Imitate Before Detect: Aligning Machine Stylistic Preference for Machine-Revised Text Detectionby Jiaqi Chen, Xiaoye Zhu,…
Targeted Angular Reversal of Weights (TARS) for Knowledge Removal in Large Language Modelsby Harry J.…
B-VLLM: A Vision Large Language Model with Balanced Spatio-Temporal Tokensby Zhuqiang Lu, Zhenfei Yin, Mengwei…
RADIOv2.5: Improved Baselines for Agglomerative Vision Foundation Modelsby Greg Heinrich, Mike Ranzinger, Hongxu, Yao Lu,…
Uncovering Uncertainty in Transformer Inferenceby Greyson Brothers, Willa Mannering, Amber Tien, John WinderFirst submitted to…
Flash Communication: Reducing Tensor Parallelization Bottleneck for Fast Large Language Model Inferenceby Qingyuan Li, Bo…
Cross-Self KV Cache Pruning for Efficient Vision-Language Inferenceby Xiaohuan Pei, Tao Huang, Chang XuFirst submitted…
AyutthayaAlpha: A Thai-Latin Script Transliteration Transformerby Davor Lauc, Attapol Rutherford, Weerin WongwarawipatrFirst submitted to arxiv…
Chain-of-Thought in Large Language Models: Decoding, Projection, and Activationby Hao Yang, Qianghua Zhao, Lei LiFirst…
From Language Models over Tokens to Language Models over Charactersby Tim Vieira, Ben LeBrun, Mario…