Contact
850 W. Taylor Street, Computer Design Research and Learning Center (CDRLC), Room 5452, Chicago, IL 60607☏: (312) 413-8028 ✉: asudeh[AT]uic[DOT]edu
A. Asudeh is an Associate Professor of Computer Science at the University of Illinois Chicago and the director of Innovative Data Exploration Laboratory (InDeX Lab).
He is a senior member of ACM and a senior member of IEEE.
He serves as an Associate Editor for the IEEE Transactions on Knowledge and Data Engineering (TKDE), a VLDB Ambassador, and the VLDB Endowment's Liaison to NSF.
His research focus is on Algorithm Design for Data and AI problems. He designs efficient, accurate, and responsible solutions that leverage Approximation, Randomized, and Computational Geometry Algorithms. His research is supported NSF and has received recognitions, including the Communications of the ACM's (CACM) Research Highlight, Google's Research Scholar Award, SIGMOD 2019 Research Highlight Award, “Best of VLDB” 2020 (the special issue of VLDBJ), and SIGMOD 2017 Reproducibility Award.
His research focus is on Algorithm Design for Data and AI problems. He designs efficient, accurate, and responsible solutions that leverage Approximation, Randomized, and Computational Geometry Algorithms. His research is supported NSF and has received recognitions, including the Communications of the ACM's (CACM) Research Highlight, Google's Research Scholar Award, SIGMOD 2019 Research Highlight Award, “Best of VLDB” 2020 (the special issue of VLDBJ), and SIGMOD 2017 Reproducibility Award.
Recent Publications (Since 2024) -- see publications for the complete list.
-
An Efficient Matrix Multiplication Algorithm for Accelerating Inference in Binary and Ternary Neural Networks.
[Code] LLMAlgorithmsMachineLearning
Mohsen Dehghankar, Mahdi Erfanian, Abolfazl Asudeh.
In ICML 2025. -
Rank It, Then Ask It: Input Reranking for Maximizing the Performance of LLMs on Symmetric Tasks.
[Code] LLMMachineLearning
Mohsen Dehghankar, Abolfazl Asudeh.
In KDD 2025. -
Mining the Minoria: Unknown, Under-represented, and Under-performing Minority Groups.
[Code] Responsible DataData-centric AI
Mohsen Dehghankar, Abolfazl Asudeh.
In VLDB, 2025. -
Fair Set Cover.
[Code] AlgorithmsFairness
Mohsen Dehghankar, Rahul Raychaudhury, Stavros Sintos, Abolfazl Asudeh.
In KDD, 2025. -
HENN: A Hierarchical Epsilon Net Navigation Graph for Approximate Nearest Neighbor Search.
[Code]Data-structureAlgorithms
Mohsen Dehghankar and Abolfazl Asudeh.
Preprint (2025) -
Fair-Count-Min: Frequency Estimation under Equal Group-wise Approximation Factor.
Data-structureFairness
Nima Shahbazi, Stavros Sintos, Abolfazl Asudeh.
Preprint (2025) -
An Adversary-Resistant Multi-Agent LLM System via Credibility Scoring.
LLM
Sana Ebrahimi, Mohsen Dehghankar, Abolfazl Asudeh.
Preprint (2025) -
Needle: A Generative-AI Powered Monte Carlo Method for Answering Complex Natural Language Queries on Multi-modal Data.
[Code] Image DatabasesLLM4DataMachineLearning
Mahdi Erfanian, Mohsen Dehghankar, Abolfazl Asudeh.
Preprint (2024) -
Evaluating the Feasibility of Sampling-Based Techniques for Training Multilayer Perceptrons.
[Slides] [Code] Computation at ScaleMachine Learning
Sana Ebrahimi, Rishi Advani, Abolfazl Asudeh.
In EDBT, 2025 -
Chameleon: Foundation Models for Fairness-aware Multi-modal Data Augmentation to Enhance Coverage of Minorities.
[Slides] [Video] [Code] LLM4Data
Mahdi Erfanian, H. V. Jagadish, Abolfazl Asudeh.
In VLDB, 2024. -
FairHash: A Fair and Memory/Time-efficient Hashmap.
