Vector-ICL: In-context Learning with Continuous Vector Representations Paper • 2410.05629 • Published Oct 8, 2024 • 3
WavSpA: Wavelet Space Attention for Boosting Transformers' Long Sequence Learning Ability Paper • 2210.01989 • Published Oct 5, 2022
Learning a Decision Tree Algorithm with Transformers Paper • 2402.03774 • Published Feb 6, 2024 • 3