Related papers: From Kepler to Newton: Inductive Biases Guide Lear…

Physics-inspired neural networks (NNs), such as Hamiltonian or Lagrangian NNs, dramatically outperform other learned dynamics models by leveraging strong inductive biases. These models, however, are challenging to apply to many real world…

This position paper argues that the next generation of artificial intelligence in meteorological and climate sciences must transition from fragmented hybrid heuristics toward a unified paradigm of physics-guided multimodal transformers.…

This paper studies interpretable and fair artificial intelligence architectures for understanding English reading. Introduced transformer-based models, integrating advanced attention mechanisms and gradient-based feature attribution. The…

We focus on the task of future frame prediction in video governed by underlying physical dynamics. We work with models which are object-centric, i.e., explicitly work with object representations, and propagate a loss in the latent space.…

While current AI-driven methods excel at deriving empirical models from individual experiments, a significant challenge remains in uncovering the common fundamental physics that underlie these models -- a task at which human physicists are…

Evolution has resulted in highly developed abilities in many natural intelligences to quickly and accurately predict mechanical phenomena. Humans have successfully developed laws of physics to abstract and model such mechanical phenomena.…

World modelling, i.e. building a representation of the rules that govern the world so as to predict its evolution, is an essential ability for any agent interacting with the physical world. Despite their impressive performance, many…

Artificial intelligence (AI) is commonly depicted as transformative. Yet, after more than a decade of hype, its measurable impact remains modest outside a few high-profile scientific and commercial successes. The 2024 Nobel Prizes in…

The rapid advancement of embodied intelligence and world models has intensified efforts to integrate physical laws into AI systems, yet physical perception and symbolic physics reasoning have developed along separate trajectories without a…

World models have recently re-emerged as a central paradigm for embodied intelligence, robotics, autonomous driving, and model-based reinforcement learning. However, current world model research is often dominated by three partially…

Recent work proposes using world models to generate controlled virtual environments in which AI agents can be tested before deployment to ensure their reliability and safety. However, accurate world models often have high computational…

There are two major approaches to building good machine learning algorithms: feeding lots of data into large models, or picking a model class with an ''inductive bias'' that suits the structure of the data. When taking the second approach…

Recurrent Neural Networks were, until recently, one of the best ways to capture the timely dependencies in sequences. However, with the introduction of the Transformer, it has been proven that an architecture with only attention-mechanisms…

World modelling, i.e. building a representation of the rules that govern the world so as to predict its evolution, is an essential ability for any agent interacting with the physical world. Recent applications of the Transformer…

World models, which explicitly learn environmental dynamics to lay the foundation for planning, reasoning, and decision-making, are rapidly advancing in predicting both physical dynamics and aspects of social behavior, yet predominantly in…

Transformers pretrained via next token prediction learn to factor their world into parts, representing these factors in orthogonal subspaces of the residual stream. We formalize two representational hypotheses: (1) a representation in the…

In recent years, Transformer-based architectures have become the dominant method for Computer Vision applications. While Transformers are explainable and scale well with dataset size, they lack the inductive biases of Convolutional Neural…

A long-standing challenge in Reinforcement Learning is enabling agents to learn a model of their environment which can be transferred to solve other problems in a world with the same underlying rules. One reason this is difficult is the…

Beginning with McCarthy's Advice Taker (1959), AI has pursued the goal of providing a system with explicit, general knowledge and having the system reason over that knowledge. However, expressing the knowledge in a formal (logical or…

Borrowing from the transformer models that revolutionized the field of natural language processing, self-supervised feature learning for visual tasks has also seen state-of-the-art success using these extremely deep, isotropic networks.…