13 citations · 13 across the 2 of their papers we have counts for
4 papers
Efficiency and robustness partition the solution space for memory in recurrent networks
William Qian, Cengiz Pehlevan
In computational neuroscience, task-trained recurrent neural networks (RNNs) are commonly used as a testbed for exploring the space of recurrent circuit solutions compatible with a…
Discovering alternative solutions beyond the simplicity bias in recurrent neural networks
William Qian, Cengiz Pehlevan
Training recurrent neural networks (RNNs) to perform neuroscience-style tasks has become a popular way to generate hypotheses for how neural circuits in the brain might perform com…
Deep RL Needs Deep Behavior Analysis: Exploring Implicit Planning by Model-Free Agents in Open-Ended Environments
Riley Simmons-Edler, Ryan P. Badman, Felix Baastad Berg +5
Understanding the behavior of deep reinforcement learning (DRL) agents -particularly as task and agent sophistication increase- requires more than simple comparison of reward curve…
The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning
Nathaniel Li, Alexander Pan, Anjali Gopal +54
The White House Executive Order on Artificial Intelligence highlights the risks of large language models (LLMs) empowering malicious actors in developing biological, cyber, and che…