Large language models (LLMs) with billions of parameters have demonstrat...
Graphic layout generation, a growing research field, plays a significant...
Instruction tuning is instrumental in enabling Large Language Models (LL...
The rapid advancements in large language models (LLMs) have presented
ch...
Detoxification for LLMs is challenging since it requires models to avoid...
Diffusion models have gained significant attention in the realm of image...
Diffusion models have been successfully adapted to text generation tasks...
Currently, pre-trained language models (PLMs) do not cope well with the
...
Currently, human-bot symbiosis dialog systems, e.g., pre- and after-sale...
Non-autoregressive neural machine translation (NAT) models are proposed ...
Transformer-based autoregressive (AR) methods have achieved appealing
pe...
A deployed question answering (QA) model can easily fail when the test d...
Recent research has revealed that neural language models at scale suffer...
The conventional success of textual classification relies on annotated d...
In view of the poor robustness of existing Chinese grammatical error
cor...
Non-autoregressive (NAR) generation, which is first proposed in neural
m...
In the past few years, cross-modal image-text retrieval (ITR) has experi...
Sequential recommendation methods play an important role in real-world
r...
Establishing retrieval-based dialogue systems that can select appropriat...
Dropout is a powerful and widely used technique to regularize the traini...
Adapting pre-trained language models (PrLMs) (e.g., BERT) to new domains...
The twin support vector machine and its extensions have made great
achie...
With the prosperous of cross-border e-commerce, there is an urgent deman...