical thinking, deepen polarization and threaten our freedom.
Faculty Sponsor: Professor Aleisha Balestri
Dynamic Trust Calibration, Bruno Miranda Henrique
Dynamic Trust Calibration, Bruno Miranda Henrique
Dartmouth College Ph.D Dissertations
Trust calibration between humans and Artificial Intelligence (AI) is crucial for optimal decision-making in collaborative settings. Excessive trust can lead users to accept AI-generated outputs without question, overlooking critical flaws, while insufficient trust may result in disregarding valuable insights from AI systems, hindering performance. Despite its importance, there is currently no definitive and objective method for measuring trust calibration between humans and AI. Current approaches lack standardization and consistent metrics that can be broadly applied across various contexts, and they don’t distinguish between the formation of opinions and subsequent human decisions. This thesis brings a novel and objective method for …
Energy-Efficiency Optimization And Comparison For Irs-Assisted Bidirectional Relay And Direct Transmissions, Caixia Cai, Jiayao Zhang, Fuli Zhong, Han Hai, Yayu Yang, Sunil Chinnadurai, Anwer Al-Dulaimi
Energy-Efficiency Optimization And Comparison For Irs-Assisted Bidirectional Relay And Direct Transmissions, Caixia Cai, Jiayao Zhang, Fuli Zhong, Han Hai, Yayu Yang, Sunil Chinnadurai, Anwer Al-Dulaimi
All Works
Intelligent reflecting surface (IRS) has emerged as a promising technique for achieving high-transmission rate and low-power consumption transmission to meet the requirements of future beyond 5G and 6G communication. In this paper, we optimize and compare the energy-efficiency (EE) of IRS-assisted bidirectional relay transmission (BRT) and bidirectional direct transmission (BDT). In specific, we firstly consider and give the IRS-assisted BRT and BDT models. Then, we give the analyses of signal transmission models and EE for both IRS-assisted BRT and BDT. In addition, to optimize the EE, we give the joint optimization problems for both IRS-assisted BRT and BDT, which incorporate …
Meeting The Moment With Ai-Employer Informed Education, Brent Terwilliger, John Faraca
Meeting The Moment With Ai-Employer Informed Education, Brent Terwilliger, John Faraca
Publications
As artificial intelligence transforms aviation, aerospace, and autonomy-related sectors, higher education must adapt to meet evolving workforce demands. This session shares emerging findings from a nationwide study led by Embry-Riddle Aeronautical University, focused on employer perceptions of AI adoption, responsible use, and workforce preparedness in domains including uncrewed systems, space systems, robotics, and advanced air mobility. Based on a structured survey and follow-up interviews, the presentation explores how organizations are using AI tools, from generative platforms to enterprise systems, and defining effective and inappropriate use in operational contexts. Participants will gain insight into critical concerns (e.g., data privacy, compliance, security, …
Sage: Contention-Aware Sensitivity Adjustment For Spin Lock Exiting In Vms, Sam Thomas Stowers
Sage: Contention-Aware Sensitivity Adjustment For Spin Lock Exiting In Vms, Sam Thomas Stowers
Theses - ALL
To address the severe multi-threaded performance degradation caused by lock contention in oversubscribed cloud environments, this thesis examines and improves on the Pause Loop Exit (PLE) mechanism used by hypervisors to deschedule unproductive virtual CPUs (vCPUs). These oversubscribed environments introduce contention which frequently leads to Lock Holder Preemption (LHP), where a hypervisor preempts a vCPU holding a critical spinlock, causing waiting vCPUs to waste cycles spinning. To mitigate LHP, hardware mechanisms trigger PLE events to inform hypervisors of spinning vCPUs, relying on a PLE_gap parameter to differentiate spinlock instances. The PLE_gap dictates spinlock detection sensitivity—a component of the virtualization stack …
Labeling And Describing Objects In A Photogrammetry-Based 3d Environment Using Computer Vision And Artificial Intelligence, Colin Donald Moschella
Labeling And Describing Objects In A Photogrammetry-Based 3d Environment Using Computer Vision And Artificial Intelligence, Colin Donald Moschella
Capstone Projects
Cataloging and digitizing the objects inside a building manually is a task that is often impractical at scale. This project therefore automates the process, using a custom-made system. Using a photogrammetry-based 3D reconstruction of a room, this system is applied to sequences of 2D images used to make the 3D models. The system applies object detection, image segmentation, and image-text models to identify and describe objects, using CNN based models such as YOLO and OpenCLIP. Each analyzed object is then stored in a structured database with spatial coordinates from the 3D scanning, descriptive attributes from the image-text models, and other …
Development And Launch Of Abn: An Adventist Freelance Web Application, Abishur Moses-Pakkianathan
Development And Launch Of Abn: An Adventist Freelance Web Application, Abishur Moses-Pakkianathan
MS in Computer Science Project Reports
The Seventh-day Adventist community often relies on personal networks and word-of-mouth for Adventist business services. Many of these businesses meet and provide services to their clients primarily through church connections and community recommendations. As the community and businesses grow, traditional networking methods become increasingly difficult to maintain. General marketplaces lack the trust framework shared by Adventists, and faith-based directories are often static or outdated without booking capabilities. Our solution provides a reliable and modern platform for Adventists to create service listings, receive and manage bookings, and connect with faith-aligned clients.
