Related papers: RoboCSE: Robot Common Sense Embedding
An ultimate goal of artificial intelligence is to build computer systems that can understand human languages. Understanding commonsense knowledge about the world expressed in text is one of the foundational and challenging problems to…
Accurate robot segmentation is a fundamental capability for robotic perception. It enables precise visual servoing for VLA systems, scalable robot-centric data augmentation, accurate real-to-sim transfer, and reliable safety monitoring in…
Artificial Intelligence (AI) has significantly advanced in recent years, driving innovation across various fields, especially in robotics. Even though robots can perform complex tasks with increasing autonomy, challenges remain in ensuring…
Embodied AI models often employ off the shelf vision backbones like CLIP to encode their visual observations. Although such general purpose representations encode rich syntactic and semantic information about the scene, much of this…
Imitation learning from human demonstrations has become a dominant approach for training autonomous robot policies. However, collecting demonstration datasets is costly: it often requires access to robots and needs sustained effort in a…
A major problem in machine learning is that of inductive bias: how to choose a learner's hypothesis space so that it is large enough to contain a solution to the problem being learnt, yet small enough to ensure reliable generalization from…
Deep Reinforcement Learning has been successfully applied in various computer games [8]. However, it is still rarely used in real-world applications, especially for the navigation and continuous control of real mobile robots [13]. Previous…
Cross-embodiment generalization underpins the vision of building generalist embodied agents for any robot, yet its enabling factors remain poorly understood. We investigate embodiment scaling laws, the hypothesis that increasing the number…
Assistive mobile robots are a transformative technology that helps persons with disabilities regain the ability to move freely. Although autonomous wheelchairs significantly reduce user effort, they still require human input to allow users…
This paper proposes to address the word sense ambiguity issue in an unsupervised manner, where word sense representations are learned along a word sense selection mechanism given contexts. Prior work focused on designing a single model to…
Taking inspiration from Set Theory, we introduce SetCSE, an innovative information retrieval framework. SetCSE employs sets to represent complex semantics and incorporates well-defined operations for structured information querying under…
Robots and intelligent systems that sense or interact with the world are increasingly being used to automate a wide array of tasks. The ability of these systems to complete these tasks depends on a large range of technologies such as the…
Soft robotics is a modern robotic paradigm for performing dexterous interactions with the surroundings via morphological flexibility. The desire for autonomous operation requires soft robots to be capable of proprioception and makes it…
Autonomous robots used in infrastructure inspection, space exploration and other critical missions operate in highly dynamic environments. As such, they must continually verify their ability to complete the tasks associated with these…
We present Graph Attention Collaborative Similarity Embedding (GACSE), a new recommendation framework that exploits collaborative information in the user-item bipartite graph for representation learning. Our framework consists of two parts:…
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…
Embedding is a common technique for analyzing multi-dimensional data. However, the embedding projection cannot always form significant and interpretable visual structures that foreshadow underlying data patterns. We propose an approach that…
Representation learning has been proven to play an important role in the unprecedented success of machine learning models in numerous tasks, such as machine translation, face recognition and recommendation. The majority of existing…
Pretrained language models for code token embeddings are used in code search, code clone detection, and other code-related tasks. Similarly, code function embeddings are useful in such tasks. However, there are no out-of-box models for…
Commonsense reasoning is intuitive for humans but has been a long-term challenge for artificial intelligence (AI). Recent advancements in pretrained language models have shown promising results on several commonsense benchmark datasets.…