Learning a recommender system model from an item's raw modality features...
Foundation language models obtain the instruction-following ability thro...
Mathematical reasoning is a challenging task for large language models
(...
The recent release of very large language models such as PaLM and GPT-4 ...
Electronic health records (EHR) contain narrative notes that provide
ext...
Advances in deep generative models shed light on de novo molecule genera...
This paper describes the results of the first shared task on the generat...
This paper presents the ADAIO team's system entry in the Building Educat...
Adapters, a plug-in neural network module with some tunable parameters, ...
Text-based collaborative filtering (TCF) has become the mainstream appro...
Recently, image-to-image translation methods based on contrastive learni...
Existing image-to-image(I2I) translation methods achieve state-of-the-ar...
Reinforcement Learning from Human Feedback (RLHF) facilitates the alignm...
Recommendation models that utilize unique identities (IDs) to represent
...
Biomedical entity linking (EL) consists of named entity recognition (NER...
Vision-and-language multi-modal pretraining and fine-tuning have shown g...
We extend a current sequence-tagging approach to Grammatical Error Corre...
Molecular dynamic simulations are important in computational physics,
ch...
Diffusion model, a new generative modelling paradigm, has achieved great...
Language models with the Transformers structure have shown great perform...
Grammatical Error Correction (GEC) is the task of automatically detectin...
Entities lie in the heart of biomedical natural language understanding, ...
The expansion of renewable energy could help realizing the goals of peak...
Pretrained language models have served as important backbones for natura...
Term clustering is important in biomedical knowledge graph construction....
Biomedical knowledge graphs (BioMedKGs) are essential infrastructures fo...
Automatic ICD coding is defined as assigning disease codes to electronic...
Smart Internet of Vehicles (IoVs) combined with Artificial Intelligence ...
Adversarial attacks provide a good way to study the robustness of deep
l...
In recent years, the security of deep learning models achieves more and ...
Nested entities are observed in many domains due to their compositionali...
Few-shot learning is a standard practice in most deep learning based
his...
In recent years, research on adversarial attacks has become a hot spot.
...
Artificial Intelligence (AI), along with the recent progress in biomedic...
Intelligent Transportation System (ITS) has become one of the essential
...
Pretrained language models have shown success in many natural language
p...
Question Answering (QA) is a benchmark Natural Language Processing (NLP)...
Recent studies have shown remarkable success in face image generations.
...
We propose a novel medical term embedding method named CODER, which stan...
We describe a deployed scalable system for organizing published scientif...
Shortage of available training data is holding back progress in the area...