Stridevision: Automated Detection Of Running Form Deviations From 2d Pose Estimation And Machine Learning, Paulina Eguibar Ortega
Stridevision: Automated Detection Of Running Form Deviations From 2d Pose Estimation And Machine Learning, Paulina Eguibar Ortega
Honors Theses
Running gait analysis plays a critical role in injury prevention and performance optimization, however, existing approaches often rely on specialized laboratory equipment or wearable sensors with limited interpretability. Recent advances in computer vision, particularly 2D human pose estimation, enable markerless motion analysis from standard video. However, progress remains constrained by the lack of publicly available datasets designed for running form analysis.
In this work, we introduce a preliminary dataset and benchmark for stride-level running gait analysis. The dataset consists of 73 treadmill running videos from 15 participants with varying experience levels, annotated with over 4,600 stride-level labels across multiple biomechanical …
How Ai Governance Differs Between Regime Type, Jackson T. Guillou
How Ai Governance Differs Between Regime Type, Jackson T. Guillou
Honors Theses
This thesis will examine how artificial intelligence (AI) regulation and development differ across political regime types, arguing that governance outcomes are fundamentally shaped by institutional political structures. This thesis will draw on comparative frameworks analyzing democratic and authoritarian systems. This thesis will also include case studies of the European Union, the United States of America, China, and Russia. The study finds that democratic regimes tend to emphasize transparency, accountability, and rights-based regulation of AI. This often results in slow regulation of AI, but it is more ethically legitimate and constrained. In contrast, authoritarian regimes prioritize centralized control, strategic coordination, and …
Nutrilog: Design And Development Of A Full-Stack Web Application For Holistic Health Tracking, Jaromir J. Saloni
Nutrilog: Design And Development Of A Full-Stack Web Application For Holistic Health Tracking, Jaromir J. Saloni
Honors Theses
NutriLog is a web-based fitness and nutrition tracking application designed to help users record, organize, and interpret personal health data in one centralized platform. Many existing applications focus primarily on either nutrition tracking or exercise performance, which can make it difficult for users to understand how food intake and physical activity interact. NutriLog addresses this gap by combining food logging, exercise logging, calorie adjustment, nutrition summaries, and historical tracking into a single dashboard-based interface.
The application was developed using React and TypeScript for the frontend and Supabase for authentication, database storage, and user-specific data management. Nutrition data is supported through …
The One-Shot Ceiling: Comparing Rag And Fine-Tuning Architectures For Ai-Assisted Math Mentoring, Michael J. Cummins
The One-Shot Ceiling: Comparing Rag And Fine-Tuning Architectures For Ai-Assisted Math Mentoring, Michael J. Cummins
Computer Science Honors Papers
Providing individualized feedback to math students is a resource-intensive bottleneck in STEM education. We present Mentir-AI, a tool designed to elevate teacher capacity by generating high-quality mathematical feedback using the Mathforum's "Problem of the Week" archive. By analyzing a corpus of nearly one million interactions, we compare the efficacy of Retrieval-Augmented Generation (RAG) and Fine-Tuning (FT) architectures. This study details the development of an automated grading pipeline, the evolution of a multi-component system prompt, and the implementation of an automated mentor grading system in AI-led evaluation. While Fine-Tuning demonstrates superior instructional judgement, our results identify persistent failure modes in mathematical …
Private Assistant Agent, Bao Le '26
Private Assistant Agent, Bao Le '26
Senior Scholarly and Creative Symposium
Our brain has limited fuel: every time we make a decision, it costs fuel. A Personal Artificial Assistant will help preserve that fuel by handling secretarial tasks and scheduling a daily timetable for its user. Personal Assistant Agent (PAA) is an AI assistant running as a text-based Windows desktop application to help users in scheduling and give reminders like a secretary. Users interact with the PAA conversationally. This project is a system of reasoning and a modular memory pipeline that makes any Large Language Model (LLM) behave like a personal assistant. The Language model is isolated inside a function to …
High-Frequency Vr-Native Eye Tracking: From Data Collection To Machine Learning Models, Meherun Nesa Shraboni, Aryabrata Basu
High-Frequency Vr-Native Eye Tracking: From Data Collection To Machine Learning Models, Meherun Nesa Shraboni, Aryabrata Basu
Research and Creative Works Expo
No abstract provided.