publications | Hasan Amin

Preprints

Likelihood Is Not Authorship: Can We Reliably Measure Human Contribution in AI-Assisted Writing?

Hasan Amin, Zhuoran Lu, and Ming Yin.

arXiv preprint arXiv:2610.19767

October 2026

PDF

BibTeX

@misc{amin2026likelihood, title = {{Likelihood Is Not Authorship: Can We Reliably Measure Human Contribution in AI-Assisted Writing?}}, author = {Amin, Hasan and Lu, Zhuoran and Yin, Ming}, eprint = {2610.19767}, archivePrefix = {arXiv}, primaryClass = {cs.CL}, doi = {10.48550/arXiv.2610.19767}, year = {2026}, url = {https://arxiv.org/abs/2610.19767} }
Simple Diffusion Language Models Are More Effective Few-Step Generators Than Reported

Hasan Amin, Ming Yin, and Rajiv Khanna.

arXiv preprint arXiv:2609.33947

September 2026

PDF Code

BibTeX

@misc{amin2026simplediffusion, title = {{Simple Diffusion Language Models Are More Effective Few-Step Generators Than Reported}}, author = {Amin, Hasan and Yin, Ming and Khanna, Rajiv}, eprint = {2609.33947}, archivePrefix = {arXiv}, primaryClass = {cs.CL}, doi = {10.48550/arXiv.2609.33947}, year = {2026}, url = {https://arxiv.org/abs/2609.33947} }
When Does Scale-Invariant Optimization Become Unstable? An Exact Schedule Law with Weight Decay

Hasan Amin, Wei-Kai Chang, and Rajiv Khanna.

arXiv preprint arXiv:2609.09116

September 2026

PDF Code

BibTeX

@misc{amin2026scaleinvariant, title = {{When Does Scale-Invariant Optimization Become Unstable? An Exact Schedule Law with Weight Decay}}, author = {Amin, Hasan and Chang, Wei-Kai and Khanna, Rajiv}, eprint = {2609.09116}, archivePrefix = {arXiv}, primaryClass = {cs.LG}, doi = {10.48550/arXiv.2609.09116}, year = {2026}, url = {https://arxiv.org/abs/2609.09116} }
Escaping the Mode Lottery: Multi-Response Training Improves Language Model Generalization

Hasan Amin, Kian Ahrabian, Ming Yin, and Rajiv Khanna.

arXiv preprint arXiv:2606.00544

May 2026

PDF Code

BibTeX

@misc{amin2026escaping, title = {{Escaping the Mode Lottery: Multi-Response Training Improves Language Model Generalization}}, author = {Amin, Hasan and Ahrabian, Kian and Yin, Ming and Khanna, Rajiv}, eprint = {2606.00544}, archivePrefix = {arXiv}, primaryClass = {cs.LG}, doi = {10.48550/arXiv.2606.00544}, year = {2026}, url = {https://arxiv.org/abs/2606.00544} }

Refereed Conference and Journal Publications

Consistent Diffusion Language Models

Hasan Amin, Yuan Gao, Yaser Souri, Subhojit Som, Ming Yin, Rajiv Khanna, and Xia Song.

Proceedings of the 43rd International Conference on Machine Learning (ICML)

Seoul, South Korea · July 2026

PDF

BibTeX

@inproceedings{amin2026consistent, title = {{Consistent Diffusion Language Models}}, author = {Amin, Hasan and Gao, Yuan and Souri, Yaser and Som, Subhojit and Yin, Ming and Khanna, Rajiv and Song, Xia}, booktitle = {Proceedings of the 43rd International Conference on Machine Learning}, year = {2026}, url = {https://icml.cc/virtual/2026/poster/66178} }
From Fallback to Frontline: When Can LLMs be Superior Annotators of Human Perspectives?

Hasan Amin, Harry Yizhou Tian, Xiaoni Duan, Chien-Ju Ho, Rajiv Khanna, and Ming Yin.

