Wenhao Zhang

Continuous Attractor Neural Networks: Candidate of a Canonical Model for Neural Information Representation

2016 · F1000Research

Owing to its many computationally desirable properties, the model of continuous attractor neural networks (CANNs) has been successfully applied to describe the encoding of simple continuous features in neural systems, such as orientation, moving direction, …

Canonical cortical circuits: A unified sampling machine for static and dynamic inference

2025 · bioRxiv (Cold Spring Harbor Laboratory)

A bstract The brain lives in an ever-changing world and needs to infer the dynamic evolution of latent states from noisy sensory inputs. Exploring how canonical recurrent neural circuits in the brain realize dynamic inference …

Towards Monotonic Improvement in In-Context Reinforcement Learning

2025 · arXiv (Cornell University)

In-Context Reinforcement Learning (ICRL) has emerged as a promising paradigm for developing agents that can rapidly adapt to new tasks by leveraging past experiences as context, without updating their parameters. Recent approaches train large sequence …