Related papers: From monoliths to modules: Decomposing transducers…

Decomposing knowledge into interchangeable pieces promises a generalization advantage when there are changes in distribution. A learning agent interacting with its environment is likely to be faced with situations requiring novel…

Transformer-based architectures have shown remarkable performance in vision and language tasks but pose unique challenges for safety-critical applications. This paper presents a conceptual framework for integrating Transformers into…

The ability to decompose scenes in terms of abstract building blocks is crucial for general intelligence. Where those basic building blocks share meaningful properties, interactions and other regularities across scenes, such decompositions…

In the rapidly evolving landscape of autonomous driving, the capability to accurately predict future events and assess their implications is paramount for both safety and efficiency, critically aiding the decision-making process. World…

Developing effective world models is crucial for creating artificial agents that can reason about and navigate complex environments. In this paper, we investigate a deep supervision technique for encouraging the development of a world model…

Computer models are indispensable tools for understanding the Earth system. While high-resolution operational models have achieved many successes, they exhibit persistent biases, particularly in simulating extreme events and statistical…

Deep neural networks have been successful in many reinforcement learning settings. However, compared to human learners they are overly data hungry. To build a sample-efficient world model, we apply a transformer to real-world episodes in an…

In this paper, we examine the problem of real-world image deblurring and take into account two key factors for improving the performance of the deep image deblurring model, namely, training data synthesis and network architecture design.…

We propose a neural network architecture, called TransNet, that combines planning and model learning for solving Partially Observable Markov Decision Processes (POMDPs) with non-uniform system dynamics. The past decade has seen a…

Explainability techniques for data-driven predictive models based on artificial intelligence and machine learning algorithms allow us to better understand the operation of such systems and help to hold them accountable. New transparency…

World Models help Artificial Intelligence (AI) predict outcomes, reason about its environment, and guide decision-making. While widely used in reinforcement learning, they lack the structured, adaptive representations that even young…

World models are central to building agents that can reason, plan, and generalize beyond their training data. However, research on world models is currently fragmented, with disparate codebases, data pipelines, and evaluation protocols…

Long-horizon embodied planning is challenging because the world does not only change through an agent's actions: exogenous processes (e.g., water heating, dominoes cascading) unfold concurrently with the agent's actions. We propose a…

Training a Neural Network (NN) with lots of parameters or intricate architectures creates undesired phenomena that complicate the optimization process. To address this issue we propose a first modular approach to NN design, wherein the NN…

AI-native 6G visions increasingly invoke wireless foundation models, large multimodal models, and wireless world models as the natural endpoint of AI-native networking, drawing an analogy to recent developments in large language models…

Transformers have been widely applied in text classification. Unfortunately, real-world data contain anomalies and noisy labels that cause challenges for state-of-art Transformers. This paper proposes Protoformer, a novel self-learning…

The study of representation universality in AI models reveals growing convergence across domains, modalities, and architectures. However, the practical applications of representation universality remain largely unexplored. We bridge this…

In complex inferential tasks like question answering, machine learning models must confront two challenges: the need to implement a compositional reasoning process, and, in many applications, the need for this reasoning process to be…

World models have garnered significant attention as a promising research direction in artificial intelligence, yet a clear and unified definition remains lacking. In this paper, we introduce OpenWorldLib, a comprehensive and standardized…

Identifying and understanding modular organizations is centrally important in the study of complex systems. Several approaches to this problem have been advanced, many framed in information-theoretic terms. Our treatment starts from the…