JJchy / CG_score
Data Valuation without Training of a Model, submitted to ICLR'23
☆23Updated 2 years ago
Alternatives and similar repositories for CG_score:
Users that are interested in CG_score are comparing it to the libraries listed below
- Code for paper "Merging Multi-Task Models via Weight-Ensembling Mixture of Experts"☆22Updated 9 months ago
- ☆42Updated last month
- Code for NeurIPS'23 paper "A Bayesian Approach To Analysing Training Data Attribution In Deep Learning"☆15Updated last year
- Uncertainty quantification for in-context learning of large language models☆16Updated 11 months ago
- AdaMerging: Adaptive Model Merging for Multi-Task Learning. ICLR, 2024.☆72Updated 5 months ago
- ☆33Updated last year
- ☆21Updated 10 months ago
- An official implementation of "Catastrophic Failure of LLM Unlearning via Quantization" (ICLR 2025)☆26Updated last month
- [ICLR 2025] Code&Data for the paper "Super(ficial)-alignment: Strong Models May Deceive Weak Models in Weak-to-Strong Generalization"☆13Updated 9 months ago
- ☆28Updated last year
- ConceptVectors Benchmark and Code for the paper "Intrinsic Evaluation of Unlearning Using Parametric Knowledge Traces"☆33Updated last month
- Code for paper "Unraveling Cross-Modality Knowledge Conflicts in Large Vision-Language Models."☆42Updated 5 months ago
- ☆48Updated 4 months ago
- Code for "Surgical Fine-Tuning Improves Adaptation to Distribution Shifts" published at ICLR 2023☆29Updated last year
- ☆16Updated 3 weeks ago
- ☆33Updated 5 months ago
- source code for NeurIPS'24 paper "HaloScope: Harnessing Unlabeled LLM Generations for Hallucination Detection"☆32Updated 3 months ago
- [NeurIPS 2024] "Can Language Models Perform Robust Reasoning in Chain-of-thought Prompting with Noisy Rationales?"☆35Updated 2 months ago
- ☆13Updated last year
- This is the repository for "Model Merging by Uncertainty-Based Gradient Matching", ICLR 2024.☆27Updated 10 months ago
- [NeurIPS 2024 Spotlight] EMR-Merging: Tuning-Free High-Performance Model Merging☆52Updated 3 weeks ago
- This repository is the official implementation of Unleashing the Power of Contrastive Self-Supervised Visual Models via Contrast-Regulari…☆21Updated 2 years ago
- Official code repository for Correct-N-Contrast☆21Updated 2 years ago
- ☆19Updated 7 months ago
- Code for paper: “What Data Benefits My Classifier?” Enhancing Model Performance and Interpretability through Influence-Based Data Selecti…☆22Updated 10 months ago
- The official code for the publication: "The Close Relationship Between Contrastive Learning and Meta-Learning".☆19Updated 2 years ago
- Codebase for decoding compressed trust.☆23Updated 10 months ago
- Code for paper "Parameter Efficient Multi-task Model Fusion with Partial Linearization"☆19Updated 6 months ago
- Representation Surgery for Multi-Task Model Merging. ICML, 2024.☆42Updated 5 months ago
- ☆65Updated 3 years ago