Thoughts You Can Trust? Evaluating the Faithfulness of Model-Generated Explanations and Their Effects on Human Performance

👩‍🏫 Speaker: Dr. Oana-Maria Camburu

📅 Time: 2025/11/12

Learning and Data in the Age of LLMs: Theoretical Insights into Knowledge Distillation, Test-Time-Training and Synthetic Data Selection

👨‍🏫 Speaker: Professor Marco Mondelli

📅 Time: 2025/10/22

Extracting and Utilizing Interpretation in Large Language Models

👨‍🎓 Speaker: Xuansheng Wu

📅 Time: 2025/10/15

Personalized Large Language Models: Recent Progress and Future Directions

👩‍🎓 Speaker: Jiahong Liu

📅 Time: 2025/09/17

SPECTRA: Faster Large Language Model Inference with Optimized Internal and External Speculation

👨‍🏫 Speaker: Professor Le-Minh Nguyen

📅 Time: 2025/07/16