IEEE

LNLF-BERT: Transformer for Long Document Classification With Multiple Attention Levels

Abstract: Transformer-based models, such as Bidirectional Encoder Representations from Transformers (BERT), cannot process long sequences because their self-attention operation scales quadratically ...
eLife

Modality-agnostic decoding of vision and language from fMRI

Modality-agnostic decoders leverage modality-invariant representations in human subjects' brain activity to predict stimuli irrespective of their modality (image, text, mental imagery).
The New York Times

Meta Unveils New A.I. Model, Its First From the Superintelligence Lab

The model, Muse Spark, performed better than Meta’s previous A.I. models but lags rivals on coding ability. By Eli Tan Reporting from San Francisco Meta on Wednesday unveiled a new flagship artificial ...
IEEE

A Multiscale Interactive Attention Short Text Classification Model Based on BERT

Abstract: Text classification tasks aim to comprehend and classify text content into specific classifications. This task is crucial for interpreting unstructured text, making it a foundational task in ...