相关论文: Zero-shot World Models Are Developmentally Efficie…

Imitation learning is effective for training agents when expert demonstrations are available, but collecting demonstrations for every complex task in an environment is costly. We study the long-horizon, goal-conditioned setting where a…

Learning physical dynamics in a series of non-stationary environments is a challenging but essential task for model-based reinforcement learning (MBRL) with visual inputs. It requires the agent to consistently adapt to novel tasks without…

Developing world models that understand complex physical interactions is essential for advancing robotic planning and simulation.However, existing methods often struggle to accurately model the environment under conditions of data scarcity…

With the recent renaissance of deep convolution neural networks, encouraging breakthroughs have been achieved on the supervised recognition tasks, where each class has sufficient training data and fully annotated training data. However, to…

Interactive world models that simulate object dynamics are crucial for robotics, VR, and AR. However, it remains a significant challenge to learn physics-consistent dynamics models from limited real-world video data, especially for…

As autonomous systems are increasingly deployed in open and uncertain settings, there is a growing need for trustworthy world models that can reliably predict future high-dimensional observations. The learned latent representations in world…

We introduce Latent Particle World Model (LPWM), a self-supervised object-centric world model scaled to real-world multi-object datasets and applicable in decision-making. LPWM autonomously discovers keypoints, bounding boxes, and object…

Identifying predictive world models for robots in novel environments from sparse online observations is essential for robot task planning and execution in novel environments. However, existing methods that leverage differentiable…

Zero-shot classification is a promising paradigm to solve an applicable problem when the training classes and test classes are disjoint. Achieving this usually needs experts to externalize their domain knowledge by manually specifying a…

Fine-grained object recognition that aims to identify the type of an object among a large number of subcategories is an emerging application with the increasing resolution that exposes new details in image data. Traditional fully supervised…

We aim to bridge the gap between typical human and machine-learning environments by extending the standard framework of few-shot learning to an online, continual setting. In this setting, episodes do not have separate training and testing…

Reinforcement Learning (RL) has made significant strides in complex tasks but struggles in multi-task settings with different embodiments. World model methods offer scalability by learning a simulation of the environment but often rely on…

A world model is an AI system that simulates how an environment evolves under actions, enabling planning through imagined futures rather than reactive perception. Current world models, however, suffer from visual conflation: the mistaken…

Modern reinforcement learning (RL) systems capture deep truths about general, human problem-solving. In domains where new data can be simulated cheaply, these systems uncover sequential decision-making policies that far exceed the ability…

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 (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…

As autonomous decision-making agents move from narrow operating environments to unstructured worlds, learning systems must move from a closed-world formulation to an open-world and few-shot setting in which agents continuously learn new…

Zero-shot learning is a new paradigm to classify objects from classes that are not available at training time. Zero-shot learning (ZSL) methods have attracted considerable attention in recent years because of their ability to classify…

Recent advances in large generative models have shown that simple autoregressive formulations, when scaled appropriately, can exhibit strong zero-shot generalization across domains. Motivated by this trend, we investigate whether…

Vision-language models (VLMs) have shown impressive zero- and few-shot performance on real-world visual question answering (VQA) benchmarks, alluding to their capabilities as visual reasoning engines. However, the benchmarks being used…