Welcome to my portfolio!
About Me
Hello! I am a PhD candidate in Machine Learning at The University of Texas at Arlington with 6 first-authored publications and 8 total publications (58+ citations) in top-tier venues including KDD, IJCAI, and ASE. My research focuses on explainable AI, adversarial robustness, and trustworthy ML systems, conducted in collaboration with NIST. I am also the co-founder of Bhasha Tech, an AI-powered language learning platform serving 50,000+ users across 130+ countries. I combine deep research expertise with proven ability to build and scale real-world ML products.
Research Interests
My research sits at the intersection of explainable AI, trustworthy ML, and combinatorial methods for testing and improving learned systems. Current focus areas:
- Explainable AI & Interpretability – Faithful local explanations through adversarial bracketing (ABLE, KDD 2026), minimal sufficient explanations for vision models via delta debugging (DD-CAM, 2026), and quantifying feature-interaction degree in model predictions (ICSTW 2024)
- Knowledge Distillation & Tabular ML – Compact distillation of complex models using interaction diversity over learned feature bins (TabKD, IJCAI 2026)
- Combinatorial Methods for ML – Applying combinatorial testing to hyperparameter optimization (CAIN 2024) and surrogate model construction with active learning (ASE 2024)
- Synthetic Data Generation – Combining combinatorial testing with VAEs and generative models to produce diverse, distribution-faithful training data (ICSTW 2023; SN Computer Science 2026)
- Adversarial Robustness & Trustworthy ML – Probing and hardening ML systems for safety-critical deployment
Education
Ph.D. in Computer Science – Machine Learning and Artificial Intelligence
The University of Texas at Arlington
Expected August 2026
GPA: 4.0/4.0
B.S. in Software Engineering
The University of Texas at Arlington
Graduated Fall 2021
GPA: 4.0/4.0 (Summa Cum Laude)
Publications
8 publications, 58+ citations
2026
-
TabKD: Tabular Knowledge Distillation through Interaction Diversity of Learned Feature Bins
S.N. Pereira, K. Khadka, Y. Lei
International Joint Conference on Artificial Intelligence (IJCAI) 2026 (Top-tier)
-
ABLE: Using Adversarial Pairs to Construct Local Models for Explaining Model Predictions
K. Khadka, S. Shree, P. Budhathoki, Y. Lei, R. Kacker, D.R. Kuhn
32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining 2026 (Top-tier)
Achieved state-of-the-art fidelity on local explanations using novel adversarial bracketing technique
-
A Combinatorial Approach to Synthetic Data Generation for Machine Learning
K. Khadka, J. Chandrasekaran, Y. Lei, R. Kacker, D.R. Kuhn
SN Computer Science, vol. 7, no. 59, 2026
-
DD-CAM: Minimal Sufficient Explanations for Vision Models Using Delta Debugging
K. Khadka, Y. Lei, R.N. Kacker, D.R. Kuhn
arXiv preprint arXiv:2602.19274, 2026
2024
-
Constructing Surrogate Models in Machine Learning Using Combinatorial Testing and Active Learning
S. Shree, K. Khadka, Y. Lei, R.N. Kacker, D.R. Kuhn
39th IEEE/ACM International Conference on Automated Software Engineering (Top-tier), 6 citations
-
A Combinatorial Approach to Hyperparameter Optimization – Distinguished Paper Award Candidate
K. Khadka, J. Chandrasekaran, Y. Lei, R.N. Kacker, D.R. Kuhn
IEEE/ACM 3rd International Conference on AI Engineering, 25 citations
-
Assessing the Degree of Feature Interactions that Determine a Model Prediction
K. Khadka, S. Shree, Y. Lei, R.N. Kacker, D.R. Kuhn
IEEE International Conference on Software Testing, Verification and Validation Workshops, 7 citations
2023
- Synthetic Data Generation Using Combinatorial Testing and Variational Autoencoder
K. Khadka, J. Chandrasekaran, Y. Lei, R.N. Kacker, D.R. Kuhn
IEEE International Conference on Software Testing, Verification and Validation Workshops, 18 citations
Experience
Co-Founder & CTO
Bhasha Tech, Inc. – Bhasha Language Learning App
January 2025 – Present | Dallas, TX
- Co-founded and launched Bhasha, an AI-powered language learning platform now serving 50,000+ users across 130+ countries
- Shipped the iOS and Android apps, with LLM-driven personalized instruction and adaptive learning paths
- Built the end-to-end ML pipeline for speech recognition, pronunciation feedback, and conversational AI tutoring
- Operated production infrastructure across LLM, speech-recognition, and chat services, holding response latency steady as the user base scaled past 50k
Guest Lecturer – Introduction to Machine Learning
Winston-Salem State University
November 2025 | Winston-Salem, NC
- Delivered a 2-week lecture series on Introduction to Machine Learning for undergraduate students
- Covered foundational ML concepts including supervised/unsupervised learning, neural networks, and practical applications
Graduate Research Assistant
The University of Texas at Arlington
May 2022 – Present | Arlington, TX
- Pioneered ABLE (Adversarial Boundary Local Explanations), constructing local surrogate models from adversarial pairs to improve fidelity over LIME/SHAP baselines – accepted to KDD 2026
- Designed DD-CAM, a delta-debugging procedure that extracts minimal sufficient pixel sets driving CNN and Vision Transformer predictions (arXiv 2026)
- Developed combinatorial testing approaches for synthetic data generation using VAEs and GANs, improving data diversity while maintaining distributional fidelity (ICSTW 2023, SN Computer Science 2026); co-authored TabKD for tabular knowledge distillation via interaction diversity across learned feature bins (IJCAI 2026)
- Collaborating with NIST researchers (Dr. Rick Kuhn, Dr. Raghu Kacker) on integrating combinatorial testing into AI standards and trustworthy-ML guidance
Graduate Teaching Assistant – Software Testing
The University of Texas at Arlington
January 2022 – May 2022 | Arlington, TX
- Delivered lectures on software testing methodologies, including static analysis (SonarQube) and automation (Selenium)
- Mentored 40+ students on testing frameworks, code quality, and CI/CD best practices
Machine Learning Software Developer Intern
State Farm – Life Fit Project
January 2021 – August 2021 | Richardson, TX
- Designed ML pipeline generating health risk scores using K-Means clustering on Fitbit API data for insurance underwriting
- Improved model accuracy from 78% to 93% by implementing GAN-based data augmentation for imbalanced classes
- Deployed scalable backend using AWS (Lambda, SageMaker, EC2, S3, Cognito) serving 10K+ daily predictions
Technical Skills
- Machine Learning: PyTorch, TensorFlow, scikit-learn, XGBoost, Transformers, CNNs, GANs, VAEs, SHAP, LIME
- Programming: Python, R, C/C++, Java, JavaScript, SQL, Shell Scripting
- Cloud & MLOps: AWS (SageMaker, Lambda, EC2, S3), Docker, Git, MLflow, Weights & Biases
- Data & Visualization: Pandas, NumPy, Matplotlib, Seaborn, Tableau, MySQL, PostgreSQL
Honors & Awards
- Hesed Endowed Scholarship Fund Award – UTA College of Engineering (2026)
- Cyneta Networks Outstanding Graduate Teaching Assistant Award – UTA College of Engineering (2026)
- MavPitch Competition Winner – $15,000 Award (2025)
- Distinguished Paper Award Candidate – IEEE/ACM CAIN 2024
- Summa Cum Laude – B.S. Software Engineering, UTA (2021)
