About
I am a 2nd Year Ph.D. student in Computer Science at the University of Pittsburgh, advised by Professor Xiang (Lorraine) Li.
Research Interests:
- Memory Editing in Large Language Models (LLMs): Developing techniques to efficiently update internal knowledge representations for better adaptability and fairness without the computational cost of full finetuning.
- Commonsense Reasoning: Tackling challenges in grounding language models to improve fairness and reliability in real-world applications.
- Fairness in AI: Investigating methods to mitigate biases in AI systems, ensuring equitable and reliable model performance across diverse user groups.
- Conversational AI and NLU: Specializing in Natural Language Understanding for enhancing conversational AI systems, including multi-intent classification, handling out-of-domain queries, and developing real-world applications like Samsung Bixby.
A major milestone in my career was leading the overhaul of the deep learning architecture for Samsung SmartThings. During this time, I worked as a Lead Engineer - NLP at the Samsung Research, where I developed solutions for NLU challenges faced by Samsung’s Conversational AI from research to commercialization.
I earned my Master's in Computer Science and Engineering from IIT Kharagpur, following a Bachelor's in Computer Science and Engineering from NIT Jalandhar.
Publications
Patents
News
Sept'24
👨🔬Started working as Graduate Reseach Assistant @ SCI, UPittAug'24
📽️Lightning Talk - "A Fairness Analysis of Human and AI-Generated Student Reflection Summaries" in Gender Bias in Natural Language Processing Workshop at ACL 2024!Jul'24
🗣️Oral invitation - "A Fairness Analysis of Human and AI-Generated Student Reflection Summaries" in Gender Bias in Natural Language Processing Workshop at ACL 2024!Jun'24
🎉Paper publication - "A Fairness Analysis of Human and AI-Generated Student Reflection Summaries" accepted in Gender Bias in Natural Language Processing Workshop at ACL 2024!Jun'24
📽️Oral presentation - "Multimodal Understanding of Memes with Fair Explanations" @ CVPR - Multimodal Learning and Applications Workshop (MULA 2024)!May'24
🗣️Oral invitation - "Multimodal Understanding of Memes with Fair Explanations" in CVPR - Multimodal Learning and Applications Workshop (MULA 2024)!Mar'24
🎉Paper publication - "Multimodal Understanding of Memes with Fair Explanations" accepted in CVPR - Multimodal Learning and Applications Workshop (MULA 2024)!Feb'24
🎉A1 US Patent published - "Method and system for mitigating physical risks in an IOT environment"Feb'24
🤩Attended Research WeekJan'24
👨🏫Started working as Teaching Assistant - Intro to Natural Language Processing @ SCI, UPittSep'23
👨🏫Started working as Teaching Assistant - Operating System @ SCI, UPittAug'23
🎓Started CS PhD @ University of Pittsburgh, PA, USAMar'23
🆙Promoted to Lead Engineer - NLP @ SRIBMar'23
🏆Received Samsung Excellence Award @ SRIBMar'23
🎉A1 US Patent published - "Methods and systems for determining missing slots associated with a voice command for an advanced voice interaction"Mar'23
🌟Received MBO High Perfromance Bonus @ SRIBSep'22-Dec'22
✈️Business trip to HQ, South KoreaEducation
Doctor of Philosophy (PhD) Computer Science
2023 - Present
University of Pittsburgh, PA, USACourses Taken
- Advanced Topics in NLP (Seminar)
- Intro to NLP
- Distributed Operating System
Master of Technology (M.Tech) Computer Science & Engineering
2017 - 2019
Indian Institute of Technology (IIT), Kharagpur, IndiaBachelor of Technology (B.Tech) Computer Science & Engineering
2013 - 2017
National Institute of Technology (NIT), Jalandhar, IndiaAcademic Experience
Teaching Assistant - Intro to Operating Systems
Sep'23 - Dec'23
University of Pittsburgh, PA, USA- Conducted weekly recitations for class of ~50 undergrad students. Graded quizes and assignments.
Teaching Assistant - Programming and Data Structure & DBMS
Jul'18 - May'19
Indian Institute of Technology (IIT), Jalandhar, India- Thought lectures on Programming & DBMS concepts to a class of 80+ undergrad students. Evaluated lab assignments and tests based on those concepts.
Professional Experience
Lead Engineer - NLP
Jun'19 - Aug'23
Samsung Research Institute, Bangalore, India- Role: Research, Design and Develop solutions for Bixby’s (Conversational AI) industry‑level NLU challenges.
- CoSMIC ‑ Contextual SmartThings Multi‑Intent Composer: Researched and commercialized BERT‑based Multi‑Intent NLU for SmartThings. Achieved 96% E2E Accuracy with 12% performance boost. Reduced the error rate by 67%.
- Conversational AI: Worked on complex scenarios of Multi‑Intent and Slot Classification, Zero-shot Out‑Of‑Domain Detection, Intelligent Device Resolution service, Bixby Recall ‑ Chat Question Answering (QA) System and Knowledge Representation.
- Achievements: Publications (x2), Patents (x4), MBO High Performance Bonus (x3), Samsung Excellence and other awards (x5), CLab Finalist
Extreme Blue Intern
May'18 - Jul'19
IBM, Bangalore, India- Project: Template based Machine Learning Models for MVS
- Designed and developed a time series forecasting, self‑learning, DL system to predict, prevent or auto‑resolve or assist in IT infrastructure Failure.
- Achievement: 2nd Runner Up ‑ Audience Poll Category, IBM Extreme Blue Expo