ABHISHEK UMRAWALAboutResearchPublicationsTeachingServiceTalksGrantsAwardsCV ↓

Publications

Publications

Peer-reviewed research, journal manuscripts, education publications, working papers, and open-source software.

Google Scholar metrics: 411 citations · h-index 11 · Updated Oct. 2026

Journal Papers

J4.
Maximizing the Spread of Influence through a Social Network Using Partial Incentives
with Eliot Robson, Vaneet Aggarwal, and Christopher Quinn, Journal of Artificial Intelligence Research (JAIR), 2026.
Earlier version: IEEE Conference on Decision and Control (CDC), 2023.
J3.
A Community-Aware Framework for Social Influence Maximization
with Christopher Quinn and Vaneet Aggarwal, IEEE Transactions on Emerging Topics in Computational Intelligence (T-ETCI), 2023.
Earlier versions: ACM SIGMETRICS Performance Evaluation Review, 2022; AAAI Workshop on Graphs and Other Complex Structures for Learning and Reasoning, 2022.
J2.
Stochastic Top-k Subset Bandits with Linear Space and Non-Linear Feedback with Applications to Social Influence Maximization
with Mridul Agarwal, Vaneet Aggarwal, and Christopher Quinn, ACM/IMS Transactions on Data Science (TDS), 2022.
Earlier version: Algorithmic Learning Theory (ALT), 2021.
J1.
FlexPool: A Distributed Model-Free Deep Reinforcement Learning Algorithm for Shared Passengers and Goods Delivery
with Kaushik Manchella and Vaneet Aggarwal, IEEE Transactions on Intelligent Transportation Systems (T-ITS), 2021.
Earlier version: ACM Computer Science in Cars Symposium (CSCS), 2020.

Journal Manuscripts

JR5.
Optimizing Marketing Budgets for Social Influence: A Generalized Fractional Incentives Framework
with Akhil Bhimaraju, Eliot Robson, and Lav Varshney. In preparation for Management Science.
Earlier version: ACM International Conference on Information and Knowledge Management (CIKM), 2024.
JR4.
How Social Reinforcement Shapes Word-of-Mouth: A Conviction-Based Model for Marketing Diffusion and Network Targeting
with Curt Stutsman, Camille Woods, and Eliot Robson. In preparation for Management Science.
Earlier version: International AAAI Conference on Web and Social Media (ICWSM), 2026.
JR3.
Regulating Attention in Digital Platforms via Dynamic Taxation and Strategic Learning
with Eliot Robson, Alex Zheng, Elaine Ly, and Lav Varshney. In preparation for Information Systems Research.
Earlier version: ACM Workshop on Cognitive Security for Human-AI Systems (CogSec), 2026.
JR2.
Adaptive Exploration and Exploitation for Sequential Decision-Making under Uncertain and Weakly Separated Rewards
with Advaith Anand. In preparation for Operations Research.
Earlier version: NeurIPS Workshop on Mathematical Foundations and Operational Integration of Machine Learning for Uncertainty-Aware Decision-Making (MLxOR), 2026.
JR1.
A Game-Theoretic Analysis of Attacks on Large Language Models via Compositional Skills
with Xinbo Wu, Huan Zhang, and Lav Varshney. In preparation for INFORMS Journal on Computing.
Earlier version: International Conference on Machine Learning (ICML), 2026.

Conference Proceedings (Peer-Reviewed)

Note: Peer-reviewed conference publications, including ICML, ICWSM, SIGMETRICS, CIKM, ALT, and CDC, that are earlier versions of journal papers or manuscripts are listed with the entries above and are not repeated here.

C5.
CyNetDiff: A Python Library for Accelerated Implementation of Network Diffusion Models
with Eliot Robson and Dhemath Reddy, International Conference on Very Large Data Bases (VLDB), 2024.
C4.
Leveraging Causal Graphs for Blocking in Randomized Experiments
Conference on Causal Learning and Reasoning (CLeaR), 2023.
Earlier version: NeurIPS Workshop on Causal Inference Challenges in Sequential Decision Making, 2021.
C3.
An Explore-then-Commit Algorithm for Submodular Maximization under Full-Bandit Feedback
with Guanyu Nie, Mridul Agarwal, Vaneet Aggarwal, and Christopher Quinn, Conference on Uncertainty in AI (UAI), 2022.
C2.
DART: Adaptive Accept Reject Algorithm for Non-Linear Combinatorial Bandits
with Mridul Agarwal, Vaneet Aggarwal, and Christopher Quinn, AAAI Conference on AI (AAAI), 2021.
C1.
DeepFreight: A Model-Free Deep-Reinforcement-Learning-Based Algorithm for Multi-Transfer Freight Delivery
with Jiayu Chen, Tian Lan, and Vaneet Aggarwal, International Conference on Automated Planning and Scheduling (ICAPS), 2021.

Education & Teaching Publications

E2.
Low Effort, High Grades? Benchmarking LLMs on Engineering Assignments
with Yuxuan Chen, Siegfried Egg, Abdussalam Alawini, Mariana Silva, Max Fowler, and Melkior Ornik, ASEE Annual Conference and Exposition, 2026.
E1.
Understanding the Impact of Ungraded Assignments on Student Learning in Introductory Computing
with Yehya Sleiman Tellawi, ASEE Annual Conference and Exposition, 2026.
Earlier version: ACM Technical Symposium on Computer Science Education (SIGCSE), 2026.

Additional Working Papers

W4.
Efficient Influencer Selection across Interconnected Communities
with Eliot Robson.
W3.
Efficient Sequential Influencer Selection under Limited Feedback
with Advaith Anand.
W2.
Causal Steering of LLMs via Latent Vector Manipulation
with Yingbing Huang and Deming Chen.
W1.
Causal Analysis of Mixture-of-Experts
with Huiting Zhou, Yunze Xiao, and Zixin Mao.

Open-Source Software

S1.
CyNetDiff: A Python Library for Accelerated Implementation of Network Diffusion Models
Scalable open-source network diffusion modeling library distributed through PyPI; associated publication C5.