Accepted Papers

A Comparative Study of Deep Learning Architectures for Multi-Label Electrocardiogram Classification: Nicholas Kanos, Alina Lazar and Shreeshtee Dhakal

A Deep Learning Framework for Automatic Multi-View Facial–Nasal Landmark Detection in Clinical Photographs: Tran Dinh Anh Tuan, Nguyen Minh Trieu, Nguyen Thien Bao and Nguyen Truong Thinh

A Fairness-Aware Semi-Supervised Clustering Method: Cristina Maier, Cyrus Saadat and Dan Simovici

A Landscape of Trustworthy AI Frameworks and Metrics: Mapping to the NIST AI Risk Management Framework: Marlana Hatcher, Seyed Mohammad Sanjari, Maraz Mia and Mir Mehedi Pritom

A Multi Attribute Extension of MDFT: Connor Tate, Brent Venable and David Fries

A Narrative-Driven Computational Framework for Clinician Burnout Surveillance: Alyssa Meczkowska, Fazel Keshtkar, Neeam Hayder and Syed Ahmad Chan Bukhari

A Pseudo-Boolean Formulation for Graph Database Queries: Gabriel Tiveron and Bruno Ribas

A Scalable Approach to Solving Simulation-Based Network Security Games: Michael Lanier and Yevgeniy Vorobeychik

A Seven-Layer Lifecycle Framework for Fair, Robust, and Safe AI: Guidance and a German Credit Case Study: Vahid Heydari and Kofi Nyarko

A Study on How Well LLMs Can Assist Novices with Code Comprehension Tasks: Mahmudul Islam Sajib, Shanti Tamang, Jeevan Chapagain and Vasile Rus

A Unified Atlas-Aware Framework for Interpretable Spatio–Temporal EEG Source Imaging: Sina Makhdoomi Kaviri and Ramana Vinjamuri

A Visualization of Explainable Stylometry of Presidential Speech and Writing: Mina Rajaei Moghadam, Mosab Rezaei, David Koop, Maoyuan Sun and Reva Freedman

ACE-TA: An Agentic Teaching Assistant for Grounded Q&A, Quiz Generation, and Code Tutoring: Himanshu Tripathi, Charlotte Crowell, Kaley Newlin, Subash Neupane, Shahram Rahimi and Jason Keith

ASP∀: An Open Educational Resource for Answer Set Programming.: Joshua T. Guerin, David Gonzalez and Jackson Madsen

Addressing a bias in Evaluating of Student Explanations of Worked Programming Examples: Arun Balajiee Lekshmi Narayanan, Xiang Lorraine Li and Peter Brusilovsky

Advancing Fairness and Explainability in AI for Autism Diagnosis: Davis Nguyen and Sheikh Rabiul Islam

An Elicitation-Matrix Approach to Pragmatic Context Modeling in Low-Resource Machine Translation: The Case of Akuapem Twi: Kweku Yamoah, Godfred Agyapong, Kevin Scroggins, Neel Parekh, Detravious Brinkley, Chathuri Jayaweera, Shlok Gilda, Bonnie Dorr and Emmanuel Dorley

An Exploratory Study of Agentic Retrieval Augmented Generation for Mental Health Oriented Language Models: Khoa Pham, Jiacheng Li, Hassan Al Khatib, Shahram Rahimi, Noorbakhsh Amiri Golilarz and Andy Perkins

An Iterative Self Correcting Agentic RAG System: Vinay Tiparadi, Narayan Krishnan, Chetanya Rathi, Hiren Manani and Priyantha Kumarawadu

An approach to Dimensionality Reduction based on Constrastive Learning: a Preliminary Analysis: Luigi Portinale and Giacomo Bertolazzi

Approximate Decryption in Homomorphic Division and Privacy impact: Ameerah Alsulami and Marius Silaghi

Automated Identification of Lexical Misalignment in Preference-Stage Learning across Large Language Model Families: Xiaoyang Ming, Jose Hernandez and Thomas Stephan Juzek

Automatic Root-Cause Chain Extraction from Technician Maintenance Notes Using NLP and LLM Reasoning: Viquar Younus Mohammed

BDI Agent-Based Access Control Reasoning for Multimodal Retrieval-Augmented Generation: Halil Yesil, Baris Tekin Tezel and Moharram Challenger

