6 accepted papers
Large Language Models (LLMs) exhibit impressive general-purpose capabilities but also introduce serious safety risks, particularly the potential for deception as models acquire increased agency and human oversight diminishes. In this work, we present LieCraft: a novel evaluation framework and sandbo
In the past year, large ( >100 B parameter) mixture-of-expert (MoE) models have become increasingly common in the open domain. While their advantages are often framed in terms of efficiency, prior work has also explored functional differentiation through routing behavior. We investigate whether expe
Recently, particle-based variational inference (ParVI) methods have gained interest because they can avoid arbitrary parametric assumptions that are common in variational inference. However, many ParVI approaches do not allow arbitrary sampling from the posterior, and the few that do allow such samp…
Reward function specification can be difficult. Rewarding the agent for making a widget may be easy, but penalizing the multitude of possible negative side effects is hard. In toy environments, Attainable Utility Preservation (AUP) avoided side effects by penalizing shifts in the ability to achieve…
Efficient exploration remains a challenging problem in reinforcement learning, especially for those tasks where rewards from environments are sparse. In this work, we introduce an exploration approach based on a novel implicit generative modeling algorithm to estimate a Bayesian uncertainty of the a…
We introduce HyperGAN, a generative model that learns to generate all the parameters of a deep neural network. HyperGAN first transforms low dimensional noise into a latent space, which can be sampled from to obtain diverse, performant sets of parameters for a target architecture. We utilize an arch…