Madian Khabsa

Researcher, CSE, Meta

Joined

September 2018

Names

Madian Khabsa (Preferred)

Emails

****@madiankhabsa.com (Confirmed)

****@gmail.com (Confirmed)

Personal Links

Homepage

Google Scholar

DBLP

Career & Education History

Researcher

CSE, Meta (meta.com)

2019 – Present

PhD student

Pennsylvania State University (psu.edu)

2010 – 2015

Advisors, Relations & Conflicts

Coworker

Ahmad Hassan

2015 – 2021

PhD Advisor

Lee Giles

2008 – 2015

Expertise

LLM

genai

deep learning

nlp

transformers

classifications

representation learning

2015 – Present

Publications

Beyond Reasoning Gains: Mitigating General Capabilities Forgetting in Large Reasoning Model
Shengjie Bi, Deren Lei, Lijuan Liu, Madian Khabsa, Hoang Phan, Xiaocheng Tang, Xianjun Yang, Yuanshun Yao, Jingyu Zhang
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
Multi-Sample Preference Optimization for Generative Model Alignment
Chaoqi Wang, Zhuokai Zhao, Chen Zhu, Karthik Abinav Sankararaman, Michal Valko, Xuefei Cao, Zhaorun Chen, Madian Khabsa, Yuxin Chen, Hao Ma, Sinong Wang
- Submitted to ICLR 2026
- Readers: Everyone
High Accuracy, Less Talk (HALT): Reliable LLMs through Capability-Aligned Finetuning
Tim Franzmeyer, Archie Sravankumar, Lijuan Liu, Yuning Mao, Rui Hou, Sinong Wang, Jakob Nicolaus Foerster, Luke Zettlemoyer, Madian Khabsa
- ICLR 2026 Poster
- Readers: Everyone
The Perfect Blend: Redefining RLHF with Mixture of Judges
Tengyu Xu, Eryk Helenowski, Karthik Abinav Sankararaman, Di Jin, Kaiyan Peng, Eric Han, Shaoliang Nie, Chen Zhu, Hejia Zhang, Wenxuan Zhou, Zhouhao Zeng, Yun He, Karishma Mandyam, Arya Talebzadeh, Madian Khabsa, Gabriel Cohen, Sinong Wang, Yuandong Tian, Hao Ma, Han Fang
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Preference Optimization with Multi-Sample Comparisons
Chaoqi Wang, Zhuokai Zhao, Chen Zhu, Karthik Abinav Sankararaman, Michal Valko, Xuefei Cao, Zhaorun Chen, Madian Khabsa, Yuxin Chen, Hao Ma, Sinong Wang
- Submitted to ICLR 2025
- Readers: Everyone
On the Equivalence of Graph Convolution and Mixup
Xiaotian Han, Hanqing Zeng, Yu Chen, Shaoliang Nie, Jingzhou Liu, Kanika Narang, Zahra Shakeri, Karthik Abinav Sankararaman, Song Jiang, Madian Khabsa, Qifan Wang, Xia Hu
- Accepted by TMLR
- Readers: Everyone
Effective Long-Context Scaling of Foundation Models
Jingyu Liu, Wenhan Xiong, Igor Molybog, Hejia Zhang, Prajjwal Bhargava, Rui Hou, Louis Martin, Rashi Rungta, Karthik Abinav Sankararaman, Barlas Oguz, Madian Khabsa, Han Fang, Yashar Mehdad, Sharan Narang, Kshitiz Malik, Angela Fan, Shruti Bhosale, Sergey Edunov, Mike Lewis, Sinong Wang et al. (1 additional authors not shown)
- NAACL 2024
- Readers: Everyone
On the Equivalence of Graph Convolution and Mixup
Xiaotian Han, Hanqing Zeng, Yu Chen, Shaoliang Nie, Jingzhou Liu, Kanika Narang, Zahra Shakeri, Karthik Abinav Sankararaman, Song Jiang, Madian Khabsa, Qifan Wang, Xia Hu
- ICLR 2024 Conference Withdrawn Submission
- Readers: Everyone
RoAST: Robustifying Language Models via Adversarial Perturbation with Selective Training
Jaehyung Kim, Yuning Mao, Rui Hou, Hanchao Yu, Davis Liang, Pascale Fung, Qifan Wang, Fuli Feng, Lifu Huang, Madian Khabsa
- EMNLP 2023 Findings
- Readers: Everyone
XLM-V: Overcoming the Vocabulary Bottleneck in Multilingual Masked Language Models
Davis Liang, Hila Gonen, Yuning Mao, Rui Hou, Naman Goyal, Marjan Ghazvininejad, Luke Zettlemoyer, Madian Khabsa
- EMNLP 2023 Main
- Readers: Everyone

View all 23 publications

Co-Authors

View all 102 co-authors