Image de couverture de livre

PLATE: Plasticity-Tunable Efficient Adapters for Geometry-Aware Continual Learning

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteur principal:	Cosentino, Romain
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Characterizing Large Language Model Geometry Helps Solve Toxicity Detection and Generation
par: Balestriero, Randall, et autres
Publié: (2023)

Tunable MAGMAX: Preference-Aware Model Merging for Continual Learning
par: Hiroshima, Kei, et autres
Publié: (2026)

Sparse Adapter Fusion for Continual Learning in NLP
par: Zeng, Min, et autres
Publié: (2026)

Self-Normalized Resets for Plasticity in Continual Learning
par: Farias, Vivek F., et autres
Publié: (2024)

Plasticity vs. Rigidity: The Impact of Low-Rank Adapters on Reasoning on a Micro-Budget
par: Khan, Zohaib, et autres
Publié: (2026)

Addressing Loss of Plasticity and Catastrophic Forgetting in Continual Learning
par: Elsayed, Mohamed, et autres
Publié: (2024)

Preserving Plasticity in Continual Learning with Adaptive Linearity Injection
par: Rohani, Seyed Roozbeh Razavi, et autres
Publié: (2025)

Maintaining Plasticity in Continual Learning via Regenerative Regularization
par: Kumar, Saurabh, et autres
Publié: (2023)

Adaptive Budget Allocation for Orthogonal-Subspace Adapter Tuning in LLMs Continual Learning
par: Wan, Zhiyi, et autres
Publié: (2025)

Context-Aware Adapter Tuning for Few-Shot Relation Learning in Knowledge Graphs
par: Liu, Ran, et autres
Publié: (2024)

Mitigating Plasticity Loss in Continual Reinforcement Learning by Reducing Churn
par: Tang, Hongyao, et autres
Publié: (2025)

Scaling-Aware Adapter for Structure-Grounded LLM Reasoning
par: Jing, Zihao, et autres
Publié: (2026)

\textsc{MasFACT}: Continual Multi-Agent Topology Learning via Geometry-Aware Posterior Transfer
par: Wang, Xuefei, et autres
Publié: (2026)

Beyond Retention: Orchestrating Structural Safety and Plasticity in Continual Learning for LLMs
par: Meng, Fei
Publié: (2026)

Learning to Route for Dynamic Adapter Composition in Continual Learning with Language Models
par: Araujo, Vladimir, et autres
Publié: (2024)

Pareto Continual Learning: Preference-Conditioned Learning and Adaption for Dynamic Stability-Plasticity Trade-off
par: Lai, Song, et autres
Publié: (2025)

On the Geometry of Reinforcement Learning in Continuous State and Action Spaces
par: Tiwari, Saket, et autres
Publié: (2022)

Geometry of Neural Reinforcement Learning in Continuous State and Action Spaces
par: Tiwari, Saket, et autres
Publié: (2025)

JumpLoRA: Sparse Adapters for Continual Learning in Large Language Models
par: Dragomir, Alexandra, et autres
Publié: (2026)

SplitLoRA: Balancing Stability and Plasticity in Continual Learning Through Gradient Space Splitting
par: Qiu, Haomiao, et autres
Publié: (2025)

GeoAda: Efficiently Finetune Geometric Diffusion Models with Equivariant Adapters
par: Zhao, Wanjia, et autres
Publié: (2025)

PACIA: Parameter-Efficient Adapter for Few-Shot Molecular Property Prediction
par: Wu, Shiguang, et autres
Publié: (2023)

Geometry-Aware Contrastive Learning for Few-Shot Automatic Modulation Recognition
par: Zhao, Guanqun, et autres
Publié: (2026)

A Geometry-Aware Algorithm to Learn Hierarchical Embeddings in Hyperbolic Space
par: Wang, Zhangyu, et autres
Publié: (2024)

Task-Aware Adaptive Modulation: A Replay-Free and Resource-Efficient Approach For Continual Graph Learning
par: Liu, Jingtao, et autres
Publié: (2025)

Not All Adapters Matter: Selective Adapter Freezing for Memory-Efficient Fine-Tuning of Language Models
par: Son, Hyegang, et autres
Publié: (2024)

Experience Replay Addresses Loss of Plasticity in Continual Learning
par: Wang, Jiuqi, et autres
Publié: (2025)

OrchMoE: Efficient Multi-Adapter Learning with Task-Skill Synergy
par: Wang, Haowen, et autres
Publié: (2024)

Rethinking Plasticity in Deep Reinforcement Learning
par: He, Zhiqiang
Publié: (2026)

TaskVAE: Task-Specific Variational Autoencoders for Exemplar Generation in Continual Learning for Human Activity Recognition
par: Kann, Bonpagna, et autres
Publié: (2025)

Sparse High Rank Adapters
par: Bhardwaj, Kartikeya, et autres
Publié: (2024)

Navigating Potholes with Geometry-Aware Sharpness Minimization
par: Dufort-Labbé, Simon, et autres
Publié: (2026)

WIMLE: Uncertainty-Aware World Models with IMLE for Sample-Efficient Continuous Control
par: Aghabozorgi, Mehran, et autres
Publié: (2026)

Continual Adapter Tuning with Semantic Shift Compensation for Class-Incremental Learning
par: Zhou, Qinhao, et autres
Publié: (2024)

Magnitude-Modulated Equivariant Adapter for Parameter-Efficient Fine-Tuning of Equivariant Graph Neural Networks
par: Jin, Dian, et autres
Publié: (2025)

EigenLoRAx: Recycling Adapters to Find Principal Subspaces for Resource-Efficient Adaptation and Inference
par: Kaushik, Prakhar, et autres
Publié: (2025)

SketchOGD: Memory-Efficient Continual Learning
par: Min, Youngjae, et autres
Publié: (2023)

CRAFT: Forgetting-Aware Intervention-Based Adaptation for Continual Learning
par: Hossen, Md Anwar, et autres
Publié: (2026)

Activation Function Design Sustains Plasticity in Continual Learning
par: Lillo, Lute, et autres
Publié: (2025)

GO-OSC and VASH: Geometry-Aware Representation Learning for Early Degradation Detection in Oscillatory Systems
par: Nobaub, Vashista
Publié: (2026)