Beyond Accuracy: Performance and Behavioral Evaluation of Multimodal AI for Suspicious Aerial Traffic Monitoring: Gabriel Dietzsch and Elcio Hideiti Shiguemori

Beyond Coefficients: Forecast-Necessity Testing for Interpretable Causal Discovery in Nonlinear Time-Series Models: Valentina Kuskova, Dmitry Zaytsev and Michael Coppedge

Botox Detection and Face Analytics Using Deep Learning: Audison Beaubrun, Gabriella Pangelinan and Michael King

Bridging Expectation Signals: LLM-Based Experiments and a Behavioral Kalman Filter Framework: Yu Wang and Xiangchen Liu

Comparing EPGP Surrogates and Finite Elements Under Degree-of-Freedom Parity: Obed Amo, Samit Ghosh, Markus Lange-Hegermann, Bogdan Raita and Michael Pokojovy

Comparing Explanations of Competing Clinical Classification Algorithms: Moumita Kamal, Doug Talbert, Nolan Patterson, Nick Atkins and Celia Hough

Computational Models of Player Strategy in Roguelike Games: Chris Alvin

Dense Attention-Enhanced U-Net for Complex Image Segmentation Tasks: Shahariaj Moham Sajid and Nazmul Shahadat

Do Programmers and AI See the Same Problem? Quantifying Cognitive Misalignment in Code Generation: Yi Zhang and Julia Rayz

Domain-Adapted NLP for Multi-Label Crash Narrative Classification under Extreme Class Imbalance: Md Sajjad Hossain, Lin Li, Judy A. Perkins, John Clary, Joel Meyer and Ramon Gomez

Dwell Time Estimation Using Periodic Image Captures and Deep Learning: John Butoto, Xudong Liu and Thobias Sando

Effects of Personalization in Large Language Model Tutors on Cognitive Load during Mathematics Learning: Uriel Karerwa, Thadde Rolon-Merette, Hajar Laghmari, Katrina Sollazzo, Alejandra Ruiz Segura, Constantinos Coursaris, Sylvain Sénécal, Pierre-Majorique Leger and Alexander Karran

Evaluating Mistral 7B Instruct Jailbreak Vulnerabilities: Sina Jamshidi, Hady Ahmady Phoulady and Shafika Showkat Moni

Evaluating Personalized Content Using Large Language Models: Joshua Shay Kricheli, Benjamin Nye, Daniel Auerbach, Aaron Shiel, Kayla Carr, Kaelyn Ellison and Bill Swartout

Evidence-Grounded Verification of Oncology Clinical Notes Using Structured EHR Data: Sajib Acharjee Dip, Bikash Kumar Paul, Adrika Zafor and Liqing Zhang

Fairness Implications of Data Minimization in Deep Collaborative Filtering: Sipei Li, Nasim Sonboli, Mehdi Elahi and Alva Couch

Fast and Flexible Sampling-Based Local Replanning for Single-Query Paths in Unknown Environments: Ros Maria E. F. Stanly, Irene Ramirez, Shalini Mehra and Ayan Dutta

Forecasting Geomagnetic Disturbances with Interpretable Deep Learning: Teja P. S. Singampalli, Jason T. L. Wang, Chunhui Xu and Katherine G. Herbert

Forgetting by Design: Testing the Effectiveness of Machine Unlearning in Right to Be Forgotten Data Deletion: Jericka Guy and Chutima Boonthum-Denecke

Fragment-Based AI for Antibiotic Discovery: Adam Bess, Chris Alvin and Supratik Mukhopadhyay

From Tokens to Ties: Network and Discourse Analysis of Web3 Ecosystems: Valentina Kuskova and Dmitry Zaytsev

FuseGO: Evaluating Embedding Fusion Across Species with Unequal Encoder Capacity for Automated Protein Function Prediction: Anne Howell and Indika Kahanda

Have (A)I Seen this Before? Exploring LLM Metacognition Using Self-Reported Rankings and Scoring: Anura Deshpande, Celine Cerezci, Benjamin Nye, Mark G. Core, Suvaditya Mukherjee and Joshua Shay Kricheli

Impact of AI-Generated Queries on SQL Code Complexity: Janka Pecuchová and Ľubomír Benko

