VITA-Group / Robust_Weight_SignaturesLinks
[ICML 2023] "Robust Weight Signatures: Gaining Robustness as Easy as Patching Weights?" by Ruisi Cai, Zhenyu Zhang, Zhangyang Wang
☆16Updated 2 years ago
Alternatives and similar repositories for Robust_Weight_Signatures
Users that are interested in Robust_Weight_Signatures are comparing it to the libraries listed below
Sorting:
- ☆25Updated 2 years ago
- Host CIFAR-10.2 Data Set☆13Updated 4 years ago
- Representation Surgery for Multi-Task Model Merging. ICML, 2024.☆47Updated last year
- ☆24Updated last year
- ☆43Updated 2 years ago
- official code repo for paper "Merging Models on the Fly Without Retraining: A Sequential Approach to Scalable Continual Model Merging"☆22Updated 3 months ago
- Source code for the TMLR paper "Black-Box Prompt Learning for Pre-trained Language Models"☆57Updated 2 years ago
- ☆44Updated last year
- Code for T-MARS data filtering☆35Updated 2 years ago
- A modern look at the relationship between sharpness and generalization [ICML 2023]☆43Updated 2 years ago
- ☆24Updated last year
- [ICLR'24] RAIN: Your Language Models Can Align Themselves without Finetuning☆98Updated last year
- ☆23Updated 7 months ago
- ☆48Updated last year
- ☆37Updated last year
- EMNLP 2024: Model Editing Harms General Abilities of Large Language Models: Regularization to the Rescue☆38Updated 8 months ago
- [ECCV 2024] Official PyTorch Implementation of "How Many Unicorns Are in This Image? A Safety Evaluation Benchmark for Vision LLMs"☆86Updated 2 years ago
- ☆51Updated 2 years ago
- ☆60Updated 2 years ago
- ☆15Updated 3 years ago
- Code for Representation Bending Paper☆16Updated 6 months ago
- ☆32Updated last year
- ☆18Updated last year
- This repository is the official implementation of Dataset Condensation with Contrastive Signals (DCC), accepted at ICML 2022.☆22Updated 3 years ago
- Codebase for decoding compressed trust.☆25Updated last year
- Source code of "Calibrating Large Language Models Using Their Generations Only", ACL2024☆22Updated last year
- Code for the paper "Evading Black-box Classifiers Without Breaking Eggs" [SaTML 2024]☆21Updated last year
- Code for safety test in "Keeping LLMs Aligned After Fine-tuning: The Crucial Role of Prompt Templates"☆22Updated 4 months ago
- ☆23Updated 2 years ago
- ☆52Updated 2 years ago