Sara Abdali

Senior Researcher

出版物

表示方法:

- Hegelian Self-Reflection for Improved Mathematical and Symbolic Reasoning, and Scientific Discovery in Large Language Models
  
  Sara Abdali, Michael Solodko, Can Goksen, Saeed Amizadeh, Julie E. Maybee, Kazuhito Koishida, Pashmina Cameron
  
  September 2026
  
  MathNLP 2026: The 4th Workshop on Mathematical Natural Language Processing at EMNLP 2026 | September 2026
  
  PDF
- Echoverse: Deep, Evolving Environments for Training Computer-Use Agents at Scale
  
  Yash Pandya, Sahil Gupta, Sarthak Harne, Archana Yadav, Kavyansh Chourasia, Hussein Mozannar, Vibhav Vineet, Sara Abdali, Corby Rosset, Yash Lara, Ahmed Awadallah, Ece Kamar, Akshay Nambi
  
  July 2026
- Hierarchical Self-Attention: Generalizing Neural Attention Mechanics to Multi-Scale Problems
  
  Saeed Amizadeh, Sara Abdali, Yinheng Li, Kazuhito Koishida
  
  NeurIPS 2025 | September 2025
  
  Publication
- Misaligned Roles, Misplaced Images: Structural Input Perturbations Expose Multimodal Alignment Blind Spots
  
  Erfan Shayegani, G. M. Shahariar, Sara Abdali, Lei Yu, Nael B. Abu-Ghazaleh, Yue Dong
  
  ICLR 2026 | March 2025
  
  DOI Publication
- Self-reflecting Large Language Models: A Hegelian Dialectical Approach
  
  Sara Abdali, Can Goksen, Michael Solodko, Saeed Amizadeh, Kazuhito Koishida
  
  ArXiv | January 2025
  
  Publication Publication
- Windows Agent Arena: Evaluating Multi-Modal OS Agents at Scale
  
  Rogerio Bonatti, Dan Zhao, Francesco Bonacci, Dillon Dupont, Sara Abdali, Yinheng Li, Yadong Lu, Justin Wagle, Kazuhito Koishida, A. Bucker, Lawrence Jang, Zack Hui
  
  ICML 2025 | September 2024
  
  DOI Publication Publication
- Decoding the AI Pen: Techniques and Challenges in Detecting AI-Generated Text
  
  Sara Abdali, Richard Anarfi, CJ Barberan, Jia He
  
  KDD 2024 | August 2024
  
  Publication
- Can LLMs be Fooled? Investigating Vulnerabilities in LLMs
  
  Sara Abdali, Jia He, CJ Barberan, Richard Anarfi
  
  July 2024
  
  arXiv | July 2024
  
  PDF Publication
- Securing Large Language Models: Threats, Vulnerabilities and Responsible Practices
  
  Sara Abdali, Richard Anarfi, C. Barberan, Jia He, Erfan Shayegani
  
  March 2024
  
  arXiv | March 2024
  
  Publication Publication
- Extracting Self-Consistent Causal Insights from Users Feedback with LLMs and In-context Learning
  
  Sara Abdali, Anjali Parikh, Steve Lim, Emre Kiciman
  
  ArXiv | December 2023
  
  DOI Publication Publication
- Vec2Node: Self-training with Tensor Augmentation for Text Classification with Few Labels
  
  Sara Abdali
  
  European Conference on Principles of Data Mining and Knowledge Discovery | September 2022
  
  ECML-PKDD Scholarship Award
  
  Publication

- Hegelian Self-Reflection for Improved Mathematical and Symbolic Reasoning, and Scientific Discovery in Large Language Models
  
  Sara Abdali, Michael Solodko, Can Goksen, Saeed Amizadeh, Julie E. Maybee, Kazuhito Koishida, Pashmina Cameron
  
  September 2026
  
  MathNLP 2026: The 4th Workshop on Mathematical Natural Language Processing at EMNLP 2026 | September 2026
  
  PDF
- Echoverse: Deep, Evolving Environments for Training Computer-Use Agents at Scale
  
  Yash Pandya, Sahil Gupta, Sarthak Harne, Archana Yadav, Kavyansh Chourasia, Hussein Mozannar, Vibhav Vineet, Sara Abdali, Corby Rosset, Yash Lara, Ahmed Awadallah, Ece Kamar, Akshay Nambi
  
  July 2026
- Hierarchical Self-Attention: Generalizing Neural Attention Mechanics to Multi-Scale Problems
  
