I am an Assistant Professor in the Computer Science Department at Carnegie Mellon University. I am also affiliated with the Machine Learning Department.
I aim to advance our scientific understanding of frontier models. I am particularly interested in uncovering the root causes of their failures and designing principled approaches to improve their reliability and safety.
I wrote a short post about our group’s recent work presented at
ICML 2025 sharing what we explored, what we learned, and a bit of behind-the-scenes context.
Read it here:
Aditi Raghunathan's group at ICML 2025
I received my PhD from Stanford University in 2021 where I was fortunate to be advised by Percy Liang. My thesis won the Arthur Samuel Best Thesis Award at Stanford. Previously, I obtained my BTech in Computer Science from IIT Madras in 2016.
If you are a current CMU undergraduate or masters student interested in working with my group, please apply here.
I aim to advance our scientific understanding of frontier models. I am particularly interested in uncovering the root causes of their failures and designing principled approaches to improve their reliability and safety.
Our recent results have revealed important blind spots that impede the efficiency of data curation and quantization. We developed new frameworks to evaluate AI agent safety, distribution shifts, and identified pitfalls in post-training defenses against jailbreaks and context fidelity.
Current focus: Checkout research highlights from my group at ICML 2025. My group is actively studying the interplay between pre-training and post-training, uncovering surprising limits to scaling, improved reasoning, creativity and privacy.
Publications
PhD advisees
Undergraduate and Master's advisees
- Taeyoun Kim
- Charles Ding
- Rishi Shah
- Jerick Shi (co-advised with Vince Conitzer)
I am fortunate to also collaborate with several masters students and PhD students at CMU who I do not directly advise.
Alumni
- Tanishq Kumar (now PhD student at Stanford)
- Suhas Kotha (MS 2024, now PhD student at Stanford)
- Janet Hsieh (MS 2024, now software engineer at Syllo)
- Aman Mehra (MS 2024, will be PhD student at MILA)
- Erik Jones (MS 2020, now PhD student at Berkeley)
