Audio visual segmentation (AVS) aims to segment the sounding objects for...
Equipped with Chain-of-Thought (CoT), Large language models (LLMs) have ...
The long-standing one-to-many issue of the open-domain dialogues poses
s...
Large Transformer-based Pretrained Language Models (PLMs) dominate almos...
Variational autoencoders (VAEs) are one of the powerful unsupervised lea...
Mixture-of-Experts (MoE) networks have been proposed as an efficient way...
Recommender systems usually learn user interests from various user behav...
Understanding the intention of the users and recognizing the semantic
en...
Semantic search for candidate retrieval is an important yet neglected pr...
Dual-Encoders is a promising mechanism for answer retrieval in question
...
Recent advances in sequence-to-sequence learning reveal a purely data-dr...
With the development of community based question answering (Q&A) service...