Cover Image

From "Weak" Signals to Strong Models: Preference Delta Aggregation with LoRA Merging

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Sun, Qi, Zhang, Siyue, Chen, Yulin, Xue, Yuxiang, Peng, Ru, Zhao, Chen
Format:	Preprint
Published:	2026
Subjects:	Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

LoBAM: LoRA-Based Backdoor Attack on Model Merging
by: Yin, Ming, et al.
Published: (2024)

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

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

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

Unraveling LoRA Interference: Orthogonal Subspaces for Robust Model Merging
by: Zhang, Haobo, et al.
Published: (2025)

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

Evolutionary Negative Module Pruning for Better LoRA Merging
by: Cao, Anda, et al.
Published: (2026)

Preference-Aligned LoRA Merging: Preserving Subspace Coverage and Addressing Directional Anisotropy
by: Jeong, Wooseong, et al.
Published: (2026)

Convergence Analysis of Aggregation-Broadcast in LoRA-enabled Distributed Fine-Tuning
by: Chen, Xin, et al.
Published: (2025)

Search, Do not Guess: Teaching Small Language Models to Be Effective Search Agents
by: Liu, Yizhou, et al.
Published: (2026)

MapReduce LoRA: Advancing the Pareto Front in Multi-Preference Optimization for Generative Models
by: Chen, Chieh-Yun, et al.
Published: (2025)

Higher Layers Need More LoRA Experts
by: Gao, Chongyang, et al.
Published: (2024)

LoRA-Leak: Membership Inference Attacks Against LoRA Fine-tuned Language Models
by: Ran, Delong, et al.
Published: (2025)

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

Causal-Guided Detoxify Backdoor Attack of Open-Weight LoRA Models
by: Chen, Linzhi, et al.
Published: (2025)

A Note on LoRA
by: Fomenko, Vlad, et al.
Published: (2024)

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

LoRA as Oracle
by: Arazzi, Marco, et al.
Published: (2026)

Reversible Lifelong Model Editing via Semantic Routing-Based LoRA
by: Luo, Haihua, et al.
Published: (2026)

Beyond Factor Aggregation: Gauge-Aware Low-Rank Server Representations for Federated LoRA
by: Chen, Jinqian, et al.
Published: (2026)

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

LoRA Meets Dropout under a Unified Framework
by: Wang, Sheng, et al.
Published: (2024)

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

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

Improving the Serving Performance of Multi-LoRA Large Language Models via Efficient LoRA and KV Cache Management
by: Zhang, Hang, et al.
Published: (2025)

LoRA in LoRA: Towards Parameter-Efficient Architecture Expansion for Continual Visual Instruction Tuning
by: Che, Chang, et al.
Published: (2025)

LoRA is All You Need for Safety Alignment of Reasoning LLMs
by: Xue, Yihao, et al.
Published: (2025)

In-Context Meta LoRA Generation
by: Shao, Yihua, et al.
Published: (2025)

The Scaling Law for LoRA Base on Mutual Information Upper Bound
by: Zhang, Jing, et al.
Published: (2025)

Conditional LoRA Parameter Generation
by: Jin, Xiaolong, et al.
Published: (2024)

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

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

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

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

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

SAMoRA: Semantic-Aware Mixture of LoRA Experts for Task-Adaptive Learning
by: Shi, Boyan, et al.
Published: (2026)

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

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

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

Empower Vision Applications with LoRA LMM
by: Mi, Liang, et al.
Published: (2024)