Image de couverture de livre

Position: Pause Recycling LoRAs and Prioritize Mechanisms to Uncover Limits and Effectiveness

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Chen, Mei-Yen, Hoang, Thi Thu Uyen, Hahn, Michael, Sarfraz, M. Saquib
Format:	Preprint
Publié:	2025
Sujets:	Computation and Language Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Mixture-of-LoRAs: An Efficient Multitask Tuning for Large Language Models
par: Feng, Wenfeng, et autres
Publié: (2024)

Rethinking Parameter Sharing for LLM Fine-Tuning with Multiple LoRAs
par: Ban, Hao, et autres
Publié: (2025)

Merging LoRAs like Playing LEGO: Pushing the Modularity of LoRA to Extremes Through Rank-Wise Clustering
par: Zhao, Ziyu, et autres
Publié: (2024)

MoSLD: An Extremely Parameter-Efficient Mixture-of-Shared LoRAs for Multi-Task Learning
par: Zhao, Lulu, et autres
Publié: (2024)

Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs
par: Microsoft, et autres
Publié: (2025)

ORAL: Prompting Your Large-Scale LoRAs via Conditional Recurrent Diffusion
par: Khan, Rana Muhammad Shahroz, et autres
Publié: (2025)

LoRA-Squeeze: Simple and Effective Post-Tuning and In-Tuning Compression of LoRA Modules
par: Vulić, Ivan, et autres
Publié: (2026)

The Bayesian Origin of the Probability Weighting Function in Human Representation of Probabilities
par: Tong, Xin, et autres
Publié: (2025)

On the Limitations of Vision-Language Models in Understanding Image Transforms
par: Anis, Ahmad Mustafa, et autres
Publié: (2025)

Position: Quo Vadis, Unsupervised Time Series Anomaly Detection?
par: Sarfraz, M. Saquib, et autres
Publié: (2024)

LoRA Done RITE: Robust Invariant Transformation Equilibration for LoRA Optimization
par: Yen, Jui-Nan, et autres
Publié: (2024)

CARLoS: Retrieval via Concise Assessment Representation of LoRAs at Scale
par: Sarfaty, Shahar, et autres
Publié: (2025)

Rank-1 LoRAs Encode Interpretable Reasoning Signals
par: Ward, Jake, et autres
Publié: (2025)

DR-LoRA: Dynamic Rank LoRA for Fine-Tuning Mixture-of-Experts Models
par: Deng, Guanzhi, et autres
Publié: (2026)

Dynamic Training-Free Fusion of Subject and Style LoRAs
par: Cao, Qinglong, et autres
Publié: (2026)

LoRA-Gen: Specializing Large Language Model via Online LoRA Generation
par: Xiao, Yicheng, et autres
Publié: (2025)

A Note on LoRA
par: Fomenko, Vlad, et autres
Publié: (2024)

Learning Rate Matters: Vanilla LoRA May Suffice for LLM Fine-tuning
par: Lee, Yu-Ang, et autres
Publié: (2026)

Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs
par: Hu, Zixuan, et autres
Publié: (2024)

LoRA on the Go: Instance-level Dynamic LoRA Selection and Merging
par: Lee, Seungeon, et autres
Publié: (2025)

Higher Layers Need More LoRA Experts
par: Gao, Chongyang, et autres
Publié: (2024)

LoRA Meets Dropout under a Unified Framework
par: Wang, Sheng, et autres
Publié: (2024)

HydraLoRA: An Asymmetric LoRA Architecture for Efficient Fine-Tuning
par: Tian, Chunlin, et autres
Publié: (2024)

Doc-to-LoRA: Learning to Instantly Internalize Contexts
par: Charakorn, Rujikorn, et autres
Publié: (2026)

LoraMap: Harnessing the Power of LoRA Connections
par: Park, Hyeryun, et autres
Publié: (2024)

LoRA-Leak: Membership Inference Attacks Against LoRA Fine-tuned Language Models
par: Ran, Delong, et autres
Publié: (2025)

KD-LoRA: A Hybrid Approach to Efficient Fine-Tuning with LoRA and Knowledge Distillation
par: Azimi, Rambod, et autres
Publié: (2024)

ALTER: Asymmetric LoRA for Token-Entropy-Guided Unlearning of LLMs
par: Chen, Xunlei, et autres
Publié: (2026)

LoRA Soups: Merging LoRAs for Practical Skill Composition Tasks
par: Prabhakar, Akshara, et autres
Publié: (2024)

DynMoLE: Boosting Mixture of LoRA Experts Fine-Tuning with a Hybrid Routing Mechanism
par: Li, Dengchun, et autres
Publié: (2025)

Improving LoRA with Variational Learning
par: Cong, Bai, et autres
Publié: (2025)

Chinese Essay Rhetoric Recognition Using LoRA, In-context Learning and Model Ensemble
par: Lai, Yuxuan, et autres
Publié: (2026)

In-Context Meta LoRA Generation
par: Shao, Yihua, et autres
Publié: (2025)

LoRATK: LoRA Once, Backdoor Everywhere in the Share-and-Play Ecosystem
par: Liu, Hongyi, et autres
Publié: (2024)

The Impact of Initialization on LoRA Finetuning Dynamics
par: Hayou, Soufiane, et autres
Publié: (2024)

LoRA Learns Less and Forgets Less
par: Biderman, Dan, et autres
Publié: (2024)

LoRA Is Slower Than You Think
par: Ko, Seokmin
Publié: (2025)

SAMoRA: Semantic-Aware Mixture of LoRA Experts for Task-Adaptive Learning
par: Shi, Boyan, et autres
Publié: (2026)

DLP-LoRA: Efficient Task-Specific LoRA Fusion with a Dynamic, Lightweight Plugin for Large Language Models
par: Zhang, Yuxuan, et autres
Publié: (2024)

Sci-LoRA: Mixture of Scientific LoRAs for Cross-Domain Lay Paraphrasing
par: Cheng, Ming, et autres
Publié: (2025)