Cover Image

Parameter Importance-Driven Continual Learning for Foundation Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Lingxiang, Zhang, Hainan, Zheng, Zhiming
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

HSF: Defending against Jailbreak Attacks with Hidden State Filtering
by: Qian, Cheng, et al.
Published: (2024)

TSN-Affinity: Similarity-Driven Parameter Reuse for Continual Offline Reinforcement Learning
by: Żurek, Dominik, et al.
Published: (2026)

A Survey on Parameter-Efficient Fine-Tuning for Foundation Models in Federated Learning
by: Bian, Jieming, et al.
Published: (2025)

CodeBC: A More Secure Large Language Model for Smart Contract Code Generation in Blockchain
by: Wang, Lingxiang, et al.
Published: (2025)

The Importance of Being Lazy: Scaling Limits of Continual Learning
by: Graldi, Jacopo, et al.
Published: (2025)

$\texttt{MiniMol}$: A Parameter-Efficient Foundation Model for Molecular Learning
by: Kläser, Kerstin, et al.
Published: (2024)

Parameter-Efficient Fine-Tuning for Foundation Models
by: Zhang, Dan, et al.
Published: (2025)

Prompt-Driven Continual Graph Learning
by: Wang, Qi, et al.
Published: (2025)

Rethinking the Foundations for Continual Reinforcement Learning
by: Elelimy, Esraa, et al.
Published: (2025)

The Future of Continual Learning in the Era of Foundation Models: Three Key Directions
by: Bell, Jack, et al.
Published: (2025)

Stable Forgetting: Bounded Parameter-Efficient Unlearning in Foundation Models
by: Garg, Arpit, et al.
Published: (2025)

Principled Curriculum Learning using Parameter Continuation Methods
by: Pathak, Harsh Nilesh, et al.
Published: (2025)

Federated Generative Learning with Foundation Models
by: Zhang, Jie, et al.
Published: (2023)

Diffusion Models for Reinforcement Learning: Foundations, Taxonomy, and Development
by: Xu, Changfu, et al.
Published: (2025)

EAGLE: Edge-Aware Graph Learning for Proactive Delivery Delay Prediction in Smart Logistics Networks
by: Xue, Zhiming, et al.
Published: (2026)

Importance Analysis for Dynamic Control of Balancing Parameter in a Simple Knowledge Distillation Setting
by: Kim, Seongmin, et al.
Published: (2025)

GILT: An LLM-Free, Tuning-Free Graph Foundational Model for In-Context Learning
by: Ma, Weishuo, et al.
Published: (2025)

Wavelet-Driven Masked Multiscale Reconstruction for PPG Foundation Models
by: Thukral, Megha, et al.
Published: (2026)

Dynamic Continual Learning: Harnessing Parameter Uncertainty for Improved Network Adaptation
by: Angelini, Christopher, et al.
Published: (2025)

Importance Sampling for Nonlinear Models
by: Rajmohan, Prakash Palanivelu, et al.
Published: (2025)

Relative Importance Sampling for off-Policy Actor-Critic in Deep Reinforcement Learning
by: Humayoo, Mahammad, et al.
Published: (2018)

FedPFT: Federated Proxy Fine-Tuning of Foundation Models
by: Peng, Zhaopeng, et al.
Published: (2024)

PPSEBM: An Energy-Based Model with Progressive Parameter Selection for Continual Learning
by: Li, Xiaodi, et al.
Published: (2025)

BID-LoRA: A Parameter-Efficient Framework for Continual Learning and Unlearning
by: Rachapudi, Jagadeesh, et al.
Published: (2026)

Foundations and Frontiers of Graph Learning Theory
by: Huang, Yu, et al.
Published: (2024)

Foundation Model in Biomedicine
by: Liu, Xiangrui, et al.
Published: (2025)

From Predictive Importance to Causality: Which Machine Learning Model Reflects Reality?
by: Arshad, Muhammad Arbab, et al.
Published: (2024)

Puppet-CNN: Continuous Parameter Dynamics for Input-Adaptive Convolutional Networks
by: Xing, Yucheng, et al.
Published: (2024)

AIS: Adaptive Importance Sampling for Quantized RL
by: Zhou, Jiajun, et al.
Published: (2026)

Parameter-Efficient Fine-Tuning for Continual Learning: A Neural Tangent Kernel Perspective
by: Liu, Jingren, et al.
Published: (2024)

Event Fields: Learning Latent Event Structure for Waveform Foundation Models
by: Na, Li, et al.
Published: (2026)

Ergodic Risk Measures: Towards a Risk-Aware Foundation for Continual Reinforcement Learning
by: Rojas, Juan Sebastian, et al.
Published: (2025)

Continual Harness: Online Adaptation for Self-Improving Foundation Agents
by: Karten, Seth, et al.
Published: (2026)

GIPO: Gaussian Importance Sampling Policy Optimization
by: Lu, Chengxuan, et al.
Published: (2026)

From Parameters to Performance: A Data-Driven Study on LLM Structure and Development
by: Wang, Suqing, et al.
Published: (2025)

Theory Foundation of Physics-Enhanced Residual Learning
by: Liang, Shixiao, et al.
Published: (2025)

Adaptive Pruning for Large Language Models with Structural Importance Awareness
by: Zheng, Haotian, et al.
Published: (2024)

Learning to Detect Critical Nodes in Sparse Graphs via Feature Importance Awareness
by: Tan, Xuwei, et al.
Published: (2021)

Non-Interfering Weight Fields: Treating Model Parameters as a Continuously Extensible Function
by: Chaudhry, Sarim
Published: (2026)

The Importance of Architecture Choice in Deep Learning for Climate Applications
by: Dräger, Simon, et al.
Published: (2024)