Search Results for author: Guangyu Robert Yang

Found 9 papers, 3 papers with code

Lyfe Agents: Generative agents for low-cost real-time social interactions

no code implementations3 Oct 2023 Zhao Kaiya, Michelangelo Naim, Jovana Kondic, Manuel Cortes, Jiaxin Ge, Shuying Luo, Guangyu Robert Yang, Andrew Ahn

Meanwhile, our techniques enabled Lyfe Agents to operate at a computational cost 10-100 times lower than existing alternatives.

Dual policy as self-model for planning

no code implementations7 Jun 2023 Jaesung Yoo, Fernanda De La Torre, Guangyu Robert Yang

In such dual-policy agents, a model-free policy and a distilled policy are used for model-free actions and planned actions, respectively.

Decision Making

Neural Foundations of Mental Simulation: Future Prediction of Latent Representations on Dynamic Scenes

1 code implementation NeurIPS 2023 Aran Nayebi, Rishi Rajalingham, Mehrdad Jazayeri, Guangyu Robert Yang

In particular, we find that neural responses are currently best predicted by models trained to predict the future state of their environment in the latent space of pretrained foundation models optimized for dynamic scenes in a self-supervised manner.

Future prediction

Biological key-value memory networks

no code implementations NeurIPS 2021 Danil Tyulmankov, Ching Fang, Annapurna Vadaparty, Guangyu Robert Yang

In neuroscience, classical Hopfield networks are the standard biologically plausible model of long-term memory, relying on Hebbian plasticity for storage and attractor dynamics for recall.

Biological learning in key-value memory networks

no code implementations NeurIPS 2021 Danil Tyulmankov, Ching Fang, Annapurna Vadaparty, Guangyu Robert Yang

In neuroscience, classical Hopfield networks are the standard biologically plausible model of long-term memory, relying on Hebbian plasticity for storage and attractor dynamics for recall.

Artificial neural networks for neuroscientists: A primer

1 code implementation1 Jun 2020 Guangyu Robert Yang, Xiao-Jing Wang

Artificial neural networks (ANNs) are essential tools in machine learning that have drawn increasing attention in neuroscience.

Understanding the functional and structural differences across excitatory and inhibitory neurons

no code implementations25 Sep 2019 Sun Minni, Li Ji-An, Theodore Moskovitz, Grace Lindsay, Kenneth Miller, Mario Dipoppa, Guangyu Robert Yang

We found that neurons that project to higher-order areas will have greater stimulus selectivity, regardless of whether they are excitatory or not.

A Dataset and Architecture for Visual Reasoning with a Working Memory

1 code implementation ECCV 2018 Guangyu Robert Yang, Igor Ganichev, Xiao-Jing Wang, Jonathon Shlens, David Sussillo

COG is much simpler than the general problem of video analysis, yet it addresses many of the problems relating to visual and logical reasoning and memory -- problems that remain challenging for modern deep learning architectures.

Logical Reasoning Visual Question Answering (VQA) +1

Cannot find the paper you are looking for? You can Submit a new open access paper.