Anuj Kumar
Research Scholar
Indian Institute of Technology (IIT) Jammu
Jammu - 181221, India
Currently: Visiting Researcher at Natural Language Processing Laboratory (Watanabe Laboratory) at the Division of Information Science, Nara Institute of Science and Technology., Japan
About Me
I am a Ph.D. candidate in Computer Science & Engineering at Indian Institute of Technology (IIT) Jammu, advised by Dr. Yamuna Prasad and Prof. Virendra Singh. My research focuses on Natural Language Processing, Large Language Models (LLMs), Neuro-symbolic AI, and Explainable AI.
I completed my Master's degree in Computer Science & Engineering from IIT Jammu and my Bachelor's degree from K.K. Wagh Institute of Engineering Education and Research, Nashik.
Research Interests: LLM, Neuro-symbolic AI, Natural language reasoning, Explainable AI, Knowledge Graphs, Unsupervised Learning, Deep Learning
My Journey
I began my academic path with a Bachelor's degree in Computer Science & Engineering from K.K. Wagh Institute of Engineering Education and Research, Nashik, where I developed a strong foundation in programming and computational thinking. It was during these undergraduate years that I first encountered the rapidly evolving world of Artificial Intelligence — and I was captivated. The idea that machines could learn, reason, and make decisions from data felt like the most exciting frontier in science and technology.
Driven by this curiosity, I pursued a Master of Technology in Computer Science & Engineering at the Indian Institute of Technology (IIT) Jammu, where I immersed myself in machine learning, data science, and intelligent systems. It was here, while working on my Master's thesis on cross-lingual entity alignment in Knowledge Graphs, that I had my defining encounter with Natural Language Processing. The depth and complexity of human language — and the challenge of teaching machines to truly understand it — drew me in completely and set the direction for everything that followed.
That passion for NLP led me to pursue a PhD at IIT Jammu under the guidance of Dr. Yamuna Prasad and Prof. Virendra Singh (IIT Bombay). My doctoral research explores Large Language Models, low-resource and multilingual NLP, Knowledge Graphs, Explainable AI, and Neuro-symbolic approaches — questions that sit at the intersection of language, reasoning, and machine understanding.
I am currently a Visiting Researcher at the Natural Language Processing Laboratory (Watanabe Laboratory), Division of Information Science, Nara Institute of Science and Technology (NAIST), Japan. This visit is supported by the LOTUS Program by the Japan Science and Technology Agency (JST), which fosters research collaboration between India and Japan. This international experience has broadened my perspective and deepened my commitment to advancing NLP research at a global level.
Recent Updates
- Oct 2026 Paper accepted at EMNLP 2026 — How Reliable are AMR Parser Outputs? Uncertainty Estimation for AMR Parsing
- Jul 2026 Paper accepted at Computers and Electrical Engineering — PSO–GP: An evolutionary optimization-based activation function approximation for hardware efficient neural network
- Jul 2026 Paper accepted at TMLR 2026 — You Only Prune Once: A Zero-Shot, Data-Free Pruning at Initialization via Low-Rank Residual Saliency
- Jul 2026 Paper accepted at TMLR 2026 — You Only Prune Once: A Zero-Shot, Data-Free Pruning at Initialization via Low-Rank Residual Saliency
- Jul 2026 Paper published at ACL 2026 — Revisiting Evaluation of Question Answering Systems in Low-Resource Indic Languages: Bridging Human and Metric Alignment
- Jun 2026 Journal paper published in Language Resources and Evaluation — ToxicBias-Reasoning: A Multicultural Dataset for Social Bias Detection with Human-Aligned Reasoning
- Mar 2026 Started as Visiting Researcher at NAIST, Japan under the LOTUS Program by JST
- Nov 2025 Paper accepted at EMNLP 2025 — MarathiEmoExplain: A Dataset for Sentiment, Emotion, and Explanation in Low-Resource Marathi
- Nov 2025 Paper accepted at AACL 2025 — LRMGS: A Language-Robust Metric for Evaluating Question Answering in Very Low-Resource Indic Languages
- Jan 2025 Volunteered at COLING 2025, Abu Dhabi — 31st International Conference on Computational Linguistics