Skip to content
conftrace_

parameter regularization

8 papers

Explore in graph

Co-occurring keywords · papers mentioning both

catastrophic forgetting (3) lifelong learning (2) low-resource language (1) latent variable model (1) streaming data (1) foundation model (1) weight decay (1) model generalization (1) parameter-efficient tuning (1) language generation (1)

Papers

Limited-Resource Adapters Are Regularizers, Not Linguists ACL 2025 Rethinking Weight Decay for Robust Fine-Tuning of Foundation Models NeurIPS 2024 Task Difficulty Aware Parameter Allocation & Regularization for Lifelong Learning CVPR 2023 Exposure Normalization and Compensation for Multiple-Exposure Correction CVPR 2022 How Well Does Self-Supervised Pre-Training Perform with Streaming Data? ICLR 2022 Overcoming Catastrophic Forgetting During Domain Adaptation of Seq2seq Language Generation NAACL 2022 A Dirty Model for Multi-task Learning NeurIPS 2010 Learning the Semantic Correlation: An Alternative Way to Gain from Unlabeled Text NeurIPS 2008