Imagen de Portada

Beware of the Batch Size: Hyperparameter Bias in Evaluating LoRA

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Lee, Sangyoon, Lee, Jaeho
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Riemannian Optimization for LoRA on the Stiefel Manifold
por: Park, Juneyoung, et al.
Publicado: (2025)

Fast Training of Sinusoidal Neural Fields via Scaling Initialization
por: Yeom, Taesun, et al.
Publicado: (2024)

LoRA on the Go: Instance-level Dynamic LoRA Selection and Merging
por: Lee, Seungeon, et al.
Publicado: (2025)

A Note on LoRA
por: Fomenko, Vlad, et al.
Publicado: (2024)

LoRA Users Beware: A Few Spurious Tokens Can Manipulate Your Finetuned Model
por: Salles, Marcel Mateos, et al.
Publicado: (2025)

S-LoRA: Serving Thousands of Concurrent LoRA Adapters
por: Sheng, Ying, et al.
Publicado: (2023)

FedSVD: Adaptive Orthogonalization for Private Federated Learning with LoRA
por: Lee, Seanie, et al.
Publicado: (2025)

Kron-LoRA: Hybrid Kronecker-LoRA Adapters for Scalable, Sustainable Fine-tuning
por: Shen, Yixin
Publicado: (2025)

R-LoRA: Randomized Multi-Head LoRA for Efficient Multi-Task Learning
por: Liu, Jinda, et al.
Publicado: (2025)

LoRA-Mixer: Coordinate Modular LoRA Experts Through Serial Attention Routing
por: Li, Wenbing, et al.
Publicado: (2025)

Mechanistic Interpretability of LoRA-Adapted Language Models for Nuclear Reactor Safety Applications
por: Lee, Yoon Pyo
Publicado: (2025)

FALQON: Accelerating LoRA Fine-tuning with Low-Bit Floating-Point Arithmetic
por: Choi, Kanghyun, et al.
Publicado: (2025)

SCALE-LoRA: Auditing Post-Retrieval LoRA Composition with Residual Merging and View Reliability
por: Zhou, Shuaipeng, et al.
Publicado: (2026)

Conditional LoRA Parameter Generation
por: Jin, Xiaolong, et al.
Publicado: (2024)

SC-LoRA: Balancing Efficient Fine-tuning and Knowledge Preservation via Subspace-Constrained LoRA
por: Luo, Minrui, et al.
Publicado: (2025)

FiLoRA: Focus-and-Ignore LoRA for Controllable Feature Reliance
por: Chung, Hyunsuk, et al.
Publicado: (2026)

LoRA Done RITE: Robust Invariant Transformation Equilibration for LoRA Optimization
por: Yen, Jui-Nan, et al.
Publicado: (2024)

Hybrid-LoRA: Bridging Full Fine-Tuning and Low-Rank Adaptation for Post-Training
por: Zhang, Chengqian, et al.
Publicado: (2026)

LoRALib: A Standardized Benchmark for Evaluating LoRA-MoE Methods
por: Wang, Shaoheng, et al.
Publicado: (2025)

Subliminal Learning is a LoRA Artifact
por: Nief, Todd, et al.
Publicado: (2026)

Semantic-guided LoRA Parameters Generation
por: Li, Miaoge, et al.
Publicado: (2025)

Text-to-LoRA: Instant Transformer Adaption
por: Charakorn, Rujikorn, et al.
Publicado: (2025)

KD-LoRA: A Hybrid Approach to Efficient Fine-Tuning with LoRA and Knowledge Distillation
por: Azimi, Rambod, et al.
Publicado: (2024)

HiLoRA: Adaptive Hierarchical LoRA Routing for Training-Free Domain Generalization
por: Han, Ziyi, et al.
Publicado: (2025)

Improving LoRA with Variational Learning
por: Cong, Bai, et al.
Publicado: (2025)

Rethinking the Rank Threshold for LoRA Fine-Tuning
por: Park, Juneyoung
Publicado: (2026)

Activated LoRA: Fine-tuned LLMs for Intrinsics
por: Greenewald, Kristjan, et al.
Publicado: (2025)

ALTO: Adaptive LoRA Tuning and Orchestration for Heterogeneous LoRA Training Workloads
por: Zuo, Jingwei, et al.
Publicado: (2026)

ALLoRA: Adaptive Learning Rate Mitigates LoRA Fatal Flaws
por: Huang, Hai, et al.
Publicado: (2024)

FedTreeLoRA: Reconciling Statistical and Functional Heterogeneity in Federated LoRA Fine-Tuning
por: Bian, Jieming, et al.
Publicado: (2026)

Effective LoRA Adapter Routing using Task Representations
por: Dhasade, Akash, et al.
Publicado: (2026)

LoRA Dropout as a Sparsity Regularizer for Overfitting Control
por: Lin, Yang, et al.
Publicado: (2024)

IterIS: Iterative Inference-Solving Alignment for LoRA Merging
por: Chen, Hongxu, et al.
Publicado: (2024)

The Impact of Initialization on LoRA Finetuning Dynamics
por: Hayou, Soufiane, et al.
Publicado: (2024)

LoRA Learns Less and Forgets Less
por: Biderman, Dan, et al.
Publicado: (2024)

LoRA Is Slower Than You Think
por: Ko, Seokmin
Publicado: (2025)

RILQ: Rank-Insensitive LoRA-based Quantization Error Compensation for Boosting 2-bit Large Language Model Accuracy
por: Lee, Geonho, et al.
Publicado: (2024)

DLP-LoRA: Efficient Task-Specific LoRA Fusion with a Dynamic, Lightweight Plugin for Large Language Models
por: Zhang, Yuxuan, et al.
Publicado: (2024)

mLoRA: Fine-Tuning LoRA Adapters via Highly-Efficient Pipeline Parallelism in Multiple GPUs
por: Ye, Zhengmao, et al.
Publicado: (2023)

Label-Free Cross-Task LoRA Merging with Null-Space Compression
por: Lee, Wonyoung, et al.
Publicado: (2026)