Findings of the Association for Computational Linguistics (ACL Findings)

San Diego, USA · July 2026

PDF Code

BibTeX

@inproceedings{amin-etal-2026-fallback, title = "From Fallback to Frontline: When Can {LLM}s be Superior Annotators of Human Perspectives?", author = "Amin, Hasan and Tian, Harry Yizhou and Duan, Xiaoni and Ho, Chien-Ju and Khanna, Rajiv and Yin, Ming", editor = "Liakata, Maria and Moreira, Viviane P. and Zhang, Jiajun and Jurgens, David", booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026", month = jul, year = "2026", address = "San Diego, California, United States", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/2026.findings-acl.2124/", doi = "10.18653/v1/2026.findings-acl.2124", pages = "42798--42830", ISBN = "979-8-89176-395-1" }
Understanding the Effects of AI-Assisted Critical Thinking on Human-AI Decision Making

Harry Yizhou Tian, Hasan Amin, and Ming Yin.

Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems (CHI)

Barcelona, Spain · April 2026

PDF

BibTeX

@inproceedings{tian2026critical, title = {{Understanding the Effects of AI-Assisted Critical Thinking on Human-AI Decision Making}}, author = {Tian, Harry Yizhou and Amin, Hasan and Yin, Ming}, booktitle = {Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems}, pages = {1--30}, publisher = {ACM}, doi = {10.1145/3772318.3790785}, year = {2026}, url = {https://doi.org/10.1145/3772318.3790785} }

Best Paper Honorable Mention
Align When They Want, Complement When They Need! Human-Centered Ensembles for Adaptive Human-AI Collaboration

Hasan Amin, Ming Yin, and Rajiv Khanna.

Proceedings of the 40th AAAI Conference on Artificial Intelligence (AAAI)

Singapore · January 2026

PDF Code

BibTeX

@article{amin2026align, title = {{Align When They Want, Complement When They Need! Human-Centered Ensembles for Adaptive Human-AI Collaboration}}, author = {Amin, Hasan and Yin, Ming and Khanna, Rajiv}, journal = {Proceedings of the AAAI Conference on Artificial Intelligence}, volume = {40}, pages = {17337--17346}, publisher = {Association for the Advancement of Artificial Intelligence (AAAI)}, doi = {10.1609/aaai.v40i21.38786}, number = {21}, year = {2026}, url = {https://ojs.aaai.org/index.php/AAAI/article/view/38786} }
On the Support Vector Effect in DNNs: Rethinking Data Selection and Attribution

Syed Hasan Amin Mahmood, Ming Yin, and Rajiv Khanna.

Proceedings of the 31st ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD)

Toronto, Canada · August 2025

PDF Code

BibTeX

@inproceedings{mahmood2025support, title = {{On the Support Vector Effect in DNNs: Rethinking Data Selection and Attribution}}, author = {Mahmood, Syed Hasan Amin and Yin, Ming and Khanna, Rajiv}, booktitle = {Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1}, pages = {1020--1031}, publisher = {ACM}, doi = {10.1145/3690624.3709295}, year = {2025}, url = {https://dl.acm.org/doi/abs/10.1145/3690624.3709295} }
Mix and Match: Characterizing Heterogeneous Human Behavior in AI-assisted Decision Making

Zhuoran Lu, Syed Hasan Amin Mahmood, Zhuoyan Li, and Ming Yin.

Proceedings of the 12th AAAI Conference on Human Computation and Crowdsourcing (HCOMP)

Pittsburgh, USA · October 2024

PDF

BibTeX

@article{lu2024mix, title = {{Mix and Match: Characterizing Heterogeneous Human Behavior in AI-assisted Decision Making}}, author = {Lu, Zhuoran and Mahmood, Syed Hasan Amin and Li, Zhuoyan and Yin, Ming}, journal = {Proceedings of the AAAI Conference on Human Computation and Crowdsourcing}, volume = {12}, pages = {95--104}, publisher = {Association for the Advancement of Artificial Intelligence (AAAI)}, doi = {10.1609/hcomp.v12i1.31604}, number = {1}, year = {2024}, url = {https://ojs.aaai.org/index.php/HCOMP/article/view/31604} }
Designing Behavior-Aware AI to Improve the Human-AI Team Performance in AI-Assisted Decision Making

Syed Hasan Amin Mahmood, Zhuoran Lu, and Ming Yin.

