CORTEXA
← Browse
arxivcs.LG2026-06-26

When One Adapter Speaks for Many: Discovering Low-Rank Redundancy in Continual Fine-Tuning

Tanguy Dieudonné, Giulia Lanzillotta, Enis Simsar, Louis Barinka, Thomas Hofmann

Low-Rank Adaptation (LoRA) has become the standard tool for parameter-efficient fine-tuning of large pretrained models. When applied sequentially across tasks in Continual Learning (CL), the standard assumption is that each new task requires a dedicated low-rank adapter. In this work, we challenge this assumption empