Higher-Order Transformer Derivative Estimates for Explicit Pathwise Learning Guaranteesby Yannick Limmer, Anastasis Kratsios, Xuwei Yang,…
Explaining Modern Gated-Linear RNNs via a Unified Implicit Attention Formulationby Itamar Zimerman, Ameen Ali, Lior…
Dynamic Inhomogeneous Quantum Resource Scheduling with Reinforcement Learningby Linsen Li, Pratyush Anand, Kaiming He, Dirk…
Understanding the Effect of using Semantically Meaningful Tokens for Visual Representation Learningby Neha Kalibhat, Priyatham…
Tensor Attention Training: Provably Efficient Learning of Higher-order Transformersby Yingyu Liang, Zhenmei Shi, Zhao Song,…
BOLD: Boolean Logic Deep Learningby Van Minh Nguyen, Cristian Ocampo, Aymen Askri, Louis Leconte, Ba-Hien…
Explainable Molecular Property Prediction: Aligning Chemical Concepts with Predictions via Language Modelsby Zhenzhong Wang, Zehui…
Unsupervised Meta-Learning via In-Context Learningby Anna Vettoruzzo, Lorenzo Braccaioli, Joaquin Vanschoren, Marlena NowaczykFirst submitted to…
C3LLM: Conditional Multimodal Content Generation Using Large Language Modelsby Zixuan Wang, Qinkai Duan, Yu-Wing Tai,…
Accelerating Transformers with Spectrum-Preserving Token Mergingby Hoai-Chau Tran, Duy M. H. Nguyen, Duy M. Nguyen,…