Sotabase

Career

· Co-founder/AI, Rox2024–
· ML Engineering Intern, Predibase2021–2021
· Doctoral Candidate, Stanford University2021–
· Doctor of Philosophy - PhD, Computer Science, Stanford University2021–
· Intern, Sequoia Capital2020–2020
· Intern, Palo Alto Networks2019–2019
· Product Research Intern, Genies, Inc.2017–2017
· Bachelor of Science - BS with Honors, Computer Science, Stanford University2017–2021
· Research Intern, Stanford University School of Medicine2015–2016
· Intern, Altair2014–2014
· Intern, Swarm Fund2014–2016
· High School Diploma, Palo Alto High School

Publications (24)

On the Opportunities and Risks of Foundation Models
arXiv.org · 2021
5,795
cited
Can Foundation Models Wrangle Your Data?
Proceedings of the VLDB Endowment · 2022
290
cited
Ask Me Anything: A simple strategy for prompting language models
International Conference on Learning Representations · 2022
256
cited
Language Models Enable Simple Systems for Generating Structured Views of Heterogeneous Data Lakes
Proceedings of the VLDB Endowment · 2023
137
cited
Perfectly Balanced: Improving Transfer and Robustness of Supervised Contrastive Learning
International Conference on Machine Learning · 2022
58
cited
Rekall: Specifying Video Events using Compositions of Spatiotemporal Labels
arXiv.org · 2019
51
cited
Automating the Enterprise with Foundation Models
Proceedings of the VLDB Endowment · 2024
20
cited
TART: A plug-and-play Transformer module for task-agnostic reasoning
Neural Information Processing Systems · 2023
16
cited
Neural, Neural Everywhere: Controlled Generation Meets Scaffolded, Structured Dialogue ∗
2021
14
cited
Minions: Cost-efficient Collaboration Between On-device and Cloud Language Models
International Conference on Machine Learning · 2025
12
cited
Personalized Benchmarking with the Ludwig Benchmarking Toolkit
NeurIPS Datasets and Benchmarks · 2021
11
cited
WONDERBREAD: A Benchmark for Evaluating Multimodal Foundation Models on Business Process Management Tasks
Neural Information Processing Systems · 2024
9
cited
Neural Generation Meets Real People: Building a Social, Informative Open-Domain Dialogue Agent
SIGDIAL Conferences · 2022
7
cited
Cookbook: A framework for improving LLM generative abilities via programmatic data generating templates
arXiv.org · 2024
4
cited
Do Multimodal Foundation Models Understand Enterprise Workflows? A Benchmark for Business Process Management Tasks
arXiv.org · 2024
4
cited
Intelligence per Watt: Measuring Intelligence Efficiency of Local AI
arXiv.org · 2025
4
cited
An Information Theoretic Perspective on Agentic System Design
arXiv.org · 2025
2
cited
Applying Transformer-based Sequence Modeling to ECG Data
2021
DAMsL: A meta-learning based approach for dialogue state tracking
2020
Elastic Weight Consolidation for Reduction of Catastrophic Forgetting in GPT-2
2022
Sotabase
Avanika Narayan | Researcher Profile | Sotabase | Sotabase