Related papers: How higher goals are constructed and collapse unde…
In the present monograph we formulate a simple model for heat transfer in living tissue with self - regulation. The initial point of the model is the governing equations describing heat transfer in living tissue at the mesoscopic level,…
Image and video generative models that are pre-trained on Internet-scale data can greatly increase the generalization capacity of robot learning systems. These models can function as high-level planners, generating intermediate subgoals for…
It is not always clear how to adjust for control data in causal inference, balancing the goals of reducing bias and variance. We show how, in a setting with repeated experiments, Bayesian hierarchical modeling yields an adaptive procedure…
Despite their apparent diversity, modern machine learning methods can be reduced to a remarkably simple core principle: learning is achieved by continuously optimizing parameters to minimize or maximize a scalar objective function. This…
Most of the grand challenges of humanity today involve complex agent-based systems, such as epidemiology, economics or ecology. However, remains as a pending task the challenge of identifying the general principles underlying their…
Learning goal conditioned control in the real world is a challenging open problem in robotics. Reinforcement learning systems have the potential to learn autonomously via trial-and-error, but in practice the costs of manual reward design,…
Many decision-making problems naturally exhibit pronounced structures inherited from the characteristics of the underlying environment. In a Markov decision process model, for example, two distinct states can have inherently related…
How to behave efficiently and flexibly is a central problem for understanding biological agents and creating intelligent embodied AI. It has been well known that behavior can be classified as two types: reward-maximizing habitual behavior,…
Specialization and hierarchical organization are important features of efficient collaboration in economical, artificial, and biological systems. Here, we investigate the hypothesis that both features can be explained by the fact that each…
Intensive longitudinal biomarker data are increasingly common in scientific studies that seek temporally granular understanding of the role of behavioral and physiological factors in relation to outcomes of interest. Intensive longitudinal…
We study a general and simple model for communication processes. In the model, agents in a network (in particular, an organization) interchange information packets following simple rules that take into account the limited capability of the…
Educators teaching entry-level university engineering modules face the challenge of identifying which topics students find most difficult and how to support diverse student needs effectively. This study demonstrates a rigorous yet…
Demographic studies of cosmic populations must contend with measurement errors and selection effects. We survey some of the key ideas astronomers have developed to deal with these complications, in the context of galaxy surveys and the…
Inspired by cellular growth and self-organization, Neural Cellular Automata (NCAs) have been capable of "growing" artificial cells into images, 3D structures, and even functional machines. NCAs are flexible and robust computational systems…
We propose a model of inference and heuristic decision-making in groups that is rooted in the Bayes rule but avoids the complexities of rational inference in partially observed environments with incomplete information, which are…
Large language models (LLMs) are increasingly deployed with hierarchical instruction schemes, where certain instructions (e.g., system-level directives) are expected to take precedence over others (e.g., user messages). Yet, we lack a…
Bow-tie or hourglass structure is a common architectural feature found in biological and technological networks. A bow-tie in a multi-layered structure occurs when intermediate layers have much fewer components than the input and output…
Structural hierarchy, in which materials possess distinct features on multiple length scales, is ubiquitous in nature; diverse biological materials, such as bone, cellulose, and muscle, have as many as ten hierarchical levels. Structural…
Decision-making in complex, continuous multi-task environments is often hindered by the difficulty of obtaining accurate models for planning and the inefficiency of learning purely from trial and error. While precise environment dynamics…
One of the challenges of open-ended learning in robots is the need to autonomously discover goals and learn skills to achieve them. However, when in lifelong learning settings, it is always desirable to generate sub-goals with their…