3 papers
cs.AI2025
Language Models Are Capable of Metacognitive Monitoring and Control of Their Internal Activations
Li Ji-An, Hua-Dong Xiong, Robert C. Wilson +2
Large language models (LLMs) can sometimes report the strategies they actually use to solve tasks, yet at other times seem unable to recognize those strategies that govern their be…
cs.LG2025
Deep Learning without Weight Symmetry
Li Ji-An, Marcus K. Benna
Backpropagation, a foundational algorithm for training artificial neural networks, predominates in contemporary deep learning. Although highly successful, it is widely considered b…
cs.CL2024
Linking In-context Learning in Transformers to Human Episodic Memory
Li Ji-An, Corey Y. Zhou, Marcus K. Benna +1
Understanding connections between artificial and biological intelligent systems can reveal fundamental principles of general intelligence. While many artificial intelligence models…