conftrace_

parameter importance

14 papers

Explore in graph

Co-occurring keywords

large language model (13587) fisher information (106) catastrophic forgetting (958) continual learning (1181) model compression (3302) model pruning (237) model merging (234) federated learning (1333) cherry parameter (1) domain shift (318)

Papers

Parameter Importance is Not Static: Evolving Parameter Isolation for Supervised Fine-Tuning ACL 2026
Recurrent Knowledge Identification and Fusion for Language Model Continual Learning ACL 2025
Dynamic Fisher-weighted Model Merging via Bayesian Optimization NAACL 2025
Adapting In-Domain Few-Shot Segmentation to New Domains without Source Domain Retraining ICCV 2025
Math Neurosurgery: Isolating Language Models’ Math Reasoning Abilities Using Only Forward Passes ACL 2025
Cherry on Top: Parameter Heterogeneity and Quantization in Large Language Models NIPS 2024
Surrogate Active Subspaces for Jump-Discontinuous Functions AISTATS 2024
FIARSE: Model-Heterogeneous Federated Learning via Importance-Aware Submodel Extraction NIPS 2024
Parameter Disparities Dissection for Backdoor Defense in Heterogeneous Federated Learning NIPS 2024
Pruning Pre-trained Language Models with Principled Importance and Self-regularization ACL 2023
Unifying Importance Based Regularisation Methods for Continual Learning AISTATS 2022
Numerical Optimizations for Weighted Low-rank Estimation on Language Models EMNLP 2022
Image De-Raining via Continual Learning CVPR 2021
Not all parameters are born equal: Attention is mostly what you need EMNLP 2021