Scalability in Building Component Data Annotation: Enhancing Facade Material Classification with Synthetic Databy Josie Harrison,…
Transfer Learning Study of Motion Transformer-based Trajectory Predictionsby Lars Ullrich, Alex McMaster, Knut GraichenFirst submitted…
A Multi-Level Framework for Accelerating Training Transformer Modelsby Longwei Zou, Han Zhang, Yangdong DengFirst submitted…
On Training Data Influence of GPT Modelsby Yekun Chai, Qingyi Liu, Shuohuan Wang, Yu Sun,…
Remembering Transformer for Continual Learningby Yuwei Sun, Ippei Fujisawa, Arthur Juliani, Jun Sakuma, Ryota KanaiFirst…
A Transformer-Based Model for the Prediction of Human Gaze Behavior on Videosby Suleyman Ozdel, Yao…
What needs to go right for an induction head? A mechanistic study of in-context learning…
Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attentionby Tsendsuren Munkhdalai, Manaal Faruqui, Siddharth…
A Fixed-Point Approach for Causal Generative Modelingby Meyer Scetbon, Joel Jennings, Agrin Hilmkil, Cheng Zhang,…
PGTNet: A Process Graph Transformer Network for Remaining Time Prediction of Business Process Instancesby Keyvan…