# GLAM: Efficient Continual Learning at Scale via Grouped LoRA Adapter Merging

arXiv: https://arxiv.org/abs/2509.13211 · HTML: https://mlsanity.com/paper/2509.13211/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 34 references that are in the map.
- First posted on arXiv 16 Sep 2025.

## Builds on (most cited first, 24 of 24)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [iCaRL: Incremental Classifier and Representation Learning](https://mlsanity.com/paper/1611.07725/) (2016)
- [Gradient Episodic Memory for Continual Learning](https://mlsanity.com/paper/1706.08840/) (2017)
- [The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization](https://mlsanity.com/paper/2006.16241/) (2020)
- [Progressive Neural Networks](https://mlsanity.com/paper/1606.04671/) (2016)
- [Editing Models with Task Arithmetic](https://mlsanity.com/paper/2212.04089/) (2022)
- [Learning to Prompt for Continual Learning](https://mlsanity.com/paper/2112.08654/) (2021)
- [PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning](https://mlsanity.com/paper/1711.05769/) (2017)
- [TIES-Merging: Resolving Interference When Merging Models](https://mlsanity.com/paper/2306.01708/) (2023)
- [An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networks](https://mlsanity.com/paper/1312.6211/) (2013)
- [Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch](https://mlsanity.com/paper/2311.03099/) (2023)
- [DualPrompt: Complementary Prompting for Rehearsal-free Continual Learning](https://mlsanity.com/paper/2204.04799/) (2022)
- [CODA-Prompt: COntinual Decomposed Attention-based Prompting for Rehearsal-Free Continual Learning](https://mlsanity.com/paper/2211.13218/) (2022)
- [InfLoRA: Interference-Free Low-Rank Adaptation for Continual Learning](https://mlsanity.com/paper/2404.00228/) (2024)
- [SLCA: Slow Learner with Classifier Alignment for Continual Learning on a Pre-trained Model](https://mlsanity.com/paper/2303.05118/) (2023)
- [Class-Incremental Continual Learning into the eXtended DER-verse](https://mlsanity.com/paper/2201.00766/) (2022)
- [MagMax: Leveraging Model Merging for Seamless Continual Learning](https://mlsanity.com/paper/2407.06322/) (2024)
- [SD-LoRA: Scalable Decoupled Low-Rank Adaptation for Class Incremental Learning](https://mlsanity.com/paper/2501.13198/) (2025)
- [Self-Expansion of Pre-trained Models with Mixture of Adapters for Continual Learning](https://mlsanity.com/paper/2403.18886/) (2024)
- [Merging Models on the Fly Without Retraining: A Sequential Approach to Scalable Continual Model Merging](https://mlsanity.com/paper/2501.09522/) (2025)
- [Parameter-Efficient Continual Fine-Tuning: A Survey](https://mlsanity.com/paper/2504.13822/) (2025)

## Built on by (most cited first, 1 of 1)

- [A Compositional Paradigm for Foundation Models: Towards Smarter Robotic Agents](https://mlsanity.com/paper/2510.18608/) (2025)

## Abstract (arXiv)

The ability to learn continuously over time remains a major challenge for modern machine learning systems, even in the era of Foundation Models. While the rich representations learned by large pre-trained models can partially mitigate catastrophic forgetting, they still struggle to adapt efficiently to evolving data distributions. A key challenge remains, how to continually add new knowledge to a large pretrained model in a way that is scalable and computationally efficient over long task sequences. In this work, we introduce GLAM, a simple and effective framework for class-incremental continual learning based on LoRA adapters merging. For each task, GLAM trains a lightweight low-rank adapter with an importance scalar, incurring minimal computational overhead. Adapters are then pruned, rescaled, and sequentially grouped to enable structured knowledge reuse and limit parameter growth. At inference, all groups are combined into a single module, ensuring constant computational cost regardless of the number of tasks. We evaluate GLAM on vision benchmarks with sequences of up to 50 tasks, significantly extending beyond standard protocols. GLAM achieves the highest accuracy across the evaluated benchmarks. Compared with the baseline attaining the highest average accuracy across benchmarks, it uses 16--19% of the trainable parameters and reduces training time by approximately 63--74%, demonstrating efficient and scalable continual learning. Our source code is publicly available at https://github.com/atlas-luiss/GLAM.