Graph-based diffusion models have shown promising results in terms of
ge...
Temporal Sentence Grounding in Videos (TSGV) aims to detect the event
ti...
Goal-Conditioned Hierarchical Reinforcement Learning (GCHRL) is a promis...
We present PESCO, a novel contrastive learning framework that substantia...
Popular reinforcement learning (RL) algorithms tend to produce a unimoda...
A popular approach for improving the correctness of output from large
la...
Despite the remarkable ability of large language models (LMs) to compreh...
Recent AI-assistant agents, such as ChatGPT, predominantly rely on super...
Moreover, GPT-based zero-shot classification models tend to make indepen...
Like people, LLMs do not always generate the best text for a given gener...
Neural network-based Combinatorial Optimization (CO) methods have shown
...
Numerical simulation of non-linear partial differential equations plays ...
The waning of Moore's Law has shifted the focus of the tech industry tow...
We propose a new class of linear Transformers called
FourierLearner-Tran...
Large language models (LLMs) have recently demonstrated an impressive ab...
We address the general task of structured commonsense reasoning: given a...
Recently, deep reinforcement learning (DRL) models have shown promising
...
We propose a new paradigm to help Large Language Models (LLMs) generate ...
We present FLOWGEN, a graph-generation model inspired by the dual-proces...
Conditional set generation learns a mapping from an input sequence of to...
Extreme Multi-label Text Classification (XMTC) has been a tough challeng...
Extreme multi-label text classification (XMTC) is the task of tagging ea...
The IARAI Traffic4cast competitions at NeurIPS 2019 and 2020 showed that...
Large LMs such as GPT-3, while powerful, are not immune to mistakes, but...
How can an end-user provide feedback if a deployed structured prediction...
How can an end-user provide feedback if a deployed structured prediction...
The landscape of city-wide mobility behaviour has altered significantly ...
Current Open-Domain Question Answering (ODQA) model paradigm often conta...
A class of explainable NLP models for reasoning tasks support their deci...
Different from traditional knowledge graphs (KGs) where facts are repres...
Acquiring dynamics is an essential topic in robot learning, but up-to-da...
Back-translation is an effective strategy to improve the performance of
...
Learning from noisy labels is an important concern because of the lack o...
DETR is a recently proposed Transformer-based method which views object
...
Pre-trained contextual representations like BERT have achieved great suc...
This paper presents the first study on using large-scale pre-trained lan...
Knowledge graphs (KGs) contain rich information about world knowledge,
e...
With a large amount of parallel data, neural machine translation systems...
We are interested in gradient-based Explicit Generative Modeling where
s...
Autoregressive (AR) models have been the dominating approach to conditio...
Graph Convolutional Networks (GCNs) have received increasing attention i...
With the success of language pretraining, it is highly desirable to deve...
Given the complexity of combinations of tasks, languages, and domains in...
This paper introduces a new task of politeness transfer which involves
c...
We propose a method of curating high-quality comparable training data fo...
Change-point detection (CPD) aims at detecting the abrupt property chang...
Natural Language Processing (NLP) has recently achieved great success by...
We introduce a new task, Video-and-Language Inference, for joint multimo...
An algorithm to generate a minimal comprehensive Gröbner basis of a
par...
We consider the large-scale query-document retrieval problem: given a qu...