Summary of Tokenization Is More Than Compression, by Craig W. Schmidt et al.
Tokenization Is More Than Compressionby Craig W. Schmidt, Varshini Reddy, Haoran Zhang, Alec Alameddine, Omri…
Tokenization Is More Than Compressionby Craig W. Schmidt, Varshini Reddy, Haoran Zhang, Alec Alameddine, Omri…
MATEY: multiscale adaptive foundation models for spatiotemporal physical systemsby Pei Zhang, M. Paul Laiu, Matthew…
Next Token Prediction Towards Multimodal Intelligence: A Comprehensive Surveyby Liang Chen, Zekun Wang, Shuhuai Ren,…
Enhancing Item Tokenization for Generative Recommendation through Self-Improvementby Runjin Chen, Mingxuan Ju, Ngoc Bui, Dimosthenis…
When Worse is Better: Navigating the compression-generation tradeoff in visual tokenizationby Vivek Ramanujan, Kushal Tirumala,…
SocialED: A Python Library for Social Event Detectionby Kun Zhang, Xiaoyan Yu, Pu Li, Hao…
BarcodeMamba: State Space Models for Biodiversity Analysisby Tiancheng Gao, Graham W. TaylorFirst submitted to arxiv…
SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizerby Hao Chen, Ze Wang, Xiang Li, Ximeng Sun, Fangyi Chen,…
When Every Token Counts: Optimal Segmentation for Low-Resource Language Modelsby Bharath Raj S, Garvit Suri,…
Language-Guided Image Tokenization for Generationby Kaiwen Zha, Lijun Yu, Alireza Fathi, David A. Ross, Cordelia…