Publications and Manuscripts
Machine Learning
DreamSync: Aligning Text-to-Image Generation with Image Understanding Feedback [arxiv], Jiao Sun, Deqing Fu, Yushi Hu, Su Wang, Royi Rassin, Da-Cheng Juan, Dana Alon, Charles Herrmann, Sjoerd van Steenkiste, Ranjay Krishna, Cyrus Rashtchian. 2023.
Benchmarking Robustness to Adversarial Image Obfuscations [arxiv, dataset], Florian Stimberg, Ayan Chakrabarti, Chun-Ta Lu, Hussein Hazimeh, Otilia Stretcu, Wei Qiao, Yintao Liu, Merve Kaya, Cyrus Rashtchian, Ariel Fuxman, Mehmet Tek, Sven Gowal.
Substance or Style: What Does Your Image Embedding Know? [arxiv], Cyrus Rashtchian, Charles Herrmann, Chun-Sung Ferng, Ayan Chakrabarti, Dilip Krishnan, Deqing Sun, Da-Cheng Juan, Andrew Tomkins. NeurIPS workshop DistShift, 2023.
Robustness and Generalization to Nearest Categories [arxiv]. Yao-Yuan Yang, Cyrus Rashtchian, Kamalika Chaudhuri, Ruslan Salakhutdinov. TMLR, 2023.
A Theoretical View on Sparsely Activiated Networks [arxiv], with Cenk Baykal, Nishanth Dikkala, Rina Panigrahy, Xin Wang. NeurIPS 2022.
Lower Bounds on the Total Variation Distance Between Mixtures of Two Gaussians [arxiv], with Sami Davies, Arya Mazumdar, Soumyabrata Pal. ALT 2022.
ExKMC: Expanding Explainable k-Means Clustering [arxiv, code], with Nave Frost and Michal Moshkovitz. 2021.
A Closer Look at Accuracy vs. Robustness [arxiv, code, blog]. Yao-Yuan Yang, Cyrus Rashtchian, Hongyang Zhang, Kamalika Chaudhuri, Ruslan Salakhutdinov. NeurIPS 2020.
Unsupervised Embedding of Hierarchical Structure in Euclidean Space [arxiv, code]. Jinyu Zhao, Yi Hao, Cyrus Rashtchian, Course Project, 2020.
Explainable k-Means and k-Medians Clustering [arxiv, blog1, blog2, animated video], with Sanjoy Dasgupta, Nave Frost, Michal Moshkovitz. ICML 2020.
Robustness for Non-Parametric Classification: A Generic Attack and Defense [arxiv, code]. Yao-Yuan Yang, Cyrus Rashtchian, Yizhen Wang, Kamalika Chaudhuri. AISTATS 2020.
Every Picture Tells a Story: Generating Sentences from Images [pdf, acm dl]. Ali Farhadi, Mohsen Hejrati, Mohammad Amin Sadeghi, Peter Young, Cyrus Rashtchian, Julia Hockenmaier, David Forsyth. European Conference on Computer Vision (ECCV), 2010
Cross-Caption Coreference Resolution for Automatic Image Understanding [pdf, acm dl]. Micah Hodosh, Peter Young, Cyrus Rashtchian, Julia Hockenmaier. Conference on Natural Language Learning (CoNLL), 2010
Collecting Image Annotations Using Amazon's Mechanical Turk [pdf, acm dl]. Cyrus Rashtchian, Peter Young, Micah Hodosh, Julia Hockenmaier. NAACL HLT 2010 Workshop on Creating Speech and Language Data with Amazon's Mechanical Turk
Algorithms
Average-Case Communication Complexity of Statistical Problems [arxiv], with David P. Woodruff, Peng Ye, Hanlin Zhu. COLT 2021.
Approximate Trace Reconstruction [arxiv], with Sami Davies, Miklos Z. Racz, Benjamin Schiffer. ISIT 2021.
Vector-Matrix-Vector Queries for Solving Linear Algebra, Statistics, and Graph Problems [arxiv, animated video], with David P. Woodruff and Hanlin Zhu. RANDOM 2020.
LSF-Join: Locality Sensitive Filtering for Distributed All-Pairs Set Similarity Under Skew [arxiv], with Aneesh Sharma and David P. Woodruff. WWW (Web Conference) 2020.
Reconstructing Trees from Traces [arxiv, slides, short video], with Sami Davies and Miklos Z. Racz. COLT 2019. Full version to appear in the Annals of Applied Probability.
Edge Estimation with Independent Set Oracles [arxiv, poster, slides, video], with Paul Beame, Sariel Har-Peled, Sivaramakrishnan Natarajan Ramamoorthy, Makrand Sinha. ITCS 2018
Massively-Parallel Similarity Join, Edge-Isoperimetry, and Distance Correlations on the Hypercube [arxiv], with Paul Beame. SODA 2017
DNA Data Storage
Multivariate Analytic Combinatorics for Cost Constrained Channels and Subsequence Enumeration [arxiv], with Andreas Lenz, Stephen Melczer, Paul H. Siegel, 2021
Batch Optimization for DNA Synthesis [arxiv], with Konstantin Makarychev, Miklos Z. Racz, Sergey Yekhanin. ISIT 2021.
Trace Reconstruction Problems in Computational Biology [arxiv], with Vinnu Bhardwaj, Pavel Pevzner, Yana Safonova. IEEE Transactions on Information Theory, 2020.
Coding for Efficient DNA Synthesis [video by Andreas], with Andreas Lenz, Yi Liu, Paul H. Siegel, Antonia Wachter-Zeh, Eitan Yaakobi. ISIT 2020.
Random Access in Large-Scale DNA Data Storage [biorxiv, nature biotech], Lee Organick, Siena Dumas Ang, Yuan-Jyue Chen, Randolph Lopez, Sergey Yekhanin, Konstantin Makarychev, Miklos Z. Racz, Govinda Kamath, Parikshit Gopalan, Bichlien Nguyen, Christopher Takahashi, Sharon Newman, Hsing-Yeh Parker, Cyrus Rashtchian, Kendall Stewart, Gagan Gupta, Robert Carlson, John Mulligan, Douglas Carmean, Georg Seelig, Luis Ceze, Karin Strauss. Nature Biotechnology, Cover Story, March 2018
Clustering Billions of Reads for DNA Data Storage [pdf, nips, poster]. Cyrus Rashtchian, Konstantin Makarychev, Miklos Z. Racz, Siena Dumas Ang, Djordje Jevdjic, Sergey Yekhanin, Luis Ceze, Karin Strauss. NIPS 2017. Spotlight Presentation (top 4.7% of submissions)
Combinatorics and Complexity
Edge Isoperimetric Inequalities for Powers of the Hypercube [arxiv, EJC], with William Raynaud. Electronic Journal of Combinatorics, 2022.
Covering Codes Using Insertions or Deletions [arxiv, video], with Andreas Lenz, Paul H. Siegel, Eitan Yaakobi. Short version in ISIT 2020. Full version accepted to the IEEE Transactions on Information Theory, 2020.
Equivalence of Systematic Linear Data Structures and Matrix Rigidity [arxiv, video by Siva], with Sivaramakrishnan Natarajan Ramamoorthy. ITCS 2020.
Shattered Sets and the Hilbert Function [arxiv], with Shay Moran. MFCS 2016
Bounded Matrix Rigidity and John's Theorem [ECCC], 2015
PhD Dissertation
New Algorithmic Tools for Distributed Similarity Search and Edge Estimation [pdf]
University of Washington, Computer Science and Engineering, June 2018.
Advisor: Paul Beame