[Slides] [Code] Data-structureFairness
Nima Shahbazi, Stavros Sintos, Abolfazl Asudeh.
In SIGMOD, 2024 -
Requal-LM: Reliability and Equity through Aggregation in Large Language Models.
[Slides]LLMFairnessReliability
Sana Ebrahimi, Nima Shahbazi, Abolfazl Asudeh.
In NAACL (Findings), 2024 -
AXOLOTL: Fairness through Assisted Self-Debiasing of Large Language Model Outputs.
[Slides]LLMFairness
Sana Ebrahimi, Kaiwen Chen, Abolfazl Asudeh, Gautam Das, Nick Koudas.
In ICKG, 2024 -
Reliability Evaluation of Individual Predictions: A Data-centric Approach.
Data-centric AIReliability
Nima Shahbazi, Abolfazl Asudeh.
In VLDB Journal, 2024 -
Coverage-based Data-centric Approaches for Responsible and Trustworthy AI.
(Invited paper)
Data-centric AIResponsible Data
Nima Shahbazi, Mahdi Erfanian, Abolfazl Asudeh.
Data Engineering Bulletin 48(1), Special Issue on Data-centric Responsible AI, 2024 -
Data Coverage for Detecting Representation Bias in Image Data Sets: A Crowdsourcing Approach.
[Code] Responsible Data
Melika Mousavi, Nima Shahbazi, Abolfazl Asudeh.
In EDBT, 2024 -
Shapley Values for Explanation in Two-sided Matching Applications.
[Code] MatchingExplainability
Suraj Shetiya, Ian Swift, Abolfazl Asudeh, Gautam Das.
In EDBT, 2024 -
Data Distribution Tailoring Revisited: Cost-Efficient Integration of Representative Data.
Responsible Data
Jiwon Chang, Bohan Cui, Fatemeh Nargesian, Abolfazl Asudeh, H. V. Jagadish.
In VLDB Journal, 2024 -
FairEM360: A Suite for Responsible Entity Matching.
(Demo paper)
[Demo Code] [EMFairness Code] [Video] ResponsibleDataEntity Matching
Nima Shahbazi, Mahdi Erfanian, Abolfazl Asudeh, Fatemeh Nargesian, Divesh Srivastava.
In VLDB, 2024 presentation video
📌 Pinned Systems and Repositories 📌
Needle🪡🔍 is a deployment-ready open-source image retrieval database with high accuracy that can handle complex queries in natural language.
It is Fast, Efficient, and Precise, outperforming state-of-the-art methods.
Born from high-end research, Needle is designed to be accessible to everyone while delivering top-notch performance.
Whether you are a researcher, developer, or an enthusiast, Needle opens up innovative ways to explore your image datasets. ✨
📖 Detailed installation instructions: Getting Started .
RSR 🧮: Efficient Matrix Multiplication for Accelerating Inference in Binary and Ternary Neural Networks
This project aims to provide a fast and efficient approach to low-bit matrix multiplication. The code repository implements Redundant Segment Reduction (RSR), a fast matrix multiplication algorithm designed for matrices in binary and ternary networks. The RSR method optimizes computation efficiency by a log(n) factor, making it particularly useful for applications in low-bit deep learning and efficient inference. The codebase provides ready-to-use C++ and NumPy-based implementations, as well as PyTorch implementations with both CPU and GPU support, enabling scalable and optimized matrix operations in deep learning environments. It includes sample experiments on various `1.58bit` models and LLMs.✨Sponsors
- NSF IIS-2348919 (2024 - 2027): III: Small: Fairness-aware Data Structures for Approximate Query Processing. Abolfazl Asudeh and Stavros Sintos.
- NSF IIS-2107290 (2021 - 2024): III: Medium: Collaborative Research: Fairness in Web Database Applications. Abolfazl Asudeh (Lead PI - UIC), H. V. Jagadish (UofM), and Gautam Das and Shirin Nilizadeh (UTA).
- Google Research Scholar Award (2021 - 2022): An end-to-end system for detecting cherry-picked trendlines. Abolfazl Asudeh.