  Saeed Amizadeh, Sara Abdali, Yinheng Li, Kazuhito Koishida
  
  NeurIPS 2025 | September 2025
  
  Publication
- Misaligned Roles, Misplaced Images: Structural Input Perturbations Expose Multimodal Alignment Blind Spots
  
  Erfan Shayegani, G. M. Shahariar, Sara Abdali, Lei Yu, Nael B. Abu-Ghazaleh, Yue Dong
  
  ICLR 2026 | March 2025
  
  DOI Publication
- Self-reflecting Large Language Models: A Hegelian Dialectical Approach
  
  Sara Abdali, Can Goksen, Michael Solodko, Saeed Amizadeh, Kazuhito Koishida
  
  ArXiv | January 2025
  
  Publication Publication
- Windows Agent Arena: Evaluating Multi-Modal OS Agents at Scale
  
  Rogerio Bonatti, Dan Zhao, Francesco Bonacci, Dillon Dupont, Sara Abdali, Yinheng Li, Yadong Lu, Justin Wagle, Kazuhito Koishida, A. Bucker, Lawrence Jang, Zack Hui
  
  ICML 2025 | September 2024
  
  DOI Publication Publication
- Decoding the AI Pen: Techniques and Challenges in Detecting AI-Generated Text
  
  Sara Abdali, Richard Anarfi, CJ Barberan, Jia He
  
  KDD 2024 | August 2024
  
  Publication
- Can LLMs be Fooled? Investigating Vulnerabilities in LLMs
  
  Sara Abdali, Jia He, CJ Barberan, Richard Anarfi
  
  July 2024
  
  arXiv | July 2024
  
  PDF Publication
- Securing Large Language Models: Threats, Vulnerabilities and Responsible Practices
  
  Sara Abdali, Richard Anarfi, C. Barberan, Jia He, Erfan Shayegani
  
  March 2024
  
  arXiv | March 2024
  
  Publication Publication
- Extracting Self-Consistent Causal Insights from Users Feedback with LLMs and In-context Learning
  
  Sara Abdali, Anjali Parikh, Steve Lim, Emre Kiciman
  
  ArXiv | December 2023
  
  DOI Publication Publication
- Vec2Node: Self-training with Tensor Augmentation for Text Classification with Few Labels
  
  Sara Abdali
  
  European Conference on Principles of Data Mining and Knowledge Discovery | September 2022
  
  ECML-PKDD Scholarship Award
  
  Publication
- Hegelian Self-Reflection for Improved Mathematical and Symbolic Reasoning, and Scientific Discovery in Large Language Models
  
  Sara Abdali, Michael Solodko, Can Goksen, Saeed Amizadeh, Julie E. Maybee, Kazuhito Koishida, Pashmina Cameron
  
  September 2026
  
  MathNLP 2026: The 4th Workshop on Mathematical Natural Language Processing at EMNLP 2026 | September 2026
  
  PDF
- Self-reflecting Large Language Models: A Hegelian Dialectical Approach
  
  Sara Abdali, Can Goksen, Michael Solodko, Saeed Amizadeh, Kazuhito Koishida
  
  ArXiv | January 2025
  
  Publication Publication
- Decoding the AI Pen: Techniques and Challenges in Detecting AI-Generated Text
  
  Sara Abdali, Richard Anarfi, CJ Barberan, Jia He
  
  KDD 2024 | August 2024
  
  Publication
- Can LLMs be Fooled? Investigating Vulnerabilities in LLMs
  
  Sara Abdali, Jia He, CJ Barberan, Richard Anarfi
  
  July 2024
  
  arXiv | July 2024
  
  PDF Publication
- Hegelian Self-Reflection for Improved Mathematical and Symbolic Reasoning, and Scientific Discovery in Large Language Models
  
  Sara Abdali, Michael Solodko, Can Goksen, Saeed Amizadeh, Julie E. Maybee, Kazuhito Koishida, Pashmina Cameron
  
  September 2026
  
  MathNLP 2026: The 4th Workshop on Mathematical Natural Language Processing at EMNLP 2026 | September 2026
  
  PDF
- Hegelian Self-Reflection for Improved Mathematical and Symbolic Reasoning, and Scientific Discovery in Large Language Models
  
  Sara Abdali, Michael Solodko, Can Goksen, Saeed Amizadeh, Julie E. Maybee, Kazuhito Koishida, Pashmina Cameron
  
  September 2026
  
  MathNLP 2026: The 4th Workshop on Mathematical Natural Language Processing at EMNLP 2026 | September 2026
  
  PDF
- Decoding the AI Pen: Techniques and Challenges in Detecting AI-Generated Text
  
  Sara Abdali, Richard Anarfi, CJ Barberan, Jia He
  
  KDD 2024 | August 2024
  
  Publication
- Can LLMs be Fooled? Investigating Vulnerabilities in LLMs
  
  Sara Abdali, Jia He, CJ Barberan, Richard Anarfi
  
  July 2024
  
  arXiv | July 2024
  
  PDF Publication
- Self-reflecting Large Language Models: A Hegelian Dialectical Approach
  
  Sara Abdali, Can Goksen, Michael Solodko, Saeed Amizadeh, Kazuhito Koishida
  
  ArXiv | January 2025
  
  Publication Publication
- Can LLMs be Fooled? Investigating Vulnerabilities in LLMs
  
  Sara Abdali, Jia He, CJ Barberan, Richard Anarfi
  
  July 2024
  
  arXiv | July 2024
  
  PDF Publication
- Securing Large Language Models: Threats, Vulnerabilities and Responsible Practices
  
  Sara Abdali, Richard Anarfi, C. Barberan, Jia He, Erfan Shayegani
  
  March 2024
  
  arXiv | March 2024
  
  Publication Publication

- Hegelian Self-Reflection for Improved Mathematical and Symbolic Reasoning, and Scientific Discovery in Large Language Models
  
  Sara Abdali, Michael Solodko, Can Goksen, Saeed Amizadeh, Julie E. Maybee, Kazuhito Koishida, Pashmina Cameron
  
  September 2026
  
  MathNLP 2026: The 4th Workshop on Mathematical Natural Language Processing at EMNLP 2026 | September 2026
  
  PDF
- Can LLMs be Fooled? Investigating Vulnerabilities in LLMs
  
  Sara Abdali, Jia He, CJ Barberan, Richard Anarfi
  
  July 2024
  
  arXiv | July 2024
  
  PDF Publication
- Securing Large Language Models: Threats, Vulnerabilities and Responsible Practices
  
  Sara Abdali, Richard Anarfi, C. Barberan, Jia He, Erfan Shayegani
  
  March 2024
  
  arXiv | March 2024
  
  Publication Publication
- Echoverse: Deep, Evolving Environments for Training Computer-Use Agents at Scale
  
  Yash Pandya, Sahil Gupta, Sarthak Harne, Archana Yadav, Kavyansh Chourasia, Hussein Mozannar, Vibhav Vineet, Sara Abdali, Corby Rosset, Yash Lara, Ahmed Awadallah, Ece Kamar, Akshay Nambi
  
  July 2026
- Hierarchical Self-Attention: Generalizing Neural Attention Mechanics to Multi-Scale Problems
  
  Saeed Amizadeh, Sara Abdali, Yinheng Li, Kazuhito Koishida
  
  NeurIPS 2025 | September 2025
  
  Publication
- Misaligned Roles, Misplaced Images: Structural Input Perturbations Expose Multimodal Alignment Blind Spots
  
  Erfan Shayegani, G. M. Shahariar, Sara Abdali, Lei Yu, Nael B. Abu-Ghazaleh, Yue Dong
  
  ICLR 2026 | March 2025
  
  DOI Publication
- Windows Agent Arena: Evaluating Multi-Modal OS Agents at Scale
  
  Rogerio Bonatti, Dan Zhao, Francesco Bonacci, Dillon Dupont, Sara Abdali, Yinheng Li, Yadong Lu, Justin Wagle, Kazuhito Koishida, A. Bucker, Lawrence Jang, Zack Hui
  
  ICML 2025 | September 2024
  
  DOI Publication Publication
- Decoding the AI Pen: Techniques and Challenges in Detecting AI-Generated Text
  
  Sara Abdali, Richard Anarfi, CJ Barberan, Jia He
  
  KDD 2024 | August 2024
  
  Publication
- Vec2Node: Self-training with Tensor Augmentation for Text Classification with Few Labels
  
  Sara Abdali
  
  European Conference on Principles of Data Mining and Knowledge Discovery | September 2022
  
  ECML-PKDD Scholarship Award
  
  Publication
- Self-reflecting Large Language Models: A Hegelian Dialectical Approach
  
  Sara Abdali, Can Goksen, Michael Solodko, Saeed Amizadeh, Kazuhito Koishida
  
  ArXiv | January 2025
  
  Publication Publication
- Extracting Self-Consistent Causal Insights from Users Feedback with LLMs and In-context Learning
  
  Sara Abdali, Anjali Parikh, Steve Lim, Emre Kiciman
  
  ArXiv | December 2023
  
  DOI Publication Publication

Sara Abdali

出版物

Hegelian Self-Reflection for Improved Mathematical and Symbolic Reasoning, and Scientific Discovery in Large Language Models

Echoverse: Deep, Evolving Environments for Training Computer-Use Agents at Scale

Hierarchical Self-Attention: Generalizing Neural Attention Mechanics to Multi-Scale Problems

Misaligned Roles, Misplaced Images: Structural Input Perturbations Expose Multimodal Alignment Blind Spots

Self-reflecting Large Language Models: A Hegelian Dialectical Approach

Windows Agent Arena: Evaluating Multi-Modal OS Agents at Scale

Decoding the AI Pen: Techniques and Challenges in Detecting AI-Generated Text

Can LLMs be Fooled? Investigating Vulnerabilities in LLMs

Securing Large Language Models: Threats, Vulnerabilities and Responsible Practices

Extracting Self-Consistent Causal Insights from Users Feedback with LLMs and In-context Learning

Vec2Node: Self-training with Tensor Augmentation for Text Classification with Few Labels

Hegelian Self-Reflection for Improved Mathematical and Symbolic Reasoning, and Scientific Discovery in Large Language Models

Echoverse: Deep, Evolving Environments for Training Computer-Use Agents at Scale

Hierarchical Self-Attention: Generalizing Neural Attention Mechanics to Multi-Scale Problems

Misaligned Roles, Misplaced Images: Structural Input Perturbations Expose Multimodal Alignment Blind Spots

Self-reflecting Large Language Models: A Hegelian Dialectical Approach

Windows Agent Arena: Evaluating Multi-Modal OS Agents at Scale

Decoding the AI Pen: Techniques and Challenges in Detecting AI-Generated Text

Can LLMs be Fooled? Investigating Vulnerabilities in LLMs

Securing Large Language Models: Threats, Vulnerabilities and Responsible Practices

Extracting Self-Consistent Causal Insights from Users Feedback with LLMs and In-context Learning

Vec2Node: Self-training with Tensor Augmentation for Text Classification with Few Labels

Hegelian Self-Reflection for Improved Mathematical and Symbolic Reasoning, and Scientific Discovery in Large Language Models

Self-reflecting Large Language Models: A Hegelian Dialectical Approach

Decoding the AI Pen: Techniques and Challenges in Detecting AI-Generated Text

Can LLMs be Fooled? Investigating Vulnerabilities in LLMs

Hegelian Self-Reflection for Improved Mathematical and Symbolic Reasoning, and Scientific Discovery in Large Language Models

Hegelian Self-Reflection for Improved Mathematical and Symbolic Reasoning, and Scientific Discovery in Large Language Models

Decoding the AI Pen: Techniques and Challenges in Detecting AI-Generated Text

Can LLMs be Fooled? Investigating Vulnerabilities in LLMs

Self-reflecting Large Language Models: A Hegelian Dialectical Approach

Can LLMs be Fooled? Investigating Vulnerabilities in LLMs

Securing Large Language Models: Threats, Vulnerabilities and Responsible Practices

Hegelian Self-Reflection for Improved Mathematical and Symbolic Reasoning, and Scientific Discovery in Large Language Models

Can LLMs be Fooled? Investigating Vulnerabilities in LLMs

Securing Large Language Models: Threats, Vulnerabilities and Responsible Practices

Echoverse: Deep, Evolving Environments for Training Computer-Use Agents at Scale

Hierarchical Self-Attention: Generalizing Neural Attention Mechanics to Multi-Scale Problems

Misaligned Roles, Misplaced Images: Structural Input Perturbations Expose Multimodal Alignment Blind Spots

Windows Agent Arena: Evaluating Multi-Modal OS Agents at Scale

Decoding the AI Pen: Techniques and Challenges in Detecting AI-Generated Text

Vec2Node: Self-training with Tensor Augmentation for Text Classification with Few Labels

Self-reflecting Large Language Models: A Hegelian Dialectical Approach

Extracting Self-Consistent Causal Insights from Users Feedback with LLMs and In-context Learning