MUSE-Net: Missingness-aware mUlti-branching Self-attention Encoder for Irregular Longitudinal Electronic Health Recordsby Zekai Wang, Tieming Liu,…
Temporally Multi-Scale Sparse Self-Attention for Physical Activity Data Imputationby Hui Wei, Maxwell A. Xu, Colin…
Automated Immunophenotyping Assessment for Diagnosing Childhood Acute Leukemia using Set-Transformersby Elpiniki Maria Lygizou, Michael Reiter,…
Do LLMs dream of elephants (when told not to)? Latent concept association and associative memory…
Generative Expansion of Small Datasets: An Expansive Graph Approachby Vahid Jebraeeli, Bo Jiang, Hamid Krim,…
SiT: Symmetry-Invariant Transformers for Generalisation in Reinforcement Learningby Matthias Weissenbacher, Rishabh Agarwal, Yoshinobu KawaharaFirst submitted…
Unveiling the Hidden Structure of Self-Attention via Kernel Principal Component Analysisby Rachel S.Y. Teo, Tan…
A Primal-Dual Framework for Transformers and Neural Networksby Tan M. Nguyen, Tam Nguyen, Nhat Ho,…
A Scalable and Effective Alternative to Graph Transformersby Kaan Sancak, Zhigang Hua, Jin Fang, Yan…
Rethinking Spatio-Temporal Transformer for Traffic Prediction:Multi-level Multi-view Augmented Learning Frameworkby Jiaqi Lin, Qianqian RenFirst submitted…