To solve complex tasks, large language models (LLMs) often require multi...
Vision-and-language navigation (VLN) enables the agent to navigate to a
...
Exploration and reward specification are fundamental and intertwined
cha...
Although Large Language Models (LLMs) have demonstrated extraordinary
ca...
The L_2-regularized loss of Deep Linear Networks (DLNs) with more than
o...
Currently, video behavior recognition is one of the most foundational ta...
We introduce ClusterLLM, a novel text clustering framework that leverage...
Recent advances in weakly supervised text classification mostly focus on...
Etremely Weakly Supervised Text Classification (XWS-TC) refers to text
c...
State-of-the-art weakly supervised text classification methods, while
si...
Recent work on knowledge graph completion (KGC) focused on learning
embe...
Vision-and-language navigation (VLN) is the task to enable an embodied a...
This paper presents our Facial Action Units (AUs) recognition submission...
Masked Autoencoders learn strong visual representations and achieve
stat...
Reinforcement learning algorithms typically struggle in the absence of a...
Esports, a sports competition using video games, has become one of the m...
Understanding when and how much a model gradient leaks information about...
Speech emotion recognition (SER) classifies audio into emotion categorie...
We introduce GLM-130B, a bilingual (English and Chinese) pre-trained lan...
We propose Waveformer that learns attention mechanism in the wavelet
coe...
Multimodal demonstrations provide robots with an abundance of informatio...
This competition focus on Urban-Sense Segmentation based on the vehicle
...
Learned recommender systems may inadvertently leak information about the...
We propose a method SPGNet for 3D human pose estimation that mixes
multi...
We argue that the present setting of semisupervised learning on graphs m...
Existing backdoor defense methods are only effective for limited trigger...
Fine-tuning pre-trained language models has recently become a common pra...
In dialogue state tracking, dialogue history is a crucial material, and ...
Hierarchical text classification (HTC) is a challenging subtask of
multi...
Hierarchical text classification is a challenging subtask of multi-label...
Correspondence learning is a fundamental problem in robotics, which aims...
Existing learning from demonstration algorithms usually assume access to...
Despite recent progress in artificial intelligence and machine learning,...
Recently, recommender systems have achieved promising performances and b...
The goal of dialogue state tracking (DST) is to predict the current dial...
Identifying and understanding quality phrases from context is a fundamen...
Contract element extraction (CEE) is the novel task of automatically
ide...
Click-Through Rate (CTR) prediction is a core task in nowadays commercia...
Contextualized representations based on neural language models have furt...
In this paper, we explore to conduct text classification with extremely ...
Inspired by studies on the overwhelming presence of experience-sharing i...
Multilingual BERT (M-BERT) has been a huge success in both supervised an...
Recent work has exhibited the surprising cross-lingual abilities of
mult...
Everyone makes mistakes. So do human annotators when curating labels for...
Unsupervised word embedding has benefited a wide spectrum of NLP tasks d...
Taking word sequences as the input, typical named entity recognition (NE...
As the advancement of information security, human recognition as its cor...
Learning effective visuomotor policies for robots purely from data is
ch...