Implementing Nonmonotonic Reasoning From Weakly Consistent Conditional Belief Bases: Christoph Beierle, Aron Spang, Lars-Phillip Spiegel and Jonas Philipp Haldimann

Improving Resilience Against Cyber-attacks via Reward-Shaped Reinforcement Learning in a Network Defense Game: Prithviraj Dasgupta

Integrating Large Language Models as Cognitive Agents into the GAMA Platform for Urban Mobility Simulation: Bruno Cascaes Alves, Míriam Blank Born and Marilton Sanchotene de Aguiar

Investigating Human-Aligned Large Language Model Uncertainty: Kyle Moore, Jesse Roberts, Daryl Watson and Pamela Wisniewski

JSON-LD 1.2 and Beyond: Extensions for Machine Learning Data Exchange: Muntaser Syed, Marius Silaghi, Sheikh Abujar, Rwaida Alssadi and Sharun Akter Khushbu

Knowledge-Augmented Large Language Models for Automated Characterization of Cybersecurity Vulnerabilities: Elijah Needham, Denis Ulybyshev and Ayesha Dina

LLM Pruning with Elastic Net Enhanced Wanda Strategy: Ayman Gharaibeh, William B. Glisson, Xiyuan Liu and Majd Z. Tahat

Lipschitz-Regularized Critics Lead to Policy Robustness Against Transition Dynamics Uncertainty: Xulin Chen, Ruipeng Liu, Zhenyu Gan and Garrett E. Katz

MLSD: A Novel Few-Shot Learning Approach to Enhance Cross-Target and Cross-Domain Stance Detection: Parush Gera and Tempestt Neal

Metadata Engineering: Harmonizing CT Descriptors in Enterprise Imaging Systems: Augustus Scarlato

Multi-Label Heart Disease Classification Using Electrocardiograms and Machine Learning: Ashritha Kotagiri and Liu Xudong

Multi-Stream Fusion of Spatial, Frequency, and Attention Features for Robust Deepfake Detection in Low-Resolution Images: Vaishnavi Sen, Cody Laurie and Rashida Hasan

On Using Domain Control Knowledge in Planning: Position Paper: Lukas Chrpa and Roman Barták

OncoMark: A Two-Stage Gated Framework for Cancer Hallmark Detection from Biomedical Text: Adrika Zafor, Sajib Acharjee Dip and Liqing Zhang

Operationalization-Aware Modeling of Software Non-Functional Requirement Relationships: A Context-Aware Approach: Unnati Shah and Siba Mishra

Prediction of Solar Flares Using Photospheric Magnetic Field Parameters with Deep Learning: Yash Chaudhary, Jason T. L. Wang, Chunhui Xu and Sen Zhang

Probing Knowledge Graph Reliability and Semantic Coherence with Language Models: Yoonhyuck Woo and Julia Rayz

Propasafe-Hybrid: A Text-Based Hybrid Propaganda Detection Tool: Thomas Kimmeth, Avijit Roy and Vivek Sharma

ProtoPVAE: Improving Prototype Consistency and Stability with Regularized Latent Spaces: Shiska Raut and Manfred Huber

Quantifying Modality Contributions in Vision-Language Models via Partial Information Decomposition: Namitha Rayasam, Amit Padegal, Omkar Mahesh Kashyap, Nidhi Shekhar and Surabhi Narayan

RAMP: Exploring the Feasibility of Detecting Physics Student Misconceptions in Writing Assignments Using Large Language Models: Ella Luedeke, Natalie Spiro, Indika Kahanda, W. Brian Lane, J. Caleb Speirs, Terrie Galanti and Upulee Kanewala

Real-Time Neck Posture Classification Using a Lightweight Wearable IMU Pendant: Muntaser Syed, Alfred Sjöqvist, Noah Sedlik and Tsing Liu

Reliability Beyond Accuracy: Error Analysis of Agentic Tool-Augmented Reasoning in LLMs on CURE-Bench: Hilmi Demirhan, Ruize Ma, Tianqi Wang and Wlodek Zadrozny

Robotic Fall Prediction with Spatio-Temporal Processing of Egocentric Vision and Proprioception: Borui He, Garrett Katz and Senem Velipasalar

S3FC: Scalable Sparse Spectral Fusion Clustering for Multi-Manifold Data: Matthew Radice and Joshua Phillips

