Related papers: Deterministic World Models for Verification of Clo…
The capability of imagining internally with a mental model of the world is vitally important for human cognition. If a machine intelligent agent can learn a world model to create a "dream" environment, it can then internally ask what-if…
World models derived from large-scale video generative pre-training have emerged as a promising paradigm for generalist robot policy learning. However, standard approaches often focus on high-fidelity RGB video prediction, this can result…
Recent generative video world models aim to simulate visual environment evolution, allowing an observer to interactively explore the scene via camera control. However, they implicitly assume that the world only evolves within the observer's…
Deep Generative Models (DGMs) are versatile tools for learning data representations while adequately incorporating domain knowledge such as the specification of conditional probability distributions. Recently proposed DGMs tackle the…
Flow matching models have shown great potential in image generation tasks among probabilistic generative models. However, most flow matching models in the literature do not explicitly utilize the underlying clustering structure in the…
Deep neural networks can be trained to be efficient and effective controllers for dynamical systems; however, the mechanics of deep neural networks are complex and difficult to guarantee. This work presents a general approach for providing…
When solving inverse problems in geophysical imaging, deep generative models (DGMs) may be used to enforce the solution to display highly structured spatial patterns which are supported by independent information (e.g. the geological…
Variational inference methods for latent variable statistical models have gained popularity because they are relatively fast, can handle large data sets, and have deterministic convergence guarantees. However, in practice it is unclear…
Restricted Boltzmann Machines are generative models that consist of a layer of hidden variables connected to another layer of visible units, and they are used to model the distribution over visible variables. In order to gain a higher…
Learning predictive models from high-dimensional sensory observations is fundamental for cyber-physical systems, yet the latent representations learned by standard world models lack physical interpretability. This limits their reliability,…
Visual servoing enables robotic systems to perform accurate closed-loop control, which is required in many applications. However, existing methods either require precise calibration of the robot kinematic model and cameras or use neural…
Ensuring model explainability and robustness is essential for reliable deployment of deep vision systems. Current methods for evaluating robustness rely on collecting and annotating extensive test sets. While this is common practice, the…
Graph representation learning is a fundamental problem for modeling relational data and benefits a number of downstream applications. Traditional Bayesian-based graph models and recent deep learning based GNN either suffer from…
World models (WMs) demonstrate strong capabilities in prediction, generation, and planning tasks. Existing WMs primarily focus on unstructured data and cannot leverage the ubiquitous structured data, often represented as graphs, in the…
We present an architecture which lets us train deep, directed generative models with many layers of latent variables. We include deterministic paths between all latent variables and the generated output, and provide a richer set of…
World Action Models (WAMs) have emerged as a promising paradigm for robot control by modeling physical dynamics. Current WAMs generally follow two paradigms: the "Imagine-then-Execute" approach, which uses video prediction to infer actions…
Embodied navigation in open, dynamic environments demands accurate foresight of how the world will evolve and how actions will unfold over time. We propose AstraNav-World, an end-to-end world model that jointly reasons about future visual…
For end-to-end autonomous driving (E2E-AD), the evaluation system remains an open problem. Existing closed-loop evaluation protocols usually rely on simulators like CARLA being less realistic; while NAVSIM using real-world vision data, yet…
The remarkable recent advances in object-centric generative world models raise a few questions. First, while many of the recent achievements are indispensable for making a general and versatile world model, it is quite unclear how these…
Learning transferable knowledge from unlabeled video data and applying it in new environments is a fundamental capability of intelligent agents. This work presents VideoWorld 2, which extends VideoWorld and offers the first investigation…