George Mason computer science faculty shine at world’s top computing conferences

George Mason University’s Department of Computer Science researchers earned numerous paper acceptances at some of the world’s most selective computing conferences in 2025 and 2026. These results highlight Mason’s growing research impact across cybersecurity, computer systems, networking, artificial intelligence, and human-centered computing.  

George Mason computer science faculty and graduate student authors are in bold below.  

 

The 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025) 

July 27 to August 1st, 2025 

• ProtoLens: Advancing Prototype Learning for Fine-Grained Interpretability in Text Classification 

  Bowen Wei and Ziwei Zhu

• Spurious Correlations and Beyond: Understanding and Mitigating Shortcut Learning in SDOH Extraction with Large Language Models 

  Fardin Ahsan Sakib, Ziwei Zhu, and Ozlem Uzuner 

• Instruction-Tuning LLMs for Event Extraction with Annotation Guidelines 

  Saurabh Srivastava, Sweta Pati, and Ziyu Yao 

• Efficient but Vulnerable: Benchmarking and Defending LLM Batch Prompting Attack 

  Murong Yue, and Ziyu Yao

• Cross-Lingual Representation Alignment Through Contrastive Image-Caption Tuning 

  Nathaniel Krasner, Nicholas Lanuzo, Antonios Anastasopoulos

• Dialect Normalization using Large Language Models and Morphological Rules 

  Antonios Dimakis, John Pavlopoulos, Antonios Anastasopoulos 

 

Association for Computing Machinery Conference on Computer and Communications Security (ACM CCS) 2025 

Oct 13-17, 2025 

• Training Robust Classifiers for Classifying Encrypted Traffic under Dynamic Network Conditions 

  Yuqi Qing, Qilei Yin, Xinhao Deng, Xiaoli Zhang, Peiyang Li, Zhuotao Liu, Kun Sun, Ke Xu, Qi Li

• Virtual Reality, Real Problems: A Longitudinal Security Analysis of Virtual Reality Firmware 
  

  Vamsi Shankar Simhadri, Yichang Xiong, Habiba Farrukh, Xiaokuan Zhang  

• Exposing Privacy Risks in Anonymizing Clinical Data: Combinatorial Refinement Attacks on k‑Anonymity Without Auxiliary Information 
  

  Somiya Chhillar, Mary K. Righi, Rebecca E. Sutter, Evgenios Kornaropoulos

• Off‑Path Transmission Control Protocol Exploits: Path Maximum Transmission Unit Discovery Breaks Connection Isolation in Internet Protocol Address Sharing Scenarios 
  

  Xuewei Feng, Zhaoxi Li, Qi Li, Ziqiang Wang, Kun Sun, Ke Xu 

 

Internet Measurement Conference (IMC) 2025 

Oct 28-31, 2025 

• Hello, Generative Artificial Intelligence? Dissecting Human‑to‑Generative‑AI Calling 

  Ruizhi Cheng, Surendra Pathak, Guowu Xie, Matteo Varvello, Songqing Chen, Bo Han 

• The Decentralization Dilemma: Performance Trade‑Offs in the InterPlanetary File System and Breakpoint

  Ruizhe Shi, Yuqi Fu, Ruizhi Cheng, Bo Han, Yue Cheng, Songqing Chen  

• From Web Graphics Library to Web Graphics Processing Unit: A Reality Check of Browser‑Based GPU Acceleration 

  Sthitadhi Sengupta, Nan Wu, Matteo Varvello, Krish Jana, Songqing Chen, Bo Han 

 

The 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP 2025) 

November 4 –9, 2025 

• All for One: LLMs Solve Mental Math at the Last Token With Information Transferred From Other Tokens 

  Siddarth Mamidanna, Daking Rai, Ziyu Yao, and Yilun Zhou  

• Feature Extraction and Steering for Enhanced Chain-of-Thought Reasoning in Language Models 

  Zihao Li, Xu Wang, Yuzhe Yang, Ziyu Yao, Haoyi Xiong, and Mengnan Du 
  

• What's Not Said Still Hurts: A Description-Based Evaluation Framework for Measuring Social Bias in LLMs

   Jinhao Pan, Chahat Raj, Ziyu Yao, Ziwei Zhu  

• A survey on sparse autoencoders: Interpreting the internal mechanisms of large language models 

  Dong Shu, Xuansheng Wu, Haiyan Zhao, Daking Rai, Ziyu Yao, Ninghao Liu, and Mengnan Du  

• Toward Inclusive Language Models: Sparsity-Driven Calibration for Systematic and Interpretable 

  Prommy Sultana Hossain, Chahat Raj, Ziwei Zhu, Jessica Lin, Emanuela Marasco  

• Tracing L1 Interference in English Learner Writing: A Longitudinal Corpus with Error Annotations 

  Poorvi Acharya, J. Elizabeth Liebl, Dhiman Goswami, Kai North, Marcos Zampieri, Antonios Anastasopoulos 
  

• Dialectal Toxicity Detection: Evaluating LLM-as-a-Judge Consistency Across Language Varieties 

  Fahim Faisal, Md Mushfiqur Rahman, Antonios Anastasopoulos 

   

Neural Information Processing Systems (NeurIPS) 2025 

Dec 2-7, 2025 

• Prohibiting Generative AI in any Form of Weapon Control 

  Missy Cummings  

• Adaptive Algorithms with Sharp Convergence Rates for Stochastic Hierarchical Optimization 

  Xiaochuan Gong, Jie Hao, Mingrui Liu

• Failure by Interference: Language Models Make Balanced Parentheses Errors When Faulty Mechanisms Overshadow Sound Ones 

  Daking Rai, Samuel Miller, Kevin Moran, and Ziyu Yao

• Compositional Neural Network Verification via Assume-Guarantee Reasoning 

  Hai Duong, David Shriver, ThanhVu Nguyen, Matthew Dwyer (received Research Spotlight Award) 

• Generating and Checking DNN Verification Proofs

  Hai Duong, ThanhVu Nguyen, Matthew Dwyer 

 

Architectural Support for Programming Languages and Operating Systems (ASPLOS) 2026 

Mar 22-26, 2026 

• NotebookOS: A Replicated Notebook Platform for Interactive Training with On‑Demand Graphics Processing Units 

  Benjamin Carver, Jingyuan Zhang, Haoliang Wang, Kanak Mahadik, Yue Cheng 
  

• DeepContext: A Context‑Aware, Cross‑Platform Tool for Performance Profiling of Deep Learning Workloads 

  Qidong Zhao, Hao Wu, Yueming Hao, Zilingfeng Ye, Jiajia Li, Xu Liu, Keren Zhou  

• Triton‑Sanitizer: A Fast and Device‑Agnostic Memory Sanitizer with Rich Diagnostic Context 

  Hao Wu, Qidong Zhao, Songqing Chen, Yang Chen, Yueming Hao, Tony C. W. Liu, Sijia Chen, Adnan Aziz, Keren Zhou  

• Linear Layouts: Robust Code Generation of Efficient Tensor Computation Using Finite Fields 

  Keren Zhou, Mario Lezcano, Adam Goucher, Akhmed Rakhmati, Jeff Niu, Justin Lebar, Pawel Szczerbuk, Peter Bell, Phil Tillet, Thomas Raoux, Zahi Moudallal 

 

Association for Computing Machinery Conference on Human Factors in Computing Systems (ACM CHI) 2026 

Apr 13-17, 2026 

• Cultures as Catalysts: Nurturing HCI Communities Across Regions 

  Maristella Matera, Zhicong Lu, Gustavo Lopez, Houda Elmimouni, Susan Dray  

• Designing AI Peers for Collaborative Mathematical Problem Solving with Middle School Students: A Participatory Design Study

   Wenhan Lyu, Yimeng Wang, Murong Yue, Yifan Sun, Jennifer Suh, Meredith Kier, Ziyu Yao, Yixuan Zhang  

• Designing Multi-Robot Ground Video Sensemaking with Public Safety Professionals

   Puqi Zhou, Ali Asgarov, Aafiya Hussain, Wonjoon Park, Amit Paudyal, Sameep Shrestha, Chia-Wei Tang, Michael Lighthiser, Michael Hieb, Xuesu Xiao, Chris Thomas, Sungsoo Ray Hong  

• Emotions in Fandom Crowdfunding: Investigating How Online Interactions Affect Collaborative Monetary Activities 

  Molly Zhuangtong Huang, Zhicong Lu, Caishi Huang, Zhenning Li, Hantao Zhao, Xiaobo Zhou, Dazhao Cheng, Kanye Ye Wang  

• Exploring Collaborative Immersive Visualization & Analytics for High-Dimensional Scientific Data through Domain Expert Perspectives 

  Fahim Arsad, Jie Li, Simon Su, Songqing Chen, Bo Han  

• HieraVisVR: Hierarchical Visual Analytics for Motion-Centric VR Playtesting 

  Yongqi Zhang, Erdem Murat, Liuchuan Yu, Haikun Huang, Minsoo Choi, Christos Mousas, Lap-Fai Yu 
  

• Improving User Interface Generation Models from Designer Feedback

  Jason Wu, Amanda Swearngin, Arun Krishna Vajjala, Alan Leung, Jeffrey Nichols, Titus Barik 
  

• InterFlow: Designing Unobtrusive AI to Empower Interviewers in Semi-Structured Interviews 

  Yi Wen, Yu Zhang, Sriram Suresh, Zhicong Lu, Can Liu, Meng Xia 
  

• [Honorable Mention] MoSound: An Interactive Tool for Generative Sound Design in Motion Graphics 

  Jialin Huang, Prem Seetharaman, Timothy Richard Langlois, Li-Yi Wei, Rubaiat Habib Kazi, Yotam Gingold 
  

• PuppetChat: Fostering Intimate Communication through Bidirectional Actions and Micronarratives 

  Emma Jiren Wang, Siying Hu, Zhicong Lu 
  

• Rehearsing the Self with AI: Teens Cross-Domain Use of Chatbots 

  Cora Sula, Umama Dewan, Nora McDonald  

• Rethinking Productivity Support for Workers with ADHD in the Construction: Preliminary Insights 

  Zinat Ara, Behzad Esmaeili, Lap-Fai Yu, Sungsoo Ray Hong 
  

• Sportoonizer: Augmenting Sports Highlights’ Narratives via AI-Generated Manga B-Roll 

  Siying Hu, Jiajun Wang, Xiangzhe Yuan, Jian Ma, Zhiyang Wu, Zhicong Lu  

• ‘I Will Dream Sweet Dreams’: Understanding Remote Companionship Volunteer Activities for Factual Orphans in Rural China 

  Jingjing Zhang, Yanrong Tang, Yueqing Hu, Tianhong Wang, Hanchao Song, Zhicong Lu, Jiangtao Gong