相关论文: RoboDreamer: Learning Compositional World Models f…

While recent advancements in robotic manipulation video synthesis have shown promise, significant challenges persist in ensuring effective instruction-following and achieving high visual quality. Recent methods, like RoboDreamer, utilize…

Recent advances in video generation have shown promise for generating future scenarios, critical for planning and control in autonomous driving and embodied intelligence. However, real-world applications demand more than visually plausible…

Diffusion models excel at short-horizon robot planning, yet scaling them to long-horizon tasks remains challenging due to computational constraints and limited training data. Existing compositional approaches stitch together short segments…

The ability to compose learned concepts and apply them in novel settings is key to human intelligence, but remains a persistent limitation in state-of-the-art machine learning models. To address this issue, we introduce COGITAO, a modular…

Previous Vision-Language-Action models face critical limitations in navigation: scarce, diverse data from labor-intensive collection and static representations that fail to capture temporal dynamics and physical laws. We propose NavDreamer,…

Latent variable generative models have emerged as powerful tools for generative tasks including image and video synthesis. These models are enabled by pretrained autoencoders that map high resolution data into a compressed lower dimensional…

The objective of this work is to augment the basic abilities of a robot by learning to use sensorimotor primitives to solve complex long-horizon manipulation problems. This requires flexible generative planning that can combine primitive…

World models, which are predictive representations of how environments evolve under actions, have become a central component of robot learning. They support policy learning, planning, simulation, evaluation, data generation, and have…

Effective code optimization in compilers is crucial for computer and software engineering. The success of these optimizations primarily depends on the selection and ordering of the optimization passes applied to the code. While most…

Being able to simulate the outcomes of actions in varied environments will revolutionize the development of generalist agents at scale. However, modeling these world dynamics, especially for dexterous robotics tasks, poses significant…

Humans have the innate capability to answer diverse questions, which is rooted in the natural ability to correlate different concepts based on their semantic relationships and decompose difficult problems into sub-tasks. On the contrary,…

Hybrid systems are a compact and natural mechanism with which to address problems in robotics. This work introduces an approach to learning hybrid systems from demonstrations, with an emphasis on extracting models that are explicitly…

Customized video generation aims to generate high-quality videos guided by text prompts and subject's reference images. However, since it is only trained on static images, the fine-tuning process of subject learning disrupts abilities of…

Generalization in reinforcement learning (RL) remains a significant challenge, especially when agents encounter novel environments with unseen dynamics. Drawing inspiration from human compositional reasoning -- where known components are…

Leveraging the compositional nature of our world to expedite learning and facilitate generalization is a hallmark of human perception. In machine learning, on the other hand, achieving compositional generalization has proven to be an…

World models have demonstrated superiority in autonomous driving, particularly in the generation of multi-view driving videos. However, significant challenges still exist in generating customized driving videos. In this paper, we propose…

We present DreamToNav, a novel autonomous robot framework that uses generative video models to enable intuitive, human-in-the-loop control. Instead of relying on rigid waypoint navigation, users provide natural language prompts (e.g.…

Learning to control robots directly based on images is a primary challenge in robotics. However, many existing reinforcement learning approaches require iteratively obtaining millions of robot samples to learn a policy, which can take…

Video generation models have emerged as high-fidelity models of the physical world, capable of synthesizing high-quality videos capturing fine-grained interactions between agents and their environments conditioned on multi-modal user…

World models have become indispensable tools for embodied intelligence, serving as powerful simulators capable of generating realistic robotic videos while addressing critical data scarcity challenges. However, current embodied world models…