Imagen de Portada

Gradient-Based LoRA Rank Allocation Under GRPO: An Empirical Study

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autor principal:	Sawant, Yash Ganpat
Formato:	Preprint
Publicado:	2026
Materias:	Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Theory-Grounded Evaluation Exposes the Authorship Gap in LLM Personalization
por: Sawant, Yash Ganpat
Publicado: (2026)

High-Stakes Personalization: Rethinking LLM Customization for Individual Investor Decision-Making
por: Sawant, Yash Ganpat
Publicado: (2026)

FIM-LoRA: Task-Informative Rank Allocation for LoRA via Calibration-Time Gradient-Variance Estimation
por: Sathyavageeswaran, Ramakrishnan
Publicado: (2026)

LoRA-GA: Low-Rank Adaptation with Gradient Approximation
por: Wang, Shaowen, et al.
Publicado: (2024)

PeriodicLoRA: Breaking the Low-Rank Bottleneck in LoRA Optimization
por: Meng, Xiangdi, et al.
Publicado: (2024)

DR-LoRA: Dynamic Rank LoRA for Fine-Tuning Mixture-of-Experts Models
por: Deng, Guanzhi, et al.
Publicado: (2026)

GRASP LoRA: GRPO Guided Adapter Sparsity Policy for Cross Lingual Transfer
por: Hassan, Besher, et al.
Publicado: (2026)

HyperAdaLoRA: Accelerating LoRA Rank Allocation During Training via Hypernetworks without Sacrificing Performance
por: Zhang, Hao, et al.
Publicado: (2025)

Dual LoRA: Enhancing LoRA with Magnitude and Direction Updates
por: Xu, Yixing, et al.
Publicado: (2025)

LoRA-Drop: Temporal LoRA Decoding for Efficient LLM Inference
por: Rajabzadeh, Hossein, et al.
Publicado: (2026)

L1RA: Dynamic Rank Assignment in LoRA Fine-Tuning
por: Singh, Raul, et al.
Publicado: (2025)

GuiLoMo: Allocating Expert Number and Rank for LoRA-MoE via Bilevel Optimization with GuidedSelection Vectors
por: Zhang, Hengyuan, et al.
Publicado: (2025)

Vision as LoRA
por: Wang, Han, et al.
Publicado: (2025)

LoRA-Flow: Dynamic LoRA Fusion for Large Language Models in Generative Tasks
por: Wang, Hanqing, et al.
Publicado: (2024)

$D^2LoRA$: Data-Driven LoRA Initialization for Low Resource Tasks
por: SeraJ, Javad, et al.
Publicado: (2025)

AlphaLoRA: Assigning LoRA Experts Based on Layer Training Quality
por: Qing, Peijun, et al.
Publicado: (2024)

A Unified Study of LoRA Variants: Taxonomy, Review, Codebase, and Empirical Evaluation
por: He, Haonan, et al.
Publicado: (2026)

LoRA-drop: Efficient LoRA Parameter Pruning based on Output Evaluation
por: Zhou, Hongyun, et al.
Publicado: (2024)

LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning
por: Zhang, Longteng, et al.
Publicado: (2023)

LoRA-Pro: Are Low-Rank Adapters Properly Optimized?
por: Wang, Zhengbo, et al.
Publicado: (2024)

LoRA+: Efficient Low Rank Adaptation of Large Models
por: Hayou, Soufiane, et al.
Publicado: (2024)

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

Budgeted LoRA: Distillation as Structured Compute Allocation for Efficient Inference
por: Sabry, Mohammed, et al.
Publicado: (2026)

LoRA-Squeeze: Simple and Effective Post-Tuning and In-Tuning Compression of LoRA Modules
por: Vulić, Ivan, et al.
Publicado: (2026)

AFA-LoRA: Enabling Non-Linear Adaptations in LoRA with Activation Function Annealing
por: Li, Jiacheng, et al.
Publicado: (2025)

LoRA-Gen: Specializing Large Language Model via Online LoRA Generation
por: Xiao, Yicheng, et al.
Publicado: (2025)

ID-LoRA: Efficient Low-Rank Adaptation Inspired by Matrix Interpolative Decomposition
por: Ma, Xindian, et al.
Publicado: (2026)

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

Mixture of LoRA Experts
por: Wu, Xun, et al.
Publicado: (2024)

Make LoRA Great Again: Boosting LoRA with Adaptive Singular Values and Mixture-of-Experts Optimization Alignment
por: Fan, Chenghao, et al.
Publicado: (2025)

CA-LoRA: Adapting Existing LoRA for Compressed LLMs to Enable Efficient Multi-Tasking on Personal Devices
por: Zhao, Weilin, et al.
Publicado: (2023)

MTL-LoRA: Low-Rank Adaptation for Multi-Task Learning
por: Yang, Yaming, et al.
Publicado: (2024)

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

Merging LoRAs like Playing LEGO: Pushing the Modularity of LoRA to Extremes Through Rank-Wise Clustering
por: Zhao, Ziyu, et al.
Publicado: (2024)

Recover-to-Forget: Gradient Reconstruction from LoRA for Efficient LLM Unlearning
por: Liu, Yezi, et al.
Publicado: (2025)

LoRA Soups: Merging LoRAs for Practical Skill Composition Tasks
por: Prabhakar, Akshara, et al.
Publicado: (2024)

HydraLoRA: An Asymmetric LoRA Architecture for Efficient Fine-Tuning
por: Tian, Chunlin, et al.
Publicado: (2024)

HiP-LoRA: Budgeted Spectral Plasticity for Robust Low-Rank Adaptation
por: Chen, Lixian, et al.
Publicado: (2026)

Flexi-LoRA with Input-Adaptive Ranks: Efficient Finetuning for Speech and Reasoning Tasks
por: Li, Zongqian, et al.
Publicado: (2026)

Learning Rate Scaling across LoRA Ranks and Transfer to Full Finetuning
por: Chen, Nan, et al.
Publicado: (2026)