LiNeS: Post-training Layer Scaling Prevents Forgetting and Enhances Model Merging Paper • 2410.17146 • Published Oct 22, 2024
SequeL: A Continual Learning Library in PyTorch and JAX Paper • 2304.10857 • Published Apr 21, 2023 • 1
Localizing Task Information for Improved Model Merging and Compression Paper • 2405.07813 • Published May 13, 2024
Pareto Low-Rank Adapters: Efficient Multi-Task Learning with Preferences Paper • 2407.08056 • Published Jul 10, 2024
Pareto Manifold Learning: Tackling multiple tasks via ensembles of single-task models Paper • 2210.09759 • Published Oct 18, 2022