NOW Staff Research Scientist, Google DeepMind.
Senior Research Scientist, Google Brain.
Postdoctoral researcher at Microsoft Research.
Intern at Microsoft Research in DMX.
Contact: azade at google dot com
Embedded Files
Recent Publications: [Full list of publication]
Xinran Zhao, Hanie Sedghi, Bernd Bohnet, Dale Schuurmans, Azade Nova, Improving Large Language Model Planning with Action Sequence Similarity, ICLR 2025.
[Core Contributor] Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context, 2024, Paper
Azade Nova, Bernd Bohnet, Aaron T Parisi, Kevin Swersky, Katayoon Goshvadi, Hanjun Dai, Dale Schuurmans, Noah Fiedel, Hanie Sedghi, Exploring and Benchmarking the Planning Capabilities of Large Language Models, 2024
Huaixiu Steven Zheng, Swaroop Mishra, Hugh Zhang, Xinyun Chen, Minmin Chen, Azade Nova, Le Hou, Heng-Tze Cheng, Quoc V Le, Ed H Chi, Denny Zhou, NATURAL PLAN: Benchmarking LLMs on Natural Language Planning, 2024, Paper
Hanjun Dai, Bethany Yixin Wang, Xingchen Wan, Bo Dai, Sherry Yang, Azade Nova, Pengcheng Yin, Phitchaya Mangpo Phothilimthana, Charles Sutton, Dale Schuurmans, UQE: A Query Engine for Unstructured Databases, NeurIPS 2024
Training language models on the knowledge graph: Insights on hallucinations and their detectability, 2024
Azade Nova, Hanjun Dai, Dale Schuurmans. Gradient-Free Structured Pruning with Unlabeled Data, ICML 2023, Paper
Haoran Sun, Katayoon Goshvadi, Azade Nova, Dale Schuurmans, Hanjun Dai. Revisiting Sampling for Combinatorial Optimization, ICML 2023, Paper
Katayoon Goshvadi, Haoran Sun, Xingchao Liu, Azade Nova, Ruqi Zhang, Will Sussman Grathwohl, Dale Schuurmans, Hanjun Dai. DISCS: A Benchmark for Discrete Sampling, appears in NeurIPS 2023 Datasets and Benchmarks.
Hattie Zhou, Azade Nova, Hugo Larochelle, Aaron Courville, Behnam Neyshabur, Hanie Sedghi. Teaching Algorithmic Reasoning via In-Context Learning, In submission, [arXiv, blogpost]
Ian Swift, Sana Ebrahimi, Azade Nova, Abolfazl Asudeh. Maximizing Fair Content Spread via Edge Suggestion in Social Networks. VLDB 2022, VLDB Endowment. Paper, arxiv
Abolfazl Asudeh, G. Das, H.V. Jagadish, Shangqi Lu, Azade Nazi, Yufei Tao, Jianwen Zhao, N. Zhang. On Finding Rank Regret Representatives. ACM TODS, 2022. Paper
Azade Nazi, Qijing Huang, Hamid Shojaei, Hodjat Asghari Esfeden, Azalia Mirhosseini, Richard Ho. Adaptive Test Generation for Fast Functional Coverage Closure. DVCON 2021. Paper, Presentation
Qijing Huang, Hamid Shojaei, Fred Zyda, Azade Nazi, Shobha Vasudevan, Sat Chatterjee, Richard Ho. Test Parameter Tuning with Blackbox Optimization: A Simple Yet Effective Way to Improve Coverage. DVCON 2021.
A graph placement methodology for fast chip design. 2021 Nature and Opinion Piece.
Hanjun Dai, Azade Nazi, Yujia Li, Bo Dai, and Dale Schuurmans. Scalable Deep Generative Modeling for Sparse Graphs in ICML 2020. Paper
News and Highlights:
Our work on deep reinforcement learning for chip floorplanning was published in Nature and used in production to design next generation Google TPUs, with potential to save thousands of hours of engineering effort for each next generation. (Nature and Opinion Piece).
I have joined Google Brain as a Research Scientist.
I have joined Google AI as an AI Resident.
I have joined DMX group at Microsoft Research as a post-doc researcher.
I will be interning with the DMX group at Microsoft Research Seattle during Summer 2016.
Our demo paper "AD-WIRE: Add-on for Web Item Reviewing System", has been accepted in VLDB 2016.
Awarded "Outstanding Doctoral Student" at 2016 College of Engineering Academic Excellence Ceremony.
I will be interning with the DMX group at Microsoft Research Seattle during Summer 2015.
Our paper "The TagAdvisor: Luring the Lurkers to Review Web Items" has been accepted in SIGMOD 2015.
Our paper "Walk, Not Wait: Faster Sampling Over Online Social Networks" has been accepted in PVLDB 2015.
Our paper "Answering Complex Queries in an Online Community Network" has been accepted as a short paper in ICWSM 2015.
Our paper "Querying Hidden Attributes in Social Networks" has been accepted at Workshop on Intelligent Data Processing (IDP 2014), collocated with ICDM 2014.
Page updated
Google Sites
Report abuse