paper-with-me

Papers

Tensorized Clustered LoRA Merging for Multi-Task Interference

2025-08-06 · Zhan Su, Fengran Mo, Guojun Liang, Jinghan Zhang, Bingbing Wen, Prayag Tiwari, Jian-Yun Nie arxiv

Despite the success of the monolithic dense paradigm of large language models (LLMs), the LoRA adapters offer an efficient solution by fine-tuning small task-specific modules and merging them with the base model. However, in multi-task settings, merging LoRA adapters trained on heterogeneous sources frequently causes \textit{task interference}, degrading downstream performance. To address this, we propose a tensorized clustered LoRA (TC-LoRA) library targeting to address the task interference at the \textit{text-level} and \textit{parameter-level}. At the \textit{text-level}, we cluster the training samples in the embedding space to capture input-format similarities, then train a specialized LoRA adapter for each cluster. At the \textit{parameter-level}, we introduce a joint Canonical Polyadic (CP) decomposition that disentangles task-specific and shared factors across LoRA adapters. This joint factorization preserves essential knowledge while reducing cross-task interference. Extensive experiments on out-of-domain zero-shot and skill-composition tasks-including reasoning, question answering, and coding. Compared to strong SVD-based baselines, TC-LoRA achieves +1.4\% accuracy on Phi-3 and +2.3\% on Mistral-7B (+2.3\%), demonstrating the effectiveness of TC-LoRA in LLM adaptation.

📄 PDF Abstract BibTeX arXiv:2508.03999

Code (0)

등록된 구현이 없습니다.

Tasks

Question Answering

Similar Papers 제목 키워드 기반

Comprehensive Design Space Exploration for Tensorized Neural Network Hardware Accelerators

2025-11-22 · Jinsong Zhang, Minghe Li, Jiayi Tian, Jinming Lu 외 arxiv

High-order tensor decomposition has been widely adopted to obtain compact deep neural networks for edge deployment. However, existing studies focus primarily on its algorithmic advantages such as accuracy and compression…

Explainable Tensorized Neural Ordinary Differential Equations forArbitrary-step Time Series Prediction

2020-11-26 · Penglei Gao, Xi Yang, Rui Zhang, Kaizhu Huang

We propose a continuous neural network architecture, termed Explainable Tensorized Neural Ordinary Differential Equations (ETN-ODE), for multi-step time series prediction at arbitrary time points. Unlike the existing app…

PredictionTime SeriesTime Series AnalysisTime Series Prediction

Tensorized Optical Multimodal Fusion Network

2023-02-17 · Yequan Zhao, Xian Xiao, Geza Kurczveil, Raymond G. Beausoleil 외

We propose the first tensorized optical multimodal fusion network architecture with a self-attention mechanism and low-rank tensor fusion. Simulation results show $51.3 \times$ less hardware requirement and $3.7\times 10…

Hierarchical Reference Sets for Robust Unsupervised Detection of Scattered and Clustered Outliers

2026-03-13 · Yiqun Zhang, Zexi Tan, Xiaopeng Luo, Yunlin Liu arxiv

Most real-world IoT data analysis tasks, such as clustering and anomaly event detection, are unsupervised and highly susceptible to the presence of outliers. In addition to sporadic scattered outliers caused by factors s…

Outlier Detection

GPU-accelerated Evolutionary Multiobjective Optimization Using Tensorized RVEA

2024-04-01 · Zhenyu Liang, Tao Jiang, Kebin Sun, Ran Cheng

Evolutionary multiobjective optimization has witnessed remarkable progress during the past decades. However, existing algorithms often encounter computational challenges in large-scale scenarios, primarily attributed to …

GPUMultiobjective Optimization