Summary of Efficient Adaptation Of Pre-trained Vision Transformer Via Householder Transformation, by Wei Dong et al.
Efficient Adaptation of Pre-trained Vision Transformer via Householder Transformationby Wei Dong, Yuan Sun, Yiting Yang,…
Summary of Cogsteer: Cognition-inspired Selective Layer Intervention For Efficiently Steering Large Language Models, by Xintong Wang et al.
CogSteer: Cognition-Inspired Selective Layer Intervention for Efficiently Steering Large Language Modelsby Xintong Wang, Jingheng Pan,…
Summary of Controlled Low-rank Adaptation with Subspace Regularization For Continued Training on Large Language Models, by Yuheng Lu et al.
Controlled Low-Rank Adaptation with Subspace Regularization for Continued Training on Large Language Modelsby Yuheng Lu,…
Summary of The Effect Of Fine-tuning on Language Model Toxicity, by Will Hawkins et al.
The effect of fine-tuning on language model toxicityby Will Hawkins, Brent Mittelstadt, Chris RussellFirst submitted…
Summary of Unlearning Backdoor Attacks For Llms with Weak-to-strong Knowledge Distillation, by Shuai Zhao et al.
Unlearning Backdoor Attacks for LLMs with Weak-to-Strong Knowledge Distillationby Shuai Zhao, Xiaobao Wu, Cong-Duy Nguyen,…
Summary of Sparsegrad: a Selective Method For Efficient Fine-tuning Of Mlp Layers, by Viktoriia Chekalina et al.
SparseGrad: A Selective Method for Efficient Fine-tuning of MLP Layersby Viktoriia Chekalina, Anna Rudenko, Gleb…
Summary of Towards Full-parameter and Parameter-efficient Self-learning For Endoscopic Camera Depth Estimation, by Shuting Zhao et al.
Towards Full-parameter and Parameter-efficient Self-learning For Endoscopic Camera Depth Estimationby Shuting Zhao, Chenkang Du, Kristin…
Summary of Hm3: Heterogeneous Multi-class Model Merging, by Stefan Hackmann
HM3: Heterogeneous Multi-Class Model Mergingby Stefan HackmannFirst submitted to arxiv on: 27 Sep 2024CategoriesMain: Computation…
Summary of Disha: Dimension-sharding Adaptation Of Large Language Models with Fast Convergence and Fast Computation, by Jiale Kang
DiSHA: Dimension-Sharding Adaptation of Large Language Models with Fast Convergence and Fast Computationby Jiale KangFirst…