Related papers: Dropout's Dream Land: Generalization from Learned …

Domain generalization aims to learn a predictive model from multiple different but related source tasks that can generalize well to a target task without the need of accessing any target data. Existing domain generalization methods ignore…

Language agents based on large language models (LLMs) have demonstrated great promise in automating web-based tasks. Recent work has shown that incorporating advanced planning algorithms, e.g., tree search, is advantageous over reactive…

World models aim to capture the states and dynamics of an environment in a compact latent space. Moreover, using Boolean state representations is particularly useful for search heuristics and symbolic reasoning and planning. Existing…

Large language model (LLM) agents trained using reinforcement learning has achieved superhuman performance in low-cost environments like games, mathematics, and coding. However, these successes have not translated to complex domains where…

World models have recently emerged as a promising approach to reinforcement learning (RL), achieving state-of-the-art performance across a wide range of visual control tasks. This work aims to obtain a deep understanding of the robustness…

The objective of domain generalization (DG) is to enable models to be robust against domain shift. DG is crucial for deploying vision-language models (VLMs) in real-world applications, yet most existing methods rely on domain labels that…

Deep learning models evolve through training to learn the manifold in which the data exists to satisfy an objective. It is well known that evolution leads to different final states which produce inconsistent predictions of the same test…

Dropout is a standard training technique for neural networks that consists of randomly deactivating units at each step of their gradient-based training. It is known to improve performance in many settings, including in the large-scale…

Zero-shot generalization (ZSG) to unseen dynamics is a major challenge for creating generally capable embodied agents. To address the broader challenge, we start with the simpler setting of contextual reinforcement learning (cRL), assuming…

Despite remarkable success in a variety of applications, it is well-known that deep learning can fail catastrophically when presented with out-of-distribution data. Toward addressing this challenge, we consider the domain generalization…

Imitation learning has emerged as a promising approach towards building generalist robots. However, scaling imitation learning for large robot foundation models remains challenging due to its reliance on high-quality expert demonstrations.…

The rise of deep learning has caused a paradigm shift in robotics research, favoring methods that require large amounts of data. Unfortunately, it is prohibitively expensive to generate such data sets on a physical platform. Therefore,…

World models represent a paradigm shift in generative AI, pursuing predictive understanding and controllable simulation of environments in a structured and generalizable way. We present World Machine, a generative world-modeling…

Synthetic data is a scalable alternative to manual supervision, but it requires overcoming the sim-to-real domain gap. This discrepancy between virtual and real worlds is addressed by two seemingly opposed approaches: improving the realism…

We prove two universal approximation theorems for a range of dropout neural networks. These are feed-forward neural networks in which each edge is given a random $\{0,1\}$-valued filter, that have two modes of operation: in the first each…

Symbolic world models (e.g., PDDL domains or executable simulators) are central to model-based planning, but training LLMs to generate such world models is limited by the lack of large-scale verifiable supervision. Current approaches rely…

The capacity of an embodied agent to understand, predict, and interact with its environment is fundamentally contingent on an internal world model. This paper introduces a novel framework for investigating the formation and adaptation of…

Developing control policies in simulation is often more practical and safer than directly running experiments in the real world. This applies to policies obtained from planning and optimization, and even more so to policies obtained from…

Existing domain generalization aims to learn a generalizable model to perform well even on unseen domains. For many real-world machine learning applications, the data distribution often shifts gradually along domain indices. For example, a…

Learning Machines is developing a flexible, cross-industry, advanced analytics platform, targeted during stealth-stage at a limited number of specific vertical applications. In this paper, we aim to integrate a general machine system to…