Scope Aware Contractor Performance Prediction Using Machine Learning and Work Package Vector Similarity: Pedro Fonseca and Sergei Chuprov

Shop-The-Room: A Zero-Shot Foundation Model Framework for Visual Discovery in E-Commerce: Vaidyanath Areyur Shanthakumar, Clark Barnett, Vipul Mehra, Komson Chanprapan, Ravi Shankar and Tathagata Mukherjee

Steganography with Large Language Models: Key Sensitivity Analysis: Alexander V. Mantzaris, Wissam Ghantous, Haley Stinebrickner, Stephen Webinga and Samira Jahangiri

Sudoku Sage: Evaluating Correctness of LLM-Generated Moves as a Constraint Satisfaction Task: Aidan Gillespie, Vladimir Serov, Drew Phelps and Amr Hilal

Systematic Analysis of Tokenization Properties in Low-Resource Polysynthetic NMT: Daniel Ndayegamiye, Jesse Roberts and Benjamin Frey

TOML: Transistor Operations for Machine Learning - A Physics-Grounded Energy Efficiency Framework: Muntaser Syed, Marius Silaghi, Sheikh Abujar and Sharun Akter Khushbu

The Role of Emotions: Investigating Communicative Roles in Models and Data for Emotion Recognition: Timothy Meinert, Valerio Basile and Anna Koufakou

The effect of decomposition rule modeling on the efficiency of hierarchical planners: Roman Barták, Simona Ondrčková and Kristýna Pantůčková

Tiny KANs: A Performance Benchmark of Kolmogorov-Arnold Networks on Microcontrollers: Sai Sathvik Motamarri, Mohammed Hassan, Shiva Golugula, Shravan R Jain and Arti Arya

Towards Fair Pay and Equal Work: Imposing View Time Limits in Crowdsourced Image Classification: Yi Yang Gordon Lim, Stefan Larson, Yu Huang and Kevin Leach

Training Ethical Language Models via Reinforcement Learning from AI Feedback: Bishal Thapa, Alden Duarte-Vasquez, Sahar Hooshmand and Heena Rathore

When One Model Is Not Enough: Twin Training for Prioritized Decisions: Kn Gowri and Velampalli Sirisha

When to Measure: A Multi-Agent Reinforcement Learning Approach for Efficient Tracking: Alessandro Amato, Raffaele Galliera, K. Brent Venable and Niranjan Suri

Winning Isn't Reasoning: Evaluating Iterative Reasoning Updating in Language Models: Kevin Scroggins, Kweku Yamoah and Emmanuel Dorley

AI-Driven Cyber Defense: Advanced Multimodal Learning for Evolving Malware Threats: Ahmed Sarwar Mohammed

AstroAid: Personalized Target Down-Selection for Amateur Astronomers: Joseph Salisbury

Automatic Translation from LIME to Clinically Meaningful Triage Explanations: Doug Talbert, Steve Talbert, Nick Atkins, Katherine Phillips, Nolan Patterson and Moumita Kamal

Clinical Narratives Matter: Feature-Level Fusion for Improving ICU Length-of-Stay Prediction: Noshini Islam Naina, Abu Saleh Md Tayeen, Ingrid Russell, Andrew Jung and Akin Tatoglu

Comparative Study of Different Learning Paradigms for Zero-Shot Sentiment Analysis of the Low-Resource African Language Oromo: Linrui Zhang, Qixiang Pang and Belinda Copus

Deep Contrastive Representations for Neural-Congruency Modeling in EEG Studies of Reading Disorders: Jacqueline Torres, Maria Theodorou and Christoforos Christoforou

Document, Verify, Explain: A Transparent Accountability Framework for Equitable Generative AI Use in Computer Science Education: Angel Rivera and Unnati Shah

Dynamic Conditional Logic: A Complete Axiomatization of Update, Retraction, and Minimal Change: Konstantinos Georgatos

Evaluating Logical Structure in Computer Programs Using LLMs: Shanti Tamang, Md Abdul Mazid Adnan, Mahmudul Islam Sajib and Vasile Rus

Evaluating Synthetic Sentence Coherence Using a Large Language Model: Richard Thompson, Angelos Toutsios, Adam Pease, Christian Darken and Matthias Kolsch

Explainable Hierarchical Graph Neural Networks for Structured Decision Modeling: Sirisha Velampalli

