Aakanksha Chowdhery (original) (raw)

Adjunct Professor (Stanford) & Researcher (Reflection AI)

I am pushing the frontier of agentic LLMs by leveraging RL techniques to enable autonomous self-improving agents, especially in software engineering at the startup Reflection AI.

At Stanford, I am co-teaching CS329A (Self-Improving AI agents) in Fall/Winter 2025 and I am the Program Chair for MLSys 2026.

Before this, I was the technical Lead of 540B PaLM model and lead researcher in Gemini at Google in pre-training, scaling, and finetuning of Large Language Models. I was also a core contributor in PaLM-E, MedPaLM, and Pathways project at Google. Prior to joining Google, I was technical lead for several interdisciplinary research initiatives at Microsoft Research and Princeton University across machine learning and distributed systems.

I completed my PhD in Electrical Engineering from Stanford University and was awarded the Paul Baran Marconi Young Scholar Award for the outstanding scientific contributions of my dissertation in the field of communications and Internet.

Selected Honors & Awards: Outstanding Paper Award MLSys 2023, Outstanding Paper Award MLSys 2022, Paul Baran Marconi Young Scholar Award 2012.

Selected

Publications

MACHINE LEARNING

Gemini Team et al, “Gemini: A Family of Highly Capable Multimodal Models,” arXiv preprint arXiv:2312.11805, Dec 2023.
A. Chowdhery, S. Narang, J. Devlin, et al, “PaLM: Scaling Language Modeling with Pathways,” Journal of Machine Learning Research (JMLR), 2023.
H. W. Chung, L. Hou, J. Wei, et al, “Scaling instruction-finetuned language models,” Journal of Machine Learning Research (JMLR), 2024.
D. Driess, F. Xia, P. Florence et al, “PaLM-E: An Embodied Multimodal Language Model,” International Conference on Machine Learning (ICML), 2023.
K. Singhal, S. Azizi, et al “Large language models encode clinical knowledge”, Nature 620, 172–180 (2023).
X. Wang, J. Wei, et al, “Self-consistency improves chain of thought reasoning in language models”, International Conference on Learning Representations (ICLR), 2023.
S. Jaszczur, A. Chowdhery, A. Mohiuddin, L. Kaiser, W. Gajewski, H. Michalewski, and J. Kanerva, “Sparse is Enough in Scaling Transformers,” NeurIPS 2021.
H. Hazimeh, Z. Zhao, A. Chowdhery, M. Sathiamoorthy, et al, “Dselect-k: Differentiable selection in the mixture of experts with applications to multi-task learning,” NeurIPS 2021.

SYSTEMS

R. Pope, S. Douglas, A. Chowdhery, et al, “Efficiently scaling transformer inference,” Proceedings of Machine Learning and Systems (MLSys), 2023, Outstanding Paper Award.
P. Barham, A. Chowdhery, J. Dean, S. Ghemawat, S. Hand, D. Hurt, M. Isard, H. Lim, R. Pang, S. Roy, R. Sepassi et al, “Pathways: Asynchronous Distributed Dataflow for ML,” Proceedings of Machine Learning and Systems (MLSys), 2022, Outstanding Paper Award.
Y. Lu, A. Chowdhery, S. Kandula, and S. Chaudhuri, “Accelerating Machine Learning Queries with Probabilistic Predicates,” ACM SIGMOD 2018.
Y. Lu, A. Chowdhery, and S. Kandula, “Optasia: A Relational Platform for Efficient Large-Scale Video Analytics,” ACM Symposium on Cloud Computing (SoCC), Santa Clara, CA, 2016.

Recent

Talks

Stanford CS 528 Talk on Multimodal Reasoning: Gemini & PaLM-E 2024 (YouTube)

Invited talks at ICLR 2023, ICML 2023 and NeurIPS 2022 workshops

Keynote Panelist at NeurIPS 2023 Panel on “Beyond Scaling”

Keynote Speaker at PIMRC 2023 and ITA 2023

Keynote Speaker at Department of Energy Advanced Scientific Computing Research Meeting 2024

Berkeley CS 294 Talk on Scaling Large Language Models 2023

Aakanksha Chowdhery (original) (raw)

Selected

Gemini Team et al, “Gemini: A Family of Highly Capable Multimodal Models,” arXiv preprint arXiv:2312.11805, Dec 2023.

A. Chowdhery, S. Narang, J. Devlin, et al, “PaLM: Scaling Language Modeling with Pathways,” Journal of Machine Learning Research (JMLR), 2023.

H. W. Chung, L. Hou, J. Wei, et al, “Scaling instruction-finetuned language models,” Journal of Machine Learning Research (JMLR), 2024.

D. Driess, F. Xia, P. Florence et al, “PaLM-E: An Embodied Multimodal Language Model,” International Conference on Machine Learning (ICML), 2023.

K. Singhal, S. Azizi, et al “Large language models encode clinical knowledge”, Nature 620, 172–180 (2023).

X. Wang, J. Wei, et al, “Self-consistency improves chain of thought reasoning in language models”, International Conference on Learning Representations (ICLR), 2023.

S. Jaszczur, A. Chowdhery, A. Mohiuddin, L. Kaiser, W. Gajewski, H. Michalewski, and J. Kanerva, “Sparse is Enough in Scaling Transformers,” NeurIPS 2021.

H. Hazimeh, Z. Zhao, A. Chowdhery, M. Sathiamoorthy, et al, “Dselect-k: Differentiable selection in the mixture of experts with applications to multi-task learning,” NeurIPS 2021.

R. Pope, S. Douglas, A. Chowdhery, et al, “Efficiently scaling transformer inference,” Proceedings of Machine Learning and Systems (MLSys), 2023, Outstanding Paper Award.

P. Barham, A. Chowdhery, J. Dean, S. Ghemawat, S. Hand, D. Hurt, M. Isard, H. Lim, R. Pang, S. Roy, R. Sepassi et al, “Pathways: Asynchronous Distributed Dataflow for ML,” Proceedings of Machine Learning and Systems (MLSys), 2022, Outstanding Paper Award.

Y. Lu, A. Chowdhery, S. Kandula, and S. Chaudhuri, “Accelerating Machine Learning Queries with Probabilistic Predicates,” ACM SIGMOD 2018.

Y. Lu, A. Chowdhery, and S. Kandula, “Optasia: A Relational Platform for Efficient Large-Scale Video Analytics,” ACM Symposium on Cloud Computing (SoCC), Santa Clara, CA, 2016.

Recent