Rose E. Wang

TL;DR: The authors provides a thorough account of the opportunities and risks of foundation models, ranging from their capabilities (e.g., language, vision, robotics, reasoning, human interaction) and technical principles(e. g.g. model architectures, training procedures, data, systems, security, evaluation, theory) to their applications.

TL;DR: A deep recurrent multiagent actor-critic framework (R-MADDPG) for handling multiagent coordination under partial observable set-tings and limited communication and demonstrates that the resulting framework learns time dependencies for sharing missing observations, handling resource limitations, and developing different communication patterns among agents.

TL;DR: Bayesian Delegation is developed, a decentralized multi-agent learning mechanism that enables agents to rapidly infer the hidden intentions of others by inverse planning and makes inferences similar to human observers about the intent of others.

TL;DR: Bayesian Delegation as discussed by the authors enables agents to rapidly infer the hidden intentions of others by inverse planning, enabling agents to coordinate both their high-level plans (e.g., what sub-task they should work on) and their low-level actions (i.e., avoiding getting in each other's way).

TL;DR: The authors developed a new framework, Human-AI Language-based Interaction Evaluation (HALIE), that defines the components of interactive systems and dimensions to consider when designing evaluation metrics.