Feasibility of Tiny Recursion Models for the Traveling Salesman Problem: Learned Insertion and 2-opt Refinement: Alexander V. Mantzaris

Fine-Grained Sentence-Level Propaganda Detection in News Articles: Mustafa Eren, Aneeza Shakeel and Vivek Sharma

Generation and Validation of Configuration Management Code for Cyber Range Environments Using Large Language Models: Travis Lee, Muhammad Ismail and Jesse Roberts

Ghost Agents in SAT-based Models for Multi-Agent Pathfinding: Jiří Švancara and Roman Barták

Graph-Based Modeling of Iceberg Dynamics from Synthetic Aperture Radar Imagery: Olivia Patterson and Rebecca Williams

How the Architectural Design of the Detection Model Can Enhance the Effect of Adversarial Patches: Terrelle Thomas, Idongesit Mkpong-Ruffin, Chutima Boonthum-Denecke and Deidre Evans

InsightBoard: An Interactive Multi-Metric Visualization and Fairness Analysis Plugin for TensorBoard: Ray Chen and Christan Grant

Learning General CP-nets Using Simulated Annealing: Michael Huelsman

Learning Team Synergy from Team Composition with a Siamese Transformer: Xiaomeng Ye, Elliot Mayo, Joseph Cuthbert and Anthony Head

Monitoring therapeutic plans and risk signals from clinical narratives in mental health using natural language processing: Margarita Ruiz Olazar, Andrea Aguilera, Diego Ihara, Cecilia Scales and Fernando Sosa

Multimodal Chest Pathology Classification with Language and Image Transformers: Chamudi Abeysiriwardana, Madhukara Kekulandara and Abdeltawab Hendawi

SAGE 0.2: LLMs for DOM Informed Internet Guidance: James Brooks, Jesse Roberts and Patrick McCloud

Satellite Image Analysis Using Modified EfficientNet: Rahul Chaudhari and Nazmul Shahadat

Skull-Conditioned Facial Soft-Tissue Reconstruction Using Anatomy-First Deep Volumetric Inference: Nguyen Tuan Kiet, Nguyen Minh Trieu, Nguyen Thien Bao and Nguyen Truong Thinh

The Robot Maze Test: An Evaluation of Situated Learning for Humans and Machine Agents: Ian Perera, Brady DeCouto, Christopher Bates, Matthew Johnson, Charles Patterson, Alec Treacy and Zoeanne McCurdy

The ``Sweet Spot'' in Human-AI Teamwork: Kazuhiko Momose and Thomas Eskridge

Towards a Cross-Participant Cognitive Load Classification Using Eye Tracking and Deep Learning: Thadde Rolon-Merette, Gabriel Hardy Joseph, Alexander John Karran, Charles Bélanger, Constantinos Coursaris, Sylvain Sénécal and Pierre-Majorique Leger

UCMUNET Liver: Unified Cross-Modality 3D U-Net to Enhance Liver Segmentation in Cirrhotic Patients: Lina Chato, Kristipati Thoyajaksha Kashyap, Bhuvi Moturu, Prajwal Arun Kumar, Lavanya Sathish Raviteja Borra and Ravi Teja Thota

A Comparative Evaluation of Document Extraction Tools for Construction Specification Parsing: Alekhya Seelam and Sneha Ganupa

A Preliminary Empirical Study of Large Language Models for Grading Debugging Problems in Programming Education: Qixiang Pang, Linrui Zhang, Belinda Copus and Shan Du

A Relational Model for Fine-Grained Visual Classification: Akkhar Ulok, Atefeh Gilvari, Ziad Kobti and Sudhir Paul

Automated IoT Threat Monitoring & Mitigation using Tiny LLMs: Vinay Tiparadi, Narayan Krishnan, Chetanya Rathi and Priyantha Kumarawadu

Blockchain as a Tool for Ensuring Authenticity: Combating Fake AI-Generated Content and Misinformation: Kyle Pasion

Can LLMs Classify Vehicular Basic Safety Messages Anomalies?: Arjun Gyawali, Rakesh Das and Heena Rathore

Classifying Target Sentences for LLM-Generated Persuasion Attacks in Press Releases from Federal Research Agencies: Hsien-Te Kao, Peter Bautista, William Dupree, Gabriel Ganberg, Jeffrey M. Beaubien, Laura Cassani and Svitlana Volkova

