# VB-LoRA: Extreme Parameter Efficient Fine-Tuning with Vector Banks

arXiv: https://arxiv.org/abs/2405.15179 · HTML: https://mlsanity.com/paper/2405.15179/

## Key facts

- Cited by 52 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 65 references that are in the map.
- First posted on arXiv 24 May 2024.

## Builds on (most cited first, 30 of 39)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding](https://mlsanity.com/paper/1804.07461/) (2018)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [Mixtral of Experts](https://mlsanity.com/paper/2401.04088/) (2024)
- [Know What You Don't Know: Unanswerable Questions for SQuAD](https://mlsanity.com/paper/1806.03822/) (2018)
- [BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models](https://mlsanity.com/paper/2106.10199/) (2021)
- [The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables](https://mlsanity.com/paper/1611.00712/) (2016)
- [SemEval-2017 Task 1: Semantic Textual Similarity - Multilingual and Cross-lingual Focused Evaluation](https://mlsanity.com/paper/1708.00055/) (2017)
- [Neural Network Acceptability Judgments](https://mlsanity.com/paper/1805.12471/) (2018)
- [Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning](https://mlsanity.com/paper/2205.05638/) (2022)
- [Towards a Unified View of Parameter-Efficient Transfer Learning](https://mlsanity.com/paper/2110.04366/) (2021)
- [MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models](https://mlsanity.com/paper/2309.12284/) (2023)
- [Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-Tuning](https://mlsanity.com/paper/2012.13255/) (2020)
- [Compacter: Efficient Low-Rank Hypercomplex Adapter Layers](https://mlsanity.com/paper/2106.04647/) (2021)
- [Parameter-efficient Multi-task Fine-tuning for Transformers via Shared Hypernetworks](https://mlsanity.com/paper/2106.04489/) (2021)
- [The E2E Dataset: New Challenges For End-to-End Generation](https://mlsanity.com/paper/1706.09254/) (2017)
- [S-LoRA: Serving Thousands of Concurrent LoRA Adapters](https://mlsanity.com/paper/2311.03285/) (2023)
- [Domain Specialization as the Key to Make Large Language Models Disruptive: A Comprehensive Survey](https://mlsanity.com/paper/2305.18703/) (2023)
- [FacT: Factor-Tuning for Lightweight Adaptation on Vision Transformer](https://mlsanity.com/paper/2212.03145/) (2022)

