Tokenization Matters! Degrading Large Language Models through Challenging Their Tokenizationby Dixuan Wang, Yanda Li, Junyuan…
Super Tiny Language Modelsby Dylan Hillier, Leon Guertler, Cheston Tan, Palaash Agrawal, Chen Ruirui, Bobby…
Challenges and Opportunities in Text Generation Explainabilityby Kenza Amara, Rita Sevastjanova, Mennatallah El-AssadyFirst submitted to…
Semi-Parametric Retrieval via Binary Bag-of-Tokens Indexby Jiawei Zhou, Li Dong, Furu Wei, Lei ChenFirst submitted…
Evaluating Subword Tokenization: Alien Subword Composition and OOV Generalization Challengeby Khuyagbaatar Batsuren, Ekaterina Vylomova, Verna…
VTR: An Optimized Vision Transformer for SAR ATR Acceleration on FPGAby Sachini Wickramasinghe, Dhruv Parikh,…
Homogeneous Tokenizer Matters: Homogeneous Visual Tokenizer for Remote Sensing Image Understandingby Run Shao, Zhaoyang Zhang,…
Tokensome: Towards a Genetic Vision-Language GPT for Explainable and Cognitive Karyotypingby Haoxi Zhang, Xinxu Zhang,…
Token Alignment via Character Matching for Subword Completionby Ben Athiwaratkun, Shiqi Wang, Mingyue Shang, Yuchen…
Evaluating the Elementary Multilingual Capabilities of Large Language Models with MultiQby Carolin Holtermann, Paul Röttger,…