Codify: An Intelligent Socratic Tutoring System for Programming Education: Allan Ilyasov, Giulio Bardelli, Sebastian Torres and Fazel Keshtkar

Collaboration on Waltz Labels can Achieve Qualitative Stereo Vision: Ben Mathew, Majed Alotaibi, Debasis Mitra and Marius Silaghi

Counting Constraints in POMDPs based on PID Controllers: Garrett Gmeiner, Patrick Quinn, Asmaa Alqurashi, Prem Pochiraju, Mirajul Islam, Jackson Contreras, Sajina Pathak, Rwaida Alssadi, Sumana Boyapalli, Raghavendra Mallesha, Vijay Uppalapati, Javier Laboy-Jusino, Nikiraj Konwar, Muntaser Syed and Marius Silaghi

CultIcon-Bench: A Pilot Benchmark for Cultural Interpretation of Visual Icon: Rwaida Alssadi and Marius Silaghi

Directional Relations in Complex Word Embeddings: Samira Jahangiri and Alexander Mantzaris

Do LLMs Outperform Fine-tuned Transformers in Emotion Classification? A Case Study of Llama and RoBERTa on an Emotion Benchmark: Tim Meinert and Anna Koufakou

Domain-Specificity of Refusal Representations in Large Language Models: Charlie Tucker and Maikel Leon

Emerging AI Trends: A 2025-2026 Synthesis: Maikel Leon

Explaining Why Instrumental Rationality is Insufficient for Ethical Behavior: Nicolas Tardif, Frédéric Beaudoin and Clayton Peterson

From Recommendation to Reflection: Measuring Moral Value Stability in Human–AI Collaboration Using Cognitive Value Recontextualization: Waseem Samkari and Thomas Eskridge

HARD-Xception: A Hybrid Adversarially Robust Deepfake Detection Framework Using Frequency Decomposition and Feature Consistency Learning: Dhruv Vagadiya, Vaishnavi Sen and Rashida Hasan

Improving LLM Thematic Analysis through Metric-Driven Self-Correction: Tacksoo Im and Hyesung Park

Improving RAG/CAG Based Additional Context Retrieval from Datasets implementations via Pokemon-themed AI Chatbot: Yeriel Rhee, Zayan Estaq, Steve Le and Cengiz Gunay

Interactive Solution Viewers for Automated Theorem Proving: Daniel Li, Esteban Morales, Geoff Sutcliffe and Jack McKeown

LLM-Augmented Clustering for Customer Support Ticket Triage: Priti Sagar

Machine Learning for Hypertension Prediction in U.S. University-Aged Students: Insights from NIH All of Us Data: Deborah Asamoah and Lina Chato

Multimodal Machine Learning for Student Retention Prediction: Integrating Temporal, Textual, and Tabular Features: Kashaina Nucum

Non-Stationary Spectral Decomposition Network for Econometric Time Series Forecasting: Nikhil Sunder

Reward-Guided Fine-Tuning of Language Models with Social Feedback: Jared Scott

Scalable Clinical Informatics Frameworks for AI-Enabled Assistive Systems in Mental Health Care: Heather Cooper, Nelly Elsayed and Maria Kyrarini

Scalable GNN Training for Track Finding: Bipana Bista, Sree Sai Charan Vaitla and Alina Lazar

Seeing the Spark Before the Flame: Wildfire Risk Detection via UNets: Jamie Boyd

Semantic Conversational AI for Construction Cost Analytics: Sneha Ganupa, Alekhya Seelam, Vamsi Sai Kalasapudi and Sandeep Reddivari

Semantic Length Limits in LLM Based Steganography: Haley Stinebrickner, Alexander V. Mantzaris and Wissam Ghantous

ShZZaM: An LLM+ATP Natural Language to Logic Translator: Geoffrey Sutcliffe and Danial Haroon

The Judge Effect in Two-Round Legal Debate on LegalBench: David Johnson, Onur Bilgin and John Licato

The Submittals Agent: A Hybrid Workflow for Automating Submittal Extraction from Construction Specifications: Alekhya Seelam, Sneha Ganupa, Vamsi Sai Kalasapudi and Sandeep Reddivari

Using a chat interface for a data-driven course planning wizard: Francis Bolay and Cengiz Gunay