Aditeya Baral

MSCS @ NYU Courant & CDS | NLP @ NYU CILVR

prof_pic.jpg

New York, NY

I am a Masters in Computer Science student at New York University’s Courant Institute of Mathematics, Computing and Data Science, where I am advised by Tal Linzen, Shauli Ravfogel, and Jackson Petty at the CILVR lab.

I am interested in the principles underlying how machines learn, understand, and reason with language. My research primarily focuses on representation learning, reasoning, and mechanistic interpretability, with an emphasis on studying the training and inference dynamics of language models — how they encode and represent knowledge, apply it to solve tasks, and how we can control and interpret their internal representations.

If you’d like to chat about NLP or ML research, get advice on graduate school applications, or are looking for mentoring, I’m always happy to hear from you — just drop me an email!

On this site, you may find my research, courses I’ve assisted, and talks I’ve given.

news

Apr 26, 2026 Paper titled “Training for Compositional Sensitivity Reduces Dense Retrieval Generalization” accepted at the Sci4DL Workshop, ICLR 2026.
Dec 16, 2025 Poster titled “When ‘+’ Means ‘-’ – Probing Arithmetic Circuits Under Symbol Redefinition” presented at NYU.
Jun 09, 2025 Started interning as an Applied Research Scientist Intern at Redis as part of the Redis LangCache team.
May 21, 2025 Preprint titled “Can LLMs understand Math? – Exploring the Pitfalls in Mathematical Reasoning” released on arXiv.
May 19, 2025 Preprint titled “CMLFormer: A Dual Decoder Transformer with Switching Point Learning for Code-Mixed Language Modeling” released on arXiv.
May 14, 2025 Poster titled “Patch and Control: Steering Behavior of Large Vision-Language Models via Latent Activations” presented at NYU.
Apr 01, 2025 Started working as a Research Assistant at the Computation and Psycholinguistics lab at New York University, where I am advised by Jackson Petty and Tal Linzen.
Apr 01, 2025 Started working as a Research Assistant at the Computational Intelligence, Vision, and Robotics lab at New York University, where I am advised by Shauli Ravfogel and Tal Linzen.
Sep 03, 2024 Started my Masters in Computer Science at New York University’s Courant Institute of Mathematics, Computing and Data Science.
Jul 01, 2023 Paper titled “ChatBERT - Multi-task approach to Pre-Training for Structured Conversations” published internally at Cisco Webex AI.
Jul 10, 2022 Started working full-time as a Big Data and Applied AI Engineer at Cisco Webex as part of the Media Quality Analytics team.
Mar 21, 2022 Paper titled “CalBERT – Code-Mixed Adaptive Language Representations Using BERT” accepted at the MAKE Symposium, AAAI 2022.
Jan 01, 2022 Started interning as a Big Data Engineering Intern at Cisco Webex as part of the VideoMesh Analytics team.
Dec 12, 2021 Paper titled “Information Maximization to Overcome Catastrophic Forgetting in Few-Shot Object Detection” published internally at Intel VSG.
Nov 12, 2021 Paper titled “MAPLE – MAsking words to generate blackout Poetry using sequence-to-sequence LEarning” accepted at ACL ICNLSP 2021.
Aug 04, 2021 Paper titled “Analysis of Kepler Objects of Interest using Machine Learning for Exoplanet Identification” accepted at IEEE CONIT 2021.
Aug 01, 2021 Started working as an Applied Research Scientist Intern at Intel VSG, India, where I am advised by Dr. Anbumani Subramanian and Anay Majee.
May 01, 2020 Started working as a Research Assistant at the Center for Cloud Computing & Big Data at PES University, where I am advised by Dr. KV Subramaniam.
Aug 01, 2018 Started my Bachelors of Technology at PES University’s Department of Computer Science and Engineering.