Genre
9c26a48b7ebd37bc3e979c8651fc3649-Paper-Conference.pdf
Exploiting symmetry inherent in data can significantly improve the sample efficiency of alearning procedure and the generalization of learned models.
On the Exploitability of Instruction Tuning
In this work, we investigate how an adversary can exploit instruction tuning by injecting specific instruction-following examples into the training data that intentionally changes the model's behavior.
In-Context Learning with Representations: Contextual Generalization of Trained Transformers Tong Y ang CMU Y u Huang
This paper investigates the training dynamics of transformers by gradient descent through the lens of non-linear regression tasks.
Leveraging Contrastive Learning for Enhanced Node Representations in Tokenized Graph Transformers Jinsong Chen
These limitations hinder GNNs' ability to capture long-range dependencies in graphs, ultimately