In this work, we present a scalable reinforcement learning method for
tr...
Gestures serve as a fundamental and significant mode of non-verbal
commu...
We study how vision-language models trained on Internet-scale data can b...
Deep learning has fundamentally transformed artificial intelligence, but...
We observe that pre-trained large language models (LLMs) are capable of
...
A major challenge to deploying robots widely is navigation in human-popu...
Large language models (LLMs) have demonstrated exciting progress in acqu...
In-memory computing for Machine Learning (ML) applications remedies the ...
The medical conversational question answering (CQA) system aims at provi...
Language models have achieved impressive results in natural language
pro...
Large language models excel at a wide range of complex tasks. However,
e...
For robots to follow instructions from people, they must be able to conn...
Recent progress in large language models (LLMs) has demonstrated the abi...
Recent advances in robot learning have shown promise in enabling robots ...
By transferring knowledge from large, diverse, task-agnostic datasets, m...
Object-goal navigation (Object-nav) entails searching, recognizing and
n...
We propose a framework to enable multipurpose assistive mobile robots to...
3D object detection in point clouds is a core component for modern robot...
Despite decades of research, existing navigation systems still face
real...
Large language models (LLMs) trained on code completion have been shown ...
We propose a novel method to reliably estimate the pose of a camera give...
Recent works have shown how the reasoning capabilities of Large Language...
The medical conversational system can relieve the burden of doctors and
...
The last decade has witnessed enormous improvements in science and
techn...
Large language models can encode a wealth of semantic knowledge about th...
Scientific documents often contain a large number of acronyms. Disambigu...
Acronym disambiguation means finding the correct meaning of an ambiguous...
Acronym extraction aims to find acronyms (i.e., short-forms) and their
m...
Personal attributes represent structured information about a person, suc...
In many industry scale applications, large and resource consuming machin...
We introduce BEHAVIOR, a benchmark for embodied AI with 100 activities i...
Recent research in embodied AI has been boosted by the use of simulation...
Segmentation remains an important preprocessing step both in languages w...
Web servers scaled across distributed systems necessitate complex runtim...
Humans can robustly localize themselves without a map after they get los...
We present iGibson, a novel simulation environment to develop robotic
so...
Statistical significance testing centered on p-values is commonly used t...
Supertagging is conventionally regarded as an important task for combina...
Many Reinforcement Learning (RL) approaches use joint control signals
(p...
Humans can robustly follow a visual trajectory defined by a sequence of
...
We present Interactive Gibson, the first comprehensive benchmark for tra...
Most common navigation tasks in human environments require auxiliary arm...
Neural Networks (NNs) are steering a new generation of artificial
intell...
Tracking 6D poses of objects from videos provides rich information to a ...
Humans can routinely follow a trajectory defined by a list of
images/lan...
Inspired by research in psychology, we introduce a behavioral approach f...
We present a novel neural network architecture, termed Decomposer-Compos...
Developing visual perception models for active agents and sensorimotor
c...
Robots that interact with a dynamic environment, such as social robots a...
As datasets grow richer, an important challenge is to leverage the full
...