Gestures serve as a fundamental and significant mode of non-verbal
commu...
Key to rich, dexterous manipulation in the real world is the ability to
...
Reinforcement learning from human feedback (RLHF) is a technique for tra...
We observe that pre-trained large language models (LLMs) are capable of
...
Reusing large datasets is crucial to scale vision-based robotic manipula...
Imitation Learning (IL) is a sample efficient paradigm for robot learnin...
While natural language offers a convenient shared interface for humans a...
Consider a robot tasked with tidying a desk with a meticulously construc...
Large language models (LLMs) have demonstrated exciting progress in acqu...
AI assistance continues to help advance applications in education, from
...
In supervised learning, the question of data quality and curation has be...
Strategic reasoning enables agents to cooperate, communicate, and compet...
Diffusion models are powerful generative models but suffer from slow
sam...
Reward functions are difficult to design and often hard to align with hu...
Sequential decision making algorithms often struggle to leverage differe...
Enabling robots to learn novel visuomotor skills in a data-efficient man...
One of the fundamental quests of AI is to produce agents that coordinate...
Piecewise-affine (PWA) systems are widely used for modeling and control ...
Reward design in reinforcement learning (RL) is challenging since specif...
Robot policies need to adapt to human preferences and/or new environment...
Recent work in visual representation learning for robotics demonstrates ...
Temperature scaling is a popular technique for tuning the sharpness of a...
Systems for language-guided human-robot interaction must satisfy two key...
While reinforcement learning (RL) has become a more popular approach for...
A robotic feeding system must be able to acquire a variety of foods. Pri...
Acquiring food items with a fork poses an immense challenge to a
robot-a...
Recent works on shared autonomy and assistive-AI technologies, such as
a...
Assistance during eating is essential for those with severe mobility iss...
When humans perform contact-rich manipulation tasks, customized tools ar...
Imitation learning from human-provided demonstrations is a strong approa...
Multimodal demonstrations provide robots with an abundance of informatio...
Conditional inference on arbitrary subsets of variables is a core proble...
How do people build up trust with artificial agents? Here, we study a ke...
Constructing a diverse repertoire of manipulation skills in a scalable
f...
Multi-agent interactions are important to model for forecasting other ag...
Correspondence learning is a fundamental problem in robotics, which aims...
Existing learning from demonstration algorithms usually assume access to...
Many existing imitation learning datasets are collected from multiple
de...
While advances in multi-agent learning have enabled the training of
incr...
We present PantheonRL, a multiagent reinforcement learning software pack...
Probabilistic circuits (PCs) are a family of generative models which all...
Robot-assisted feeding in household environments is challenging because ...
We introduce Language-Informed Latent Actions (LILA), a framework for
le...
Machine learning has long since become a keystone technology, accelerati...
The goal of learning from demonstrations is to learn a policy for an age...
Most existing imitation learning approaches assume the demonstrations ar...
An overarching goal of natural language processing is to enable machines...
Learning in multi-agent environments is difficult due to the non-station...
When humans collaborate with each other, they often make decisions by
ob...
Today's robots are increasingly interacting with people and need to
effi...