I am a fourth-year PhD student in Computer Science at Stanford University,
co-advised by Prof. Jure Leskovec
and Prof. Carlos Guestrin.
Before this,
I spent a lovely year learning under
Prof. Zachary Lipton
as a visiting researcher at Carnegie Mellon University (CMU).
I did my undergrad in CS at IIT Delhi,
where I was the President's Gold Medalist for the class of 2022.
I am a machine learning (ML) researcher.
My current focus is artificial intelligence (AI) for structured data
—
building AI models and systems that can understand and reason about
tabular, relational and time-series data
to solve complex decision-making, forecasting and recommendation challenges
(e.g., see this).
In general,
I find myself drawn to all things deep learning,
including but not limited to
data, scaling, architecture, long-context and multi-modality.
Stimulating chats with interesting folks
are a highlight of my life —
please feel free to reach out!
publications
(* denotes equal contribution)
TokenGate: Adapting LLMs for Fast and Memory-Efficient Prefill with Learned Token Pruning
Liana Patel, Rishabh Ranjan, Ion Stoica, Matei Zaharia, Carlos Guestrin arXiv 2026 paper
| arxiv
| github
| cite
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, Jure Leskovec NeurIPS 2026 Foundation Models for Structured Data (FMSD) Workshop, ICML 2026 (early version) Graph Foundation Models (GFM) Workshop, ICML 2026 (early version) paper
| arxiv
| github
| website
| cite
Advancing Open and Reproducible Relational Learning: RelArena-α, TabPFN-Rel and RPI
Adrian Hayler, Klemens Flöge, Alan Arazi, Rishabh Ranjan, Jure Leskovec,
Lennart Purucker, Frank Hutter, Noah Hollmann, and the Prior Labs Team arXiv 2026 paper
| arxiv
| github
| cite
PluRel: Synthetic Data unlocks Scaling Laws for Relational Foundation Models
Vignesh Kothapalli, Rishabh Ranjan, Valter Hudovernik, Vijay Prakash Dwivedi, Johannes Hoffart,
Carlos Guestrin, Jure Leskovec ICML 2026 paper
| arxiv
| github
| website
| cite
RelBench v2: A Large-Scale Benchmark and Repository for Relational Data
Justin Gu, Rishabh Ranjan, Charilaos Kanatsoulis, Haiming Tang, Martin Jurkovic, Valter Hudovernik, Mark Znidar,
Pranshu Chaturvedi, Parth Shroff, Fengyu Li, Jure Leskovec 3rd Workshop on Navigating and Addressing Data Problems for Foundation Models (DATA-FM), ICLR 2026 paper
| arxiv
| github
| website
| cite
Relational Transformer: Toward Zero-Shot Foundation Models for Relational Data Rishabh Ranjan, Valter Hudovernik, Mark Znidar, Charilaos Kanatsoulis, Roshan Upendra, Mahmoud Mohammadi, Joe Meyer, Tom Palczewski, Carlos Guestrin, Jure Leskovec ICLR 2026 [Oral]AI for Tabular Data (AI4TD) Workshop, NeurIPS 2025 (early version) paper
| arxiv
| github
| x thread
| cite
RelBench: A Benchmark for Deep Learning on Relational Databases Rishabh Ranjan*, Joshua Robinson*, Weihua Hu*, Kexin Huang*, Jiaqi Han, Alejandro Dobles, Matthias Fey, Jan E. Lenssen, Yiwen Yuan, Zecheng Zhang, Xinwei He, Jure Leskovec NeurIPS 2024 paper
| arxiv
| github
| website
| cite
Post-Hoc Reversal: Are We Selecting Models Prematurely? Rishabh Ranjan, Saurabh Garg, Mrigank Raman, Carlos Guestrin, Zachary Lipton NeurIPS 2024 paper
| arxiv
| github
| cite
Position: Relational Deep Learning - Graph Representation Learning on Relational Databases
Matthias Fey*, Weihua Hu*, Kexin Huang*, Jan Eric Lenssen*, Rishabh Ranjan*, Joshua Robinson*, Rex Ying, Jiaxuan You, Jure Leskovec ICML 2024 paper
| arxiv
| github
| website
| cite
A Solver-Free Framework for Scalable Learning in Neural ILP Architectures
Yatin Nandwani*, Rishabh Ranjan*, Mausam, Parag Singla NeurIPS 2022 paper
| arxiv
| github
| cite
GREED: A Neural Framework for Learning Graph Distance Functions Rishabh Ranjan, Siddharth Grover, Sourav Medya, Venkatesan Chakaravarthy, Yogish Sabharwal, Sayan Ranu NeurIPS 2022 paper
| arxiv
| github
| cite
Exploiting Epochs and Symmetries in Analysing MPI Programs Rishabh Ranjan, Ishita Agrawal, Subodh Sharma ASE 2022 paper
| github
| talk
| cite
Legend:
AI4TD
AI for Tabular Data (Workshop)
ASE
IEEE/ACM International Conference on Automated Software Engineering
DATA-FM
Data for Foundation Models (Workshop)
FMSD
Foundation Models for Structured Data (Workshop)
GFM
Graph Foundation Models (Workshop)
ICLR
International Conference on Learning Representations
