Challenges, evaluation and opportunities for open-world learning
Environmental changes can profoundly impact the performance of artificial intelligence
systems operating in the real world, with effects ranging from overt catastrophic failures to …
systems operating in the real world, with effects ranging from overt catastrophic failures to …
Aligning cyber space with physical world: A comprehensive survey on embodied ai
Embodied Artificial Intelligence (Embodied AI) is crucial for achieving Artificial General
Intelligence (AGI) and serves as a foundation for various applications that bridge cyberspace …
Intelligence (AGI) and serves as a foundation for various applications that bridge cyberspace …
Foundation models in robotics: Applications, challenges, and the future
We survey applications of pretrained foundation models in robotics. Traditional deep
learning models in robotics are trained on small datasets tailored for specific tasks, which …
learning models in robotics are trained on small datasets tailored for specific tasks, which …
Mvimgnet: A large-scale dataset of multi-view images
Being data-driven is one of the most iconic properties of deep learning algorithms. The birth
of ImageNet drives a remarkable trend of" learning from large-scale data" in computer vision …
of ImageNet drives a remarkable trend of" learning from large-scale data" in computer vision …
Physics-informed machine learning: A survey on problems, methods and applications
Recent advances of data-driven machine learning have revolutionized fields like computer
vision, reinforcement learning, and many scientific and engineering domains. In many real …
vision, reinforcement learning, and many scientific and engineering domains. In many real …
Generating visual scenes from touch
An emerging line of work has sought to generate plausible imagery from touch. Existing
approaches, however, tackle only narrow aspects of the visuo-tactile synthesis problem, and …
approaches, however, tackle only narrow aspects of the visuo-tactile synthesis problem, and …
Multiply: A multisensory object-centric embodied large language model in 3d world
Human beings possess the capability to multiply a melange of multisensory cues while
actively exploring and interacting with the 3D world. Current multi-modal large language …
actively exploring and interacting with the 3D world. Current multi-modal large language …
The objectfolder benchmark: Multisensory learning with neural and real objects
Abstract We introduce the ObjectFolder Benchmark, a benchmark suite of 10 tasks for
multisensory object-centric learning, centered around object recognition, reconstruction, and …
multisensory object-centric learning, centered around object recognition, reconstruction, and …
See, hear, and feel: Smart sensory fusion for robotic manipulation
Humans use all of their senses to accomplish different tasks in everyday activities. In
contrast, existing work on robotic manipulation mostly relies on one, or occasionally two …
contrast, existing work on robotic manipulation mostly relies on one, or occasionally two …
Touching a nerf: Leveraging neural radiance fields for tactile sensory data generation
Tactile perception is key for robotics applications such as manipulation. However, tactile
data collection is time-consuming, especially when compared to vision. This limits the use of …
data collection is time-consuming, especially when compared to vision. This limits the use of …