Zorro: A Flexible and Differentiable Parametric Family of Activation Functions That Extends ReLU and GELUby…
Unveil Benign Overfitting for Transformer in Vision: Training Dynamics, Convergence, and Generalizationby Jiarui Jiang, Wei…
Enhancing TinyBERT for Financial Sentiment Analysis Using GPT-Augmented FinBERT Distillationby Graison Jos ThomasFirst submitted to…
Infer Human’s Intentions Before Following Natural Language Instructionsby Yanming Wan, Yue Wu, Yiping Wang, Jiayuan…
Decomposable Transformer Point Processesby Aristeidis PanosFirst submitted to arxiv on: 26 Sep 2024CategoriesMain: Machine Learning…
Benign Overfitting in Token Selection of Attention Mechanismby Keitaro Sakamoto, Issei SatoFirst submitted to arxiv…
CASPFormer: Trajectory Prediction from BEV Images with Deformable Attentionby Harsh Yadav, Maximilian Schaefer, Kun Zhao,…
On the Implicit Relation Between Low-Rank Adaptation and Differential Privacyby Saber Malekmohammadi, Golnoosh FarnadiFirst submitted…
Pixel-Space Post-Training of Latent Diffusion Modelsby Christina Zhang, Simran Motwani, Matthew Yu, Ji Hou, Felix…
Non-asymptotic Convergence of Training Transformers for Next-token Predictionby Ruiquan Huang, Yingbin Liang, Jing YangFirst submitted…