معرفی
Anna Leshinskaya is an Assistant Professor in the Department of Cognitive Sciences at the University of California, Irvine (UCI), and a Fellow at the Center for Neurobiology of Learning & Memory. She is also affiliated with the AI Objectives Institute. She holds a PhD in Cognitive Psychology from Harvard University (2015). Her research focuses on understanding human cognition, its neural basis, and its implications for artificial intelligence. Key areas include causal learning, semantic memory, and cognitive/moral alignment between humans and AI systems.
Education:
- PhD in Cognitive Psychology, Harvard University, 2015
Research Interests:
- Causal schema processing in the lateral temporal cortex
- Relational memory formation in the brain
- Neural representations of moral and hedonic value in large language models
- Integration of event experiences into relational knowledge
Publications Trends: Recent work emphasizes causal reasoning mechanisms (e.g., tool selectivity linked to causal inference) and the application of cognitive principles to evaluate AI alignment. This reflects a shift toward translational research connecting brain science with technological development.
Awards: No specific prizes mentioned, but her work has been published in high-impact journals like Cerebral Cortex and Cognitive Science.
Grants & Labs: Her research is supported by grants related to cognitive neuroscience and AI ethics. She runs a cognitive science lab at UCI, focusing on experimental and computational methods to study human-AI interactions.
Affiliations: Active collaboration with interdisciplinary teams at the AI Objectives Institute to address foundational challenges in AI safety and alignment.