## Built on by (most cited first, 30 of 52)

- [A Survey on LoRA of Large Language Models](https://mlsanity.com/paper/2407.11046/) (2024)
- [The Impact of Initialization on LoRA Finetuning Dynamics](https://mlsanity.com/paper/2406.08447/) (2024)
- [Towards Understanding Safety Alignment: A Mechanistic Perspective from Safety Neurons](https://mlsanity.com/paper/2406.14144/) (2024)
- [Unlearning Backdoor Attacks for LLMs with Weak-to-Strong Knowledge Distillation](https://mlsanity.com/paper/2410.14425/) (2024)
- [Learning to Reason in 13 Parameters](https://mlsanity.com/paper/2602.04118/) (2026)
- [NoRA: Nested Low-Rank Adaptation for Efficient Fine-Tuning Large Models](https://mlsanity.com/paper/2408.10280/) (2024)
- [ShareLoRA: Parameter Efficient and Robust Large Language Model Fine-tuning via Shared Low-Rank Adaptation](https://mlsanity.com/paper/2406.10785/) (2024)
- [Learning Rate Matters: Vanilla LoRA May Suffice for LLM Fine-tuning](https://mlsanity.com/paper/2602.04998/) (2026)
- [QR-LoRA: Efficient and Disentangled Fine-tuning via QR Decomposition for Customized Generation](https://mlsanity.com/paper/2507.04599/) (2025)
- [Learning Rate Scaling across LoRA Ranks and Transfer to Full Finetuning](https://mlsanity.com/paper/2602.06204/) (2026)
- [MALoRA: Mixture of Asymmetric Low-Rank Adaptation for Enhanced Multi-Task Learning](https://mlsanity.com/paper/2410.22782/) (2024)
- [Exploring Sparsity for Parameter Efficient Fine Tuning Using Wavelets for Vision](https://mlsanity.com/paper/2505.12532/) (2025)
- [Uni-LoRA: One Vector is All You Need](https://mlsanity.com/paper/2506.00799/) (2025)
- [RaSA: Rank-Sharing Low-Rank Adaptation](https://mlsanity.com/paper/2503.12576/) (2025)
- [Beyond Higher Rank: Token-wise Input-Output Projections for Efficient Low-Rank Adaptation](https://mlsanity.com/paper/2510.23123/) (2025)
- [TARA: Token-Aware LoRA for Composable Personalization in Diffusion Models](https://mlsanity.com/paper/2508.08812/) (2025)
- [WeightLoRA: Keep Only Necessary Adapters](https://mlsanity.com/paper/2506.02724/) (2025)
- [MetaTT: A Global Tensor-Train Adapter for Parameter-Efficient Fine-Tuning](https://mlsanity.com/paper/2506.09105/) (2025)
- [Dynamic Context-oriented Decomposition for Task-aware Low-rank Adaptation with Less Forgetting and Faster Convergence](https://mlsanity.com/paper/2506.13187/) (2025)
- [BoRA: Towards More Expressive Low-Rank Adaptation with Block Diversity](https://mlsanity.com/paper/2508.06953/) (2025)
- [HOFT: Householder Orthogonal Fine-tuning](https://mlsanity.com/paper/2505.16531/) (2025)
- [Optimization-Inspired Few-Shot Adaptation for Large Language Models](https://mlsanity.com/paper/2505.19107/) (2025)
- [Localized LoRA-MoE: Block-wise Low-Rank Experts With Adaptive Routing](https://mlsanity.com/paper/2607.05114/) (2026)
- [1LoRA: Summation Compression for Very Low-Rank Adaptation](https://mlsanity.com/paper/2503.08333/) (2025)
- [Revisiting LoRA through the Lens of Parameter Redundancy: Spectral Encoding Helps](https://mlsanity.com/paper/2506.16787/) (2025)
- [A Unified Study of LoRA Variants: Taxonomy, Review, Codebase, and Empirical Evaluation](https://mlsanity.com/paper/2601.22708/) (2026)
- [Meta-LoRA: Meta-Learning LoRA Components for Domain-Aware ID Personalization](https://mlsanity.com/paper/2503.22352/) (2025)
- [TLoRA: Tri-Matrix Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2504.18735/) (2025)
- [Localized LoRA: A Structured Low-Rank Approximation for Efficient Fine-Tuning](https://mlsanity.com/paper/2506.00236/) (2025)
- [A Lightweight Framework for Trigger-Guided LoRA-Based Self-Adaptation in LLMs](https://mlsanity.com/paper/2509.05385/) (2025)

## Abstract (arXiv)

As the adoption of large language models increases and the need for per-user or per-task model customization grows, the parameter-efficient fine-tuning (PEFT) methods, such as low-rank adaptation (LoRA) and its variants, incur substantial storage and transmission costs. To further reduce stored parameters, we introduce a "divide-and-share" paradigm that breaks the barriers of low-rank decomposition across matrix dimensions, modules, and layers by sharing parameters globally via a vector bank. As an instantiation of the paradigm to LoRA, our proposed VB-LoRA composites all the low-rank matrices of LoRA from a shared vector bank with a differentiable top-k admixture module. VB-LoRA achieves extreme parameter efficiency while maintaining comparable or better performance compared to state-of-the-art PEFT methods. Extensive experiments demonstrate the effectiveness of VB-LoRA on natural language understanding, natural language generation, instruction tuning, and mathematical reasoning tasks. When fine-tuning the Llama2-13B model, VB-LoRA only uses 0.4% of LoRA's stored parameters, yet achieves superior results. Our source code is available at https://github.com/leo-yangli/VB-LoRA. This method has been merged into the Hugging Face PEFT package.