Related papers: Theory of Space: Can Foundation Models Construct S…

In an interactive belief model, are the players "commonly meta-certain" of the model itself? This paper formalizes such implicit "common meta-certainty" assumption. To that end, the paper expands the objects of players' beliefs from events…

Modern generative models demonstrate impressive capabilities, likely stemming from an ability to identify and manipulate abstract concepts underlying their training data. However, fundamental questions remain: what determines the concepts a…

Spatial reasoning is central to navigation and robotics, yet measuring model capabilities on these tasks remains difficult. Existing benchmarks evaluate models in a one-shot setting, requiring full solution generation in a single response,…

Biological infants are naturally curious and try to comprehend their physical surroundings by interacting, in myriad multisensory ways, with different objects - primarily macroscopic solid objects - around them. Through their various…

Foundation models have revolutionized artificial intelligence, setting new benchmarks in performance and enabling transformative capabilities across a wide range of vision and language tasks. However, despite the prevalence of…

This paper introduces an open-source simulator, BeliefNest, designed to enable embodied agents to perform collaborative tasks by leveraging Theory of Mind. BeliefNest dynamically and hierarchically constructs simulators within a Minecraft…

Model-Based Reinforcement Learning distinguishes between physical dynamics models operating on proprioceptive inputs and latent dynamics models operating on high-dimensional image observations. A prominent latent approach is the Recurrent…

Common approaches for task-agnostic exploration learn tabula-rasa --the agent assumes isolated environments and no prior knowledge or experience. However, in the real world, agents learn in many environments and always come with prior…

Research on the so-called "free-energy principle'' (FEP) in cognitive neuroscience is becoming increasingly high-profile. To date, introductions to this theory have proved difficult for many readers to follow, but it depends mainly upon two…

Learning in environments with sparse rewards remains a fundamental challenge in reinforcement learning. Artificial curiosity addresses this limitation through intrinsic rewards to guide exploration, however, the precise formulation of these…

Spatial understanding is a critical capability for vision foundation models. While recent advances in large vision models or vision-language models (VLMs) have expanded recognition capabilities, most benchmarks emphasize localization…

Information gathering while interacting with other agents under sensing and motion uncertainty is critical in domains such as driving, service robots, racing, or surveillance. The interests of agents may be at odds with others, resulting in…

A growing body of work makes use of probing to investigate the working of neural models, often considered black boxes. Recently, an ongoing debate emerged surrounding the limitations of the probing paradigm. In this work, we point out the…

Human learning and intelligence work differently from the supervised pattern recognition approach adopted in most deep learning architectures. Humans seem to learn rich representations by exploration and imitation, build causal models of…

Animal navigation research posits that organisms build and maintain internal spatial representations, or maps, of their environment. We ask if machines -- specifically, artificial intelligence (AI) navigation agents -- also build implicit…

The mysterious phenomenon of consciousness, after having been the subject of philosophic attention for few millennia, has drawn much scientific curiosity in recent decades; and many brilliant minds of various areas of sciences are trying to…

This paper considers neural representation through the lens of active inference, a normative framework for understanding brain function. It delves into how living organisms employ generative models to minimize the discrepancy between…

When confronting a spatio-temporal regression, it is sensible to feed the model with any available prior information about the spatial dimension. For example, it is common to define the architecture of neural networks based on spatial…

In model-based reinforcement learning, generative and temporal models of environments can be leveraged to boost agent performance, either by tuning the agent's representations during training or via use as part of an explicit planning…

Active inference, a neurally-inspired model for inferring actions based on the free energy principle (FEP), has been proposed as a unifying framework for understanding perception, action, and learning in the brain. Active inference has…