Proceedings of the 33rd International Joint Conference on Artificial Intelligence (IJCAI)

Jeju, South Korea · August 2024

PDF Code

BibTeX

@inproceedings{ijcai2024p344, title = {Designing Behavior-Aware AI to Improve the Human-AI Team Performance in AI-Assisted Decision Making}, author = {Mahmood, Syed Hasan Amin and Lu, Zhuoran and Yin, Ming}, booktitle = {Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence, {IJCAI-24}}, publisher = {International Joint Conferences on Artificial Intelligence Organization}, editor = {Kate Larson}, pages = {3106--3114}, year = {2024}, month = {8}, note = {Main Track}, doi = {10.24963/ijcai.2024/344}, url = {https://doi.org/10.24963/ijcai.2024/344}, }
Phishcasting: Deep Learning for Time Series Forecasting of Phishing Attacks

Syed Hasan Amin Mahmood, Syed Mustafa Ali Abbasi, Ahmed Abbasi, and Fareed Zaffar.

Proceedings of the 2020 IEEE International Conference on Intelligence and Security Informatics (ISI)

Virtual Conference · November 2020

PDF

BibTeX

@inproceedings{mahmood2020phishcasting, title = {{Phishcasting: Deep Learning for Time Series Forecasting of Phishing Attacks}}, author = {Mahmood, Syed Hasan Amin and Abbasi, Syed Mustafa Ali and Abbasi, Ahmed and Zaffar, Fareed}, booktitle = {2020 IEEE International Conference on Intelligence and Security Informatics (ISI)}, pages = {1--6}, publisher = {IEEE}, doi = {10.1109/ISI49825.2020.9280509}, year = {2020}, url = {https://ieeexplore.ieee.org/abstract/document/9280509} }

Workshop Papers, Posters, and Extended Abstracts

On the Support Vector Effect in DNNs: Rethinking Last Layer Sensitivity-based Instance Attribution

Syed Hasan Amin Mahmood and Rajiv Khanna.

Workshop on Attributing Model Behavior at Scale (NeurIPS workshop)

New Orleans, USA · December 2023

BibTeX

@inproceedings{mahmood2023support, title = {{On the Support Vector Effect in DNNs: Rethinking Last Layer Sensitivity-based Instance Attribution}}, author = {Mahmood, Syed Hasan Amin and Khanna, Rajiv}, booktitle = {NeurIPS Workshop on Attributing Model Behavior at Scale}, year = {2023}, url = {https://neurips.cc/virtual/2023/83395} }
Give Weight to Human Reactions: Optimizing Complementary AI in Practical Human-AI Teams

Hasan Amin, Zhuoran Lu, and Ming Yin.

Workshop on Artificial Intelligence & Human Computer Interaction (ICML workshop)

Honolulu, USA · July 2023

PDF

BibTeX

@inproceedings{amin2023give, title = {{Give Weight to Human Reactions: Optimizing Complementary AI in Practical Human-AI Teams}}, author = {Amin, Hasan and Lu, Zhuoran and Yin, Ming}, booktitle = {ICML Workshop on Artificial Intelligence \& Human Computer Interaction}, year = {2023}, url = {https://icml.cc/virtual/2023/27379} }
Using Deep Generative Models to Boost Forecasting: A Phishing Prediction Case Study

Syed Hasan Amin Mahmood and Ahmed Abbasi.

Proceedings of the 2020 IEEE International Conference on Data Mining Workshops (ICDM Workshops)

Sorrento, Italy · November 2020

PDF

BibTeX

@inproceedings{mahmood2020forecasting, title = {{Using Deep Generative Models to Boost Forecasting: A Phishing Prediction Case Study}}, author = {Mahmood, Syed Hasan Amin and Abbasi, Ahmed}, booktitle = {2020 International Conference on Data Mining Workshops (ICDMW)}, pages = {496--505}, publisher = {IEEE}, doi = {10.1109/icdmw51313.2020.00073}, year = {2020}, url = {https://ieeexplore.ieee.org/abstract/document/9346362} }