Modeling Long Sequences in Bladder Cancer Recurrence: A Comparative Evaluation of LSTM,Transformer,and Mambaby Runquan Zhang,…
FinerCut: Finer-grained Interpretable Layer Pruning for Large Language Modelsby Yang Zhang, Yawei Li, Xinpeng Wang,…
2BP: 2-Stage Backpropagationby Christopher Rae, Joseph K. L. Lee, James RichingsFirst submitted to arxiv on:…
HarmoDT: Harmony Multi-Task Decision Transformer for Offline Reinforcement Learningby Shengchao Hu, Ziqing Fan, Li Shen,…
Delving into Differentially Private Transformerby Youlong Ding, Xueyang Wu, Yining Meng, Yonggang Luo, Hao Wang,…
Knowledge Circuits in Pretrained Transformersby Yunzhi Yao, Ningyu Zhang, Zekun Xi, Mengru Wang, Ziwen Xu,…
Exploring Context Window of Large Language Models via Decomposed Positional Vectorsby Zican Dong, Junyi Li,…
Boosting Protein Language Models with Negative Sample Miningby Yaoyao Xu, Xinjian Zhao, Xiaozhuang Song, Benyou…
Mechanistic Interpretability of Binary and Ternary Transformersby Jason LiFirst submitted to arxiv on: 27 May…
InversionView: A General-Purpose Method for Reading Information from Neural Activationsby Xinting Huang, Madhur Panwar, Navin…