Abstract: Transformers, especially the decoder-only variants, are the backbone of most modern large language models. Yet, we have a very limited understanding of their limitations (i.e., what tasks ...
Abstract: This paper proposes a decoder-only Transformer model for analyzing and clustering vehicle-to-vehicle interactions in highway merge zones. Leveraging deep learning, the model captures complex ...
A research project exploring deep learning architectures for cross-sectional stock return prediction. Models are trained on technical factor features derived from OHLCV data and evaluated via ...
COCO + Objects365 in the table means finetuned model on COCO using pretrained weights trained on Objects365.
Some results have been hidden because they may be inaccessible to you
Show inaccessible results