Related papers: Structural Action Transformer for 3D Dexterous Man…
Over the past few years, we have witnessed remarkable advancements in Code Pre-trained Models (CodePTMs). These models achieved excellent representation capabilities by designing structure-based pre-training tasks for code. However, how to…
Spatio-temporal alignment is crucial for temporal modeling of end-to-end (E2E) perception in autonomous driving (AD), providing valuable structural and textural prior information. Existing methods typically rely on the attention mechanism…
Transformer-based approaches have revolutionized image super-resolution by modeling long-range dependencies. However, the quadratic computational complexity of vanilla self-attention mechanisms poses significant challenges, often leading to…
Deep neural networks based purely on attention have been successful across several domains, relying on minimal architectural priors from the designer. In Human Action Recognition (HAR), attention mechanisms have been primarily adopted on…
Capturing the dependencies between joints is critical in skeleton-based action recognition task. Transformer shows great potential to model the correlation of important joints. However, the existing Transformer-based methods cannot capture…
In the spatial action representation, the action space spans the space of target poses for robot motion commands, i.e. SE(2) or SE(3). This approach has been used to solve challenging robotic manipulation problems and shows promise.…
Training on diverse, internet-scale data is a key factor in the success of recent large foundation models. Yet, using the same recipe for building embodied agents has faced noticeable difficulties. Despite the availability of many…
3D human motion prediction is a research area of high significance and a challenge in computer vision. It is useful for the design of many applications including robotics and autonomous driving. Traditionally, autogregressive models have…
3D human pose estimation can be handled by encoding the geometric dependencies between the body parts and enforcing the kinematic constraints. Recently, Transformer has been adopted to encode the long-range dependencies between the joints…
In recent years, the transformer architecture has become the de facto standard for machine learning algorithms applied to natural language processing and computer vision. Despite notable evidence of successful deployment of this…
Segmenting arbitrary 3D objects into constituent parts that are structurally meaningful is a fundamental problem encountered in a wide range of computer graphics applications. Existing methods for 3D shape segmentation suffer from complex…
Acquiring a multi-task imitation policy in 3D manipulation poses challenges in terms of scene understanding and action prediction. Current methods employ both 3D representation and multi-view 2D representation to predict the poses of the…
Autonomous manipulation in robot arms is a complex and evolving field of study in robotics. This paper proposes work stands at the intersection of two innovative approaches in the field of robotics and machine learning. Inspired by the…
Perceiving and manipulating 3D articulated objects (e.g., cabinets, doors) in human environments is an important yet challenging task for future home-assistant robots. The space of 3D articulated objects is exceptionally rich in their…
Temporal convolutions have been the paradigm of choice in action segmentation, which enhances long-term receptive fields by increasing convolution layers. However, high layers cause the loss of local information necessary for frame…
Reinforcement learning (RL) has demonstrated great potential in robotic operations. However, its data-intensive nature and reliance on the Markov Decision Process (MDP) assumption limit its practical deployment in real-world scenarios…
Large sequence model (SM) such as GPT series and BERT has displayed outstanding performance and generalization capabilities on vision, language, and recently reinforcement learning tasks. A natural follow-up question is how to abstract…
This paper focuses on transferring control policies between robot manipulators with different morphology. While reinforcement learning (RL) methods have shown successful results in robot manipulation tasks, transferring a trained policy…
3D morphing remains challenging due to the difficulty of generating semantically consistent and temporally smooth deformations, especially across categories. We present MorphAny3D, a training-free framework that leverages Structured Latent…
Self-supervised pretraining has been extensively studied in language and vision domains, where a unified model can be easily adapted to various downstream tasks by pretraining representations without explicit labels. When it comes to…