Knowledge graphs meet multi-modal learning: A comprehensive survey
Knowledge Graphs (KGs) play a pivotal role in advancing various AI applications, with the
semantic web community's exploration into multi-modal dimensions unlocking new avenues …
semantic web community's exploration into multi-modal dimensions unlocking new avenues …
Flatten transformer: Vision transformer using focused linear attention
The quadratic computation complexity of self-attention has been a persistent challenge
when applying Transformer models to vision tasks. Linear attention, on the other hand, offers …
when applying Transformer models to vision tasks. Linear attention, on the other hand, offers …
Artificial general intelligence for radiation oncology
The emergence of artificial general intelligence (AGI) is transforming radiation oncology. As
prominent vanguards of AGI, large language models (LLMs) such as GPT-4 and PaLM 2 can …
prominent vanguards of AGI, large language models (LLMs) such as GPT-4 and PaLM 2 can …
Agent attention: On the integration of softmax and linear attention
The attention module is the key component in Transformers. While the global attention
mechanism offers high expressiveness, its excessive computational cost restricts its …
mechanism offers high expressiveness, its excessive computational cost restricts its …
A survey of knowledge graph reasoning on graph types: Static, dynamic, and multi-modal
Knowledge graph reasoning (KGR), aiming to deduce new facts from existing facts based on
mined logic rules underlying knowledge graphs (KGs), has become a fast-growing research …
mined logic rules underlying knowledge graphs (KGs), has become a fast-growing research …
Slide-transformer: Hierarchical vision transformer with local self-attention
Self-attention mechanism has been a key factor in the recent progress of Vision Transformer
(ViT), which enables adaptive feature extraction from global contexts. However, existing self …
(ViT), which enables adaptive feature extraction from global contexts. However, existing self …
Grounding language models for visual entity recognition
Abstract We introduce AutoVER, an Autoregressive model for Visual Entity Recognition. Our
model extends an autoregressive Multimodal Large Language Model by employing retrieval …
model extends an autoregressive Multimodal Large Language Model by employing retrieval …
Heterogeneous contrastive learning for foundation models and beyond
In the era of big data and Artificial Intelligence, an emerging paradigm is to utilize contrastive
self-supervised learning to model large-scale heterogeneous data. Many existing foundation …
self-supervised learning to model large-scale heterogeneous data. Many existing foundation …
Transformer technology in molecular science
A transformer is the foundational architecture behind large language models designed to
handle sequential data by using mechanisms of self‐attention to weigh the importance of …
handle sequential data by using mechanisms of self‐attention to weigh the importance of …
Efficient token-guided image-text retrieval with consistent multimodal contrastive training
Image-text retrieval is a central problem for understanding the semantic relationship
between vision and language, and serves as the basis for various visual and language …
between vision and language, and serves as the basis for various visual and language …