Scholar
Aditya Taparia
Google Scholar ID: hfU1wQwAAAAJ
Ph.D. student at Arizona State University
Citations & Impact
Citations
32
H-index
4
i10-index
1
Publications
11
Co-authors
13
list available
Publications
Resume (English only)
Academic Achievements
- Paper 'BaTCAVe: Trustworthy Explanations for Robot Behaviors' accepted to IROS'25; paper 'Explainable Concept Generation through Vision-Language Preference Learning for Understanding Neural Networks' Internal Representations' accepted to ICML'25; paper 'Failures Are Fated, But Can Be Faded: Characterizing and Mitigating Unwanted Behaviors in Large-Scale Vision and Language Models' accepted to ICML'24 as a spotlight-designated paper (top 3.5%); presented four workshop papers at NeurIPS'24.
Research Experience
- Joining Lawrence Livermore National Laboratory as a Student Research Intern in MIG group starting August 2025; joined Arizona State University as a Masters student in Computer Science in August 2023.
Education
- PhD student in Computer Science at Arizona State University, advised by Prof. Ransalu Senanayake; affiliated with the Laboratory for Learning Evaluation and Naturalization of Systems (LENS Lab); completed Bachelors with Honors in Computer Science from the Indian Institute of Information Technology (IIIT), Kottayam.
Background
- Research interests center on the conceptual foundations of neural networks—exploring how models form, refine, and leverage high-level abstractions or “concepts” to learn effectively and make informed decisions. Aiming to develop concept-driven AI systems that are more robust, adaptable, and capable of handling distribution shifts in evolving real-world environments. By grounding learning and decision-making in explicit concepts, seeking to improve model's interpretability, generalization, and optimize AI-driven decision processes.
Miscellany
- Always happy to connect about research, collaborate on ideas, or share advice. Feel free to get in touch!
