We introduce MAmmoTH, a series of open-source large language models (LLM...
Large Language Models (LLMs) are becoming increasingly smart and autonom...
We introduce TacoBot, a user-centered task-oriented digital assistant
de...
The Space-Air-Ground-Sea integrated network calls for more robust and se...
This paper proposes a grant-free massive access scheme based on the
mill...
This paper focuses on advancing outdoor wireless systems to better suppo...
As opposed to general English, many concepts in biomedical terminology h...
Text-guided image editing is widely needed in daily life, ranging from
p...
We introduce Mind2Web, the first dataset for developing and evaluating
g...
This paper studies a new task of federated learning (FL) for semantic
pa...
By providing external information to large language models (LLMs), tool
...
Despite recent progress in text-to-SQL parsing, current semantic parsers...
Recent work has shown that fine-tuning large language models (LLMs) on
l...
Over-parameterized neural language models (LMs) can memorize and recite ...
A recent focus of large language model (LLM) development, as exemplified...
PiML (read π-ML, /`pai.`em.`el/) is an integrated and open-access Python...
Question answering over knowledge bases is considered a difficult proble...
Knowledge tracing (KT) aims to assess individuals' evolving knowledge st...
Task-oriented dialogue systems often assist users with personal or
confi...
A key missing ability of current language models (LMs) is grounding to
r...
Knowledge graph (KG) link prediction aims to infer new facts based on
ex...
This study focuses on embodied agents that can follow natural language
i...
Hand hygiene is a standard six-step hand-washing action proposed by the ...
Recent advances in deep learning have greatly propelled the research on
...
We present TacoBot, a task-oriented dialogue system built for the inaugu...
In natural language understanding (NLU) production systems, users' evolv...
Question answering on knowledge bases (KBQA) poses a unique challenge fo...
The strong few-shot in-context learning capability of large pre-trained
...
We study the problem of developing autonomous agents that can follow hum...
This paper presents Okapi, a new dataset for Natural Language to executa...
We present ReasonBert, a pre-training method that augments language mode...
Knowledge bases (KBs) and text often contain complementary knowledge: KB...
While users claim to be concerned about privacy, often they do little to...
Computerized Adaptive Testing (CAT) is emerging as a promising testing
a...
In recent years, the field of recommendation systems has attracted incre...
Pre-trained transformer language models such as BERT are ubiquitous in N...
Existing studies on question answering on knowledge bases (KBQA) mainly
...
Data-to-text generation has recently attracted substantial interests due...
We describe an approach to task-oriented dialogue in which dialogue stat...
The global pandemic has made it more important than ever to quickly and
...
Despite the widely successful applications, bootstrapping and fine-tunin...
Scheduling precedence-constrained tasks is a classical problem that has ...
Neural natural language generation (NLG) models have recently shown
rema...
High-level (e.g., semantic) features encoded in the latter layers of
con...
As a promising paradigm, interactive semantic parsing has shown to impro...
For offering proactive services to students in intelligent education, on...
Pre-trained embeddings such as word embeddings and sentence embeddings a...
Understanding learning materials (e.g. test questions) is a crucial issu...
With the rapid development in deep learning, deep neural networks have b...
Although promising results have been achieved in video captioning, exist...