Matthew Lyle Olson

21 papers A* 2Journal 14Unranked 5
YearRankTypeTitle / Venue / Authors
2026 J jnl
Data-Centric Interpretability for LLM-based Multi-Agent Reinforcement Learning.
CoRR
John Yan, Michael Yu, Yuqi Sun, Alexander Duffy, Tyler Marques, Matthew Lyle Olson
2026 A* conf
Democratizing Diplomacy: A Harness for Evaluating Any Large Language Model on Full-Press Diplomacy.
AAAI
Alexander Duffy, Samuel J. Paech, Ishana Shastri, Elizabeth Karpinski, Baptiste Alloui-Cros, Tyler Marques, Matthew Lyle Olson
2026 A* conf
LieCraft: A Multi-Agent Framework for Evaluating Deceptive Capabilities in Language Models.
AAAI
Matthew Lyle Olson, Neale Ratzlaff, Musashi Hinck, Tri Nguyen, Vasudev Lal, Joseph Campbell, Simon Stepputtis, Shao-Yen Tseng
2026 J jnl
LieCraft: A Multi-Agent Framework for Evaluating Deceptive Capabilities in Language Models.
CoRR
Matthew Lyle Olson, Neale Ratzlaff, Musashi Hinck, Tri Nguyen, Vasudev Lal, Joseph Campbell, Simon Stepputtis, Shao-Yen Tseng
2025 — conf
Analyzing Hierarchical Structure in Vision Models with Sparse Autoencoders.
CVPR Workshops
Matthew Lyle Olson, Musashi Hinck, Neale Ratzlaff, Changbai Li, Phillip Howard, Vasudev Lal, Shao-Yen Tseng
2025 J jnl
Analyzing Hierarchical Structure in Vision Models with Sparse Autoencoders.
CoRR
Matthew Lyle Olson, Musashi Hinck, Neale Ratzlaff, Changbai Li, Phillip Howard, Vasudev Lal, Shao-Yen Tseng
2025 J jnl
Bayesian Social Deduction with Graph-Informed Language Models.
CoRR
Shahab Rahimirad, Guven Gergerli, Lucia Romero, Angela Qian, Matthew Lyle Olson, Simon Stepputtis, Joseph Campbell
2025 — conf
Debias Your Large Multi-Modal Model at Test-Time via Non-Contrastive Visual Attribute Steering.
ICCVW
Neale Ratzlaff, Matthew Lyle Olson, Musashi Hinck, Shao-Yen Tseng, Vasudev Lal, Phillip Howard
2025 J jnl
Democratizing Diplomacy: A Harness for Evaluating Any Large Language Model on Full-Press Diplomacy.
CoRR
Alexander Duffy, Samuel J. Paech, Ishana Shastri, Elizabeth Karpinski, Baptiste Alloui-Cros, Tyler Marques, Matthew Lyle Olson
2025 — conf
Probing Semantic Routing in Large Mixture-of-Expert Models.
EMNLP (Findings)
Matthew Lyle Olson, Neale Ratzlaff, Musashi Hinck, Man Luo, Sungduk Yu, Chendi Xue, Vasudev Lal
2025 J jnl
Probing the Representational Power of Sparse Autoencoders in Vision Models.
CoRR
Matthew Lyle Olson, Musashi Hinck, Neale Ratzlaff, Changbai Li, Phillip Howard, Vasudev Lal, Shao-Yen Tseng
2025 J jnl
Semantic Specialization in MoE Appears with Scale: A Study of DeepSeek R1 Expert Specialization.
CoRR
Matthew Lyle Olson, Neale Ratzlaff, Musashi Hinck, Man Luo, Sungduk Yu, Chendi Xue, Vasudev Lal
2024 J jnl
ClimDetect: A Benchmark Dataset for Climate Change Detection and Attribution.
CoRR
Sungduk Yu, Brian L. White, Anahita Bhiwandiwalla, Musashi Hinck, Matthew Lyle Olson, Tung Nguyen, Vasudev Lal
2024 J jnl
Debias your Large Multi-Modal Model at Test-Time with Non-Contrastive Visual Attribute Steering.
CoRR
Neale Ratzlaff, Matthew Lyle Olson, Musashi Hinck, Estelle Aflalo, Shao-Yen Tseng, Vasudev Lal, Phillip Howard
2024 J jnl
Debiasing Large Vision-Language Models by Ablating Protected Attribute Representations.
CoRR
Neale Ratzlaff, Matthew Lyle Olson, Musashi Hinck, Shao-Yen Tseng, Vasudev Lal, Phillip Howard
2024 — conf
LVLM-Intrepret: An Interpretability Tool for Large Vision-Language Models.
XAI4CV
Gabriela Ben Melech Stan, Estelle Aflalo, Raanan Yehezkel Rohekar, Anahita Bhiwandiwalla, Shao-Yen Tseng, Matthew Lyle Olson, Yaniv Gurwicz, Chenfei Wu, Nan Duan, Vasudev Lal
2024 J jnl
LVLM-Intrepret: An Interpretability Tool for Large Vision-Language Models.
CoRR
Gabriela Ben Melech Stan, Raanan Yehezkel Rohekar, Yaniv Gurwicz, Matthew Lyle Olson, Anahita Bhiwandiwalla, Estelle Aflalo, Chenfei Wu, Nan Duan, Shao-Yen Tseng, Vasudev Lal
2024 J jnl
Steering Large Language Models to Evaluate and Amplify Creativity.
CoRR
Matthew Lyle Olson, Neale Ratzlaff, Musashi Hinck, Shao-Yen Tseng, Vasudev Lal
2024 J jnl
Super-Resolution without High-Resolution Labels for Black Hole Simulations.
CoRR
Thomas Helfer, Thomas D. P. Edwards, Jessica Dafflon, Kaze W. K. Wong, Matthew Lyle Olson
2024 J jnl
Why do LLaVA Vision-Language Models Reply to Images in English?
CoRR
Musashi Hinck, Carolin Holtermann, Matthew Lyle Olson, Florian Schneider, Sungduk Yu, Anahita Bhiwandiwalla, Anne Lauscher, Shao-Yen Tseng, Vasudev Lal
2018 — conf
Reduce Before You Localize: Delta-Debugging and Spectrum-Based Fault Localization.
ISSRE Workshops
Arpit Christi, Matthew Lyle Olson, Mohammad Amin Alipour, Alex Groce