Related papers: EmbodiedMAE: A Unified 3D Multi-Modal Representati…
Following its success in natural language processing and computer vision, foundation models that are pre-trained on large-scale multi-task datasets have also shown great potential in robotics. However, most existing robot foundation models…
Soft robots achieve functionality through tight coupling among geometry, material composition, and actuation. As a result, effective design optimization requires these three aspects to be considered jointly rather than in isolation. This…
Embodied AI is widely recognized as a cornerstone of artificial general intelligence (AGI) because it involves controlling embodied agents to perform tasks in the physical world. Building on the success of large language models (LLMs) and…
Multiple modalities often co-occur when describing natural phenomena. Learning a joint representation of these modalities should yield deeper and more useful representations. Previous generative approaches to multi-modal input either do not…
The advent of Large Multimodal Models (LMMs) offers a promising technology to tackle the limitations of modular design in autonomous driving, which often falters in open-world scenarios requiring sustained environmental understanding and…
Recent advancements in 3D reconstruction and neural rendering have enhanced the creation of high-quality digital assets, yet existing methods struggle to generalize across varying object shapes, textures, and occlusions. While Next Best…
Current language-guided robotic manipulation systems often require low-level action-labeled datasets for imitation learning. While object-centric flow prediction methods mitigate this issue, they remain limited to scenarios involving rigid…
Multi-modal learning is a fast growing area in artificial intelligence. It tries to help machines understand complex things by combining information from different sources, like images, text, and audio. By using the strengths of each…
"Masked Autoencoders (MAE) Are Scalable Vision Learners" revolutionizes the self-supervised learning method in that it not only achieves the state-of-the-art for image pre-training, but is also a milestone that bridges the gap between…
We present the Material Masked Autoencoder (MMAE), a self-supervised Vision Transformer pretrained on a large corpus of short-fiber composite images via masked image reconstruction. The pretrained MMAE learns latent representations that…
In this paper, we introduce a model of evolution and learning in robots that co-optimizes a distribution of latent design vectors (genotypes) and a mixture of control experts (neural modules), which are gated by the latent coordinates of…
Predicting the future of surrounding agents and accordingly planning a safe, goal-directed trajectory are crucial for automated vehicles. Current methods typically rely on imitation learning to optimize metrics against the ground truth,…
Autoencoders have been widely used for dimensional reduction and feature extraction. Various types of autoencoders have been proposed by introducing regularization terms. Most of these regularizations improve representation learning by…
Embodied action planning is a core challenge in robotics, requiring models to generate precise actions from visual observations and language instructions. While video generation world models are promising, their reliance on pixel-level…
This paper introduces EmbodiedAgent, a hierarchical framework for heterogeneous multi-robot control. EmbodiedAgent addresses critical limitations of hallucination in impractical tasks. Our approach integrates a next-action prediction…
Embodied agents are expected to assist humans by actively exploring unknown environments and reasoning about spatial contexts. When deployed in real life, agents often face sequential tasks where each new task follows the completion of the…
Molecular representation learning plays a crucial role in advancing applications such as drug discovery and material design. Existing work leverages 2D and 3D modalities of molecular information for pre-training, aiming to capture…
Learning a robust Variational Autoencoder (VAE) is a fundamental step for many deep learning applications in medical image analysis, such as MRI synthesizes. Existing brain VAEs predominantly focus on single-modality data (i.e., T1-weighted…
Cross-embodiment learning seeks to build generalist robots that operate across diverse morphologies, but differences in action spaces and kinematics hinder data sharing and policy transfer. This raises a central question: Is there any…
We propose the Motion Capsule Autoencoder (MCAE), which addresses a key challenge in the unsupervised learning of motion representations: transformation invariance. MCAE models motion in a two-level hierarchy. In the lower level, a…