Vignesh Kothapalli

I am a second-year CS PhD student at Stanford University, advised by Prof. Jure Leskovec. I am interested in building foundation models over structured data (tables, databases, and graphs) and unstructured data (text). I see these models as the building blocks of continual learning systems that acquire new knowledge on the fly. My research is supported by the Stanford School of Engineering Fellowship.

In summer 2026, I interned at NVIDIA, where I worked on Kumo Tabular, a tabular foundation model. Previously I was a senior ML engineer at LinkedIn AI, building LLM-based foundation models for recommendation. I have also contributed to TensorFlow and maintained TensorFlow-IO at IBM.

I earned my MSc in Computer Science at NYU Courant, where I was advised by Prof. Joan Bruna in the Math and Data Group. I also hold a B.Tech in Electronics and Communication Engineering from IIT Guwahati.

Email / Scholar / GitHub / LinkedIn / X

Publications

RT-J: Large-Scale Pretraining of Relational Transformers for Context-Efficient Predictions

Rishabh Ranjan, Vignesh Kothapalli, Harshvardhan Agarwal, Charilaos Kanatsoulis, Roshan Upendra, Tom Palczewski, Carlos Guestrin, and Jure Leskovec

In The Fortieth Annual Conference on Neural Information Processing Systems , 2026

PDF Code Model Data Website
Memorilla: Latent Semantic Memory for LLMs

Adibvafa Fallahpour*, Parsa Idehpour*, Vignesh Kothapalli*, Nikita Mounier, Shirley Wu, Shayan Pardis, and Jure Leskovec

In COLM Workshop on Context Beyond the Window: Persistent Knowledge in Language Models , 2026

* Equal contribution

PDF Code Data Website
PluRel: Synthetic Data unlocks Scaling Laws for Relational Foundation Models

Vignesh Kothapalli, Rishabh Ranjan, Valter Hudovernik, Vijay Prakash Dwivedi, Johannes Hoffart, Carlos Guestrin, and Jure Leskovec

International Conference on Machine Learning, 2026

PDF Talk Blog Model Data Website
Distilling the Essence: Efficient Reasoning Distillation via Sequence Truncation

Wei-Rui Chen, Vignesh Kothapalli, Ata Fatahibaarzi, Hejian Sang, Shao Tang, Qingquan Song, Zhipeng Wang, and Muhammad Abdul-Mageed

In Findings of the Association for Computational Linguistics , 2026

PDF Code
To Think or Not to Think: The Hidden Cost of Meta-Training with Excessive CoT Examples

Vignesh Kothapalli, Ata Fatahibaarzi, Hamed Firooz, and Maziar Sanjabi

In Proceedings of the Association for Computational Linguistics , 2026

PDF Code Website
Balancing Learning Rates Across Layers: Exact Two-Step Dynamics and Optimal Scaling in Linear Neural Networks

Tianyu Pang, Vignesh Kothapalli, Shenyang Deng, Haohui Wang, Dawei Zhou, and Yaoqing Yang

International Conference on Machine Learning, 2026

PDF Code
Scaling Down, Serving Fast: Compressing and Deploying Efficient LLMs for Recommendation Systems

Kayhan Behdin, Ata Fatahibaarzi, Qingquan Song, Yun Dai, Aman Gupta, Zhipeng Wang, Hejian Sang, Shao Tang, Gregory Dexter, Sirou Zhu, Siyu Zhu, Tejas Dharamsi, Vignesh Kothapalli, Zhoutong Fu, Yihan Cao, Pin-Lun Hsu, Fedor Borisyuk, Natesh S. Pillai, Luke Simon, and Rahul Mazumder

In Conference on Empirical Methods in Natural Language Processing (Industry Track) , 2025

Oral PDF Code

true
CoT-ICL Lab: A Synthetic Framework for Studying Chain-of-Thought Learning from In-Context Demonstrations

Vignesh Kothapalli, Hamed Firooz, and Maziar Sanjabi

In Proceedings of the Association for Computational Linguistics , 2025

PDF Code Website
From Spikes to Heavy Tails: Unveiling the Spectral Evolution of Neural Networks

Vignesh Kothapalli, Tianyu Pang, Shenyang Deng, Zongmin Liu, and Yaoqing Yang

Transactions on Machine Learning Research, 2025

PDF
Liger-Kernel: Efficient Triton Kernels for LLM Training

Pin-Lun Hsu, Yun Dai, Vignesh Kothapalli, Qingquan Song, Shao Tang, Siyu Zhu, Steven Shimizu, Shivam Sahni, Haowen Ning, Yanning Chen, and Zhipeng Wang

Championing Open-source DEvelopment in ML Workshop @ ICML25, 2025

PDF Talk Blog Code
Can Kernel Methods Explain How the Data Affects Neural Collapse?

Vignesh Kothapalli, and Tom Tirer

Transactions on Machine Learning Research, 2025

PDF Code
A Neural Collapse Perspective on Feature Evolution in Graph Neural Networks

Vignesh Kothapalli, Tom Tirer, and Joan Bruna

Advances in Neural Information Processing Systems, 2023

PDF Code Slides
Randomized Schur Complement Views for Graph Contrastive Learning

Vignesh Kothapalli

In International Conference on Machine Learning , 2023

PDF Code
Neural Collapse: A Review on Modelling Principles and Generalization

Vignesh Kothapalli

Transactions on Machine Learning Research, 2023

PDF
Abnormal Event Detection on BMTT-PETS 2017 Surveillance Challenge

Vignesh Kothapalli, Gaurav Yadav, and Amit Sethi

In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops , 2017

PDF Code