We present a model that can perform multiple vision tasks and can be ada...
Large Language Models (LLMs) have achieved remarkable results. But exist...
Recent AI-assistant agents, such as ChatGPT, predominantly rely on super...
Decision Transformers (DT) have demonstrated strong performances in offl...
Humans possess a versatile mechanism for extracting structured
represent...
Existing large language model-based code generation pipelines typically ...
Large Transformer-based Pretrained Language Models (PLMs) dominate almos...
Optimization in multi-task learning (MTL) is more challenging than
singl...
Mixture-of-Experts (MoE) networks have been proposed as an efficient way...
Humans can leverage prior experience and learn novel tasks from a handfu...
In this thesis, we try to build a connection between the two schools by
...
Many complex real-world tasks are composed of several levels of sub-task...
There are two major classes of natural language grammars – the dependenc...
Transformers do not scale very well to long sequence lengths largely bec...
We model the recursive production property of context-free grammars for
...
It is commonly believed that knowledge of syntactic structure should imp...
Stack-augmented recurrent neural networks (RNNs) have been of interest t...
The ability to understand logical relationships between sentences is an
...
Recurrent neural network (RNN) models are widely used for processing
seq...
In this work, we propose a novel method for training neural networks to
...
In this work, we propose a novel constituency parsing scheme. The model
...
Learning distributed sentence representations remains an interesting pro...
We propose a neural language model capable of unsupervised syntactic
str...
We propose a new self-organizing hierarchical softmax formulation for
ne...
With the development of community based question answering (Q&A) service...