Harsha Nori

Research Engineer, Microsoft

Joined

July 2019

Names

Harsha Nori

Emails

****@live.com (Confirmed)

,

****@microsoft.com

Personal Links

Career & Education History

Research Engineer

Microsoft (microsoft.com)

2016 – Present

Advisors, Relations & Conflicts

No relations added

Expertise

Interpretability

Present

Differential Privacy

Present

Publications

GAMformer: Bridging Tabular Foundation Models and Interpretable Machine Learning
Andreas C Mueller, Julien Siems, Harsha Nori, David Salinas, Arber Zela, Rich Caruana, Frank Hutter
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
Steering Language Model Refusal with Sparse Autoencoders
Kyle O'Brien, David Majercak, Xavier Fernandes, Richard G. Edgar, Blake Bullwinkel, Jingya Chen, Harsha Nori, Dean Carignan, Eric Horvitz, Forough Poursabzi-Sangdeh
- ICML 2025 R2-FM Workshop Poster
- Readers: Everyone
JSONSchemaBench: Evaluating Constrained Decoding with LLMs on Efficiency, Coverage and Quality
Saibo Geng, Hudson Cooper, Michal Moskal, Samuel Jenkins, Julian Berman, Nathan Ranchin, Robert West, Eric Horvitz, Harsha Nori
- ES-FoMo III
- Readers: Everyone
GAMformer: In-Context Learning for Generalized Additive Models
Andreas C Mueller, Julien Siems, Harsha Nori, David Salinas, Arber Zela, Rich Caruana, Frank Hutter
- Submitted to ICLR 2025
- Readers: Everyone
GAMformer: Exploring In-Context Learning for Generalized Additive Models
Andreas C Mueller, Julien Siems, Harsha Nori, David Salinas, Arber Zela, Rich Caruana, Frank Hutter
- TRL @ NeurIPS 2024 Poster
- Readers: Everyone
GAMformer: Exploring In-Context Learning for Generalized Additive Models
Andreas C Mueller, Julien Siems, Harsha Nori, Rich Caruana, Frank Hutter
- IAI Workshop @ NeurIPS 2024
- Readers: Everyone
Elephants Never Forget: Memorization and Learning of Tabular Data in Large Language Models
Sebastian Bordt, Harsha Nori, Vanessa Cristiny Rodrigues Vasconcelos, Besmira Nushi, Rich Caruana
- COLM
- Readers: Everyone
Differentially Private Synthetic Data via Foundation Model APIs 2: Text
Chulin Xie, Zinan Lin, Arturs Backurs, Sivakanth Gopi, Da Yu, Huseyin A Inan, Harsha Nori, Haotian Jiang, Huishuai Zhang, Yin Tat Lee, Bo Li, Sergey Yekhanin
- SeT LLM @ ICLR 2024
- Readers: Everyone
Differentially Private Synthetic Data via Foundation Model APIs 2: Text
Chulin Xie, Zinan Lin, Arturs Backurs, Sivakanth Gopi, Da Yu, Huseyin A Inan, Harsha Nori, Haotian Jiang, Huishuai Zhang, Yin Tat Lee, Bo Li, Sergey Yekhanin
- ICML 2024 Spotlight
- Readers: Everyone
Elephants Never Forget: Testing Language Models for Memorization of Tabular Data
Sebastian Bordt, Harsha Nori, Rich Caruana
- TRL @ NeurIPS 2023 Poster
- Readers: Everyone

View all 16 publications

Co-Authors

View all 50 co-authors