Related papers: Keypoint Action Tokens Enable In-Context Imitation…
Transformers and masked language modeling are quickly being adopted and explored in computer vision as vision transformers and masked image modeling (MIM). In this work, we argue that image token masking differs from token masking in text,…
Building robotic agents capable of operating across diverse environments and object types remains a significant challenge, often requiring extensive data collection. This is particularly restrictive in robotics, where each data point must…
Latent actions serve as an intermediate representation that enables consistent modeling of vision-language-action (VLA) models across heterogeneous datasets. However, approaches to supervising VLAs with latent actions are fragmented and…
In order to understand the in-context learning phenomenon, recent works have adopted a stylized experimental framework and demonstrated that Transformers can learn gradient-based learning algorithms for various classes of real-valued…
Generalizing across robot embodiments and tasks is crucial for adaptive robotic systems. Modular policy learning approaches adapt to new embodiments but are limited to specific tasks, while few-shot imitation learning (IL) approaches often…
Visual imitation learning provides efficient and intuitive solutions for robotic systems to acquire novel manipulation skills. However, simultaneously learning geometric task constraints and control policies from visual inputs alone remains…
While video action recognition has been an active area of research for several years, zero-shot action recognition has only recently started gaining traction. In this work, we propose a novel end-to-end trained transformer model which is…
Recent studies have shown remarkable success in image-to-image translation for attribute transfer applications. However, most of existing approaches are based on deep learning and require an abundant amount of labeled data to produce good…
Transformers have become one of the dominant architectures in deep learning, particularly as a powerful alternative to convolutional neural networks (CNNs) in computer vision. However, Transformer training and inference in previous works…
Imitation learning is a popular approach for teaching motor skills to robots. However, most approaches focus on extracting policy parameters from execution traces alone (i.e., motion trajectories and perceptual data). No adequate…
Tendon-driven robots, a type of continuum robot, have the potential to reduce the invasiveness of surgery by enabling access to difficult-to-reach anatomical targets. In the future, the automation of surgical tasks for these robots may help…
Humans can naturally learn to execute a new task by seeing it performed by other individuals once, and then reproduce it in a variety of configurations. Endowing robots with this ability of imitating humans from third person is a very…
Converting a model's internals to text can yield human-understandable insights about the model. Inspired by the recent success of training-free approaches for image captioning, we propose ZS-A2T, a zero-shot framework that translates the…
Using massive datasets to train large-scale models has emerged as a dominant approach for broad generalization in natural language and vision applications. In reinforcement learning, however, a key challenge is that available data of…
Vision transformer has achieved impressive performance for many vision tasks. However, it may suffer from high redundancy in capturing local features for shallow layers. Local self-attention or early-stage convolutions are thus utilized,…
While Transformers have rapidly gained popularity in various computer vision applications, post-hoc explanations of their internal mechanisms remain largely unexplored. Vision Transformers extract visual information by representing image…
Imitation learning has been commonly applied to solve different tasks in isolation. This usually requires either careful feature engineering, or a significant number of samples. This is far from what we desire: ideally, robots should be…
Self-attention-based vision transformers (ViTs) have emerged as a highly competitive architecture in computer vision. Unlike convolutional neural networks (CNNs), ViTs are capable of global information sharing. With the development of…
Attention-based neural networks such as transformers have demonstrated a remarkable ability to exhibit in-context learning (ICL): Given a short prompt sequence of tokens from an unseen task, they can formulate relevant per-token and…
Meta-learning has emerged as a trending technique to tackle few-shot text classification and achieve state-of-the-art performance. However, the performance of existing approaches heavily depends on the inter-class variance of the support…