Linh Le

PhD student@University of queensland·澳大利亚·OpenReview

研究方向

Text Classification · Fairness Evaluation Metrics · Dementia Detection · EEG · MRI · Reinforcement Learning · NER · Active Learning · Computer Vision · NLP

3.5

Latent Personality Alignment: Improving harmlessness without mentioning harms

ICLR 2026Withdrawn

一作

3.0

House, G.P.T.: Diagnosing Pathological Chain-of-Thought in Reasoning Models

合作者 (10)

Mohamed Amine Merzouk