I’m excited to be spending the next two weeks in this incredible city for a research visit at the University of Zurich. I’ll be based in the Digital Linguistics Lab, collaborating with the team. My visit involves research collaborations to improve LLM alignment with eye-tracking data and establishing best practices for collecting high-quality signals, getting …
The 2025 ACM Symposium on Eye Tracking Research and Applications (ETRA), the premier conference in the field of eye-tracking, was held in Tokyo, Japan, from May 26th to May 29th. The event brought together researchers and practitioners to explore cutting-edge developments and innovative applications shaping the future of eye-tracking technology. It was a great experience, …
To better understand the potential of cognitive data in improving machine learning models, specifically Large Language Models (LLMs), we propose GazeReward, an innovative framework for aligning LLMs with human preferences by incorporating eye-tracking (ET) data into reward modeling. LLMs like GPT-4 [1], Llama 3 [2], and others have revolutionized Natural Language Processing (NLP), excelling in …
Read more “Aligning LLMs with human preferences with eye-tracking rewards”