Existing instance segmentation models learn task-specific information us...
Text-to-image (T2I) models based on diffusion processes have achieved
re...
Prompt tuning approaches, which learn task-specific soft prompts for a
d...
We propose value retrieval with arbitrary queries for form-like document...
Despite great progress in object detection, most existing methods are li...
Although pre-trained language models, such as BERT, achieve state-of-art...
In this work, we propose to improve the effectiveness of language
pre-tr...
How to make unsupervised language pre-training more efficient and less
r...
The Transformer is widely used in natural language processing tasks. To ...
Deep neural networks (DNNs) are poorly-calibrated when trained in
conven...
Metric-based meta-learning techniques have successfully been applied to
...
This paper reviews the first challenge on efficient perceptual image
enh...
Exploring why stochastic gradient descent (SGD) based optimization metho...
We study the problem of response selection for multi-turn conversation i...
We study multi-turn response generation in chatbots where a response is
...
We study response selection for multi-turn conversation in retrieval-bas...
While automatic response generation for building chatbot systems has dra...
We consider incorporating topic information into the sequence-to-sequenc...