Recent work has considered whether large language models (LLMs) can function as
planners: given a task, generate a plan. We investigate whether LLMs can serve as …

Goal-conditioned reinforcement learning endows an agent with a large variety of skills, but it
often struggles to solve tasks that require more temporally extended reasoning. In this work …

Both Minsky's" society of mind" and Schmidhuber's" learning to think" inspire diverse
societies of large multimodal neural networks (NNs) that solve problems by interviewing …

Everyday tasks of long-horizon and comprising a sequence of multiple implicit subtasks still
impose a major challenge in offline robot control. While a number of prior methods aimed to …

We present a visually grounded hierarchical planning algorithm for long-horizon
manipulation tasks. Our algorithm offers a joint framework of neuro-symbolic task planning …

Simulation is the key to scaling up validation and verification for robotic systems such as
autonomous vehicles. Despite advances in high-fidelity physics and sensor simulation, a …

Planning, the ability to analyze the structure of a problem in the large and decompose it into
interrelated subproblems, is a hallmark of human intelligence. While deep reinforcement …

Deep learning has enabled algorithms to generate realistic images. However, accurately
predicting long video sequences requires understanding long-term dependencies and …

Current model-based reinforcement learning methods struggle when operating from
complex visual scenes due to their inability to prioritize task-relevant features. To mitigate …

The use of broad datasets has proven to be crucial for generalization for a wide range of
fields. However, how to effectively make use of diverse multi-task data for novel downstream …