zzp1012 / Cross-Task-LinearityLinks
[ICML 2024] Code release for "On the Emergence of Cross-Task Linearity in Pretraining-Finetuning Paradigm"
☆11Updated 5 months ago
Alternatives and similar repositories for Cross-Task-Linearity
Users that are interested in Cross-Task-Linearity are comparing it to the libraries listed below
Sorting:
- [ICLR 2025] "Rethinking LLM Unlearning Objectives: A Gradient Perspective and Go Beyond"☆12Updated 5 months ago
- [NeurIPS 2024] "Can Language Models Perform Robust Reasoning in Chain-of-thought Prompting with Noisy Rationales?"☆35Updated 3 weeks ago
- [NeurIPS 2023] Code release for "Going Beyond Linear Mode Connectivity: The Layerwise Linear Feature Connectivity"☆18Updated last year
- AdaMerging: Adaptive Model Merging for Multi-Task Learning. ICLR, 2024.☆88Updated 9 months ago
- [NeurIPS2023] "Selectivity Drives Productivity: Efficient Dataset Pruning for Enhanced Transfer Learning" by Yihua Zhang*, Yimeng Zhang*,…☆13Updated last year
- Representation Surgery for Multi-Task Model Merging. ICML, 2024.☆46Updated 9 months ago
- [NeurIPS 2024 Spotlight] EMR-Merging: Tuning-Free High-Performance Model Merging☆62Updated 5 months ago
- ☆24Updated 2 years ago
- translation of VHL repo in paddle☆25Updated 2 years ago
- Official repository of "Localizing Task Information for Improved Model Merging and Compression" [ICML 2024]☆47Updated 9 months ago
- Prioritize Alignment in Dataset Distillation☆20Updated 8 months ago
- [CVPR2024 highlight] Generalized Large-Scale Data Condensation via Various Backbone and Statistical Matching (G-VBSM)☆28Updated 9 months ago
- This repository is the official implementation of Dataset Condensation with Contrastive Signals (DCC), accepted at ICML 2022.☆22Updated 3 years ago
- [NeurIPS 2024] "Mind the Gap between Prototypes and Images in Cross-domain Finetuning"☆11Updated 8 months ago
- This is the official code for the paper "Booster: Tackling Harmful Fine-tuning for Large Language Models via Attenuating Harmful Perturba…☆29Updated 4 months ago
- ☆86Updated 2 years ago
- [ICLR 2025 Spotlight] Code release for "Sharpness-Aware Minimization Efficiently Selects Flatter Minima Late In Training"☆13Updated 5 months ago
- ☆35Updated last year
- [ECCV 2024] Official PyTorch Implementation of "How Many Unicorns Are in This Image? A Safety Evaluation Benchmark for Vision LLMs"☆81Updated last year
- ☆15Updated 11 months ago
- Official Repository for The Paper: Safety Alignment Should Be Made More Than Just a Few Tokens Deep☆143Updated 3 months ago
- ☆29Updated 2 years ago
- Code for paper "Parameter Efficient Multi-task Model Fusion with Partial Linearization"☆21Updated 10 months ago
- [ICML 2025] "From Passive to Active Reasoning: Can Large Language Models Ask the Right Questions under Incomplete Information?"☆19Updated 3 weeks ago
- ☆21Updated 4 months ago
- (ICML 2023) Discover and Cure: Concept-aware Mitigation of Spurious Correlation☆41Updated last year
- Github repo for NeurIPS 2024 paper "Safe LoRA: the Silver Lining of Reducing Safety Risks when Fine-tuning Large Language Models"☆17Updated 3 weeks ago
- A Task of Fictitious Unlearning for VLMs☆19Updated 4 months ago
- Localize-and-Stitch: Efficient Model Merging via Sparse Task Arithmetic☆27Updated 6 months ago
- [ICML 2024] Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models.☆72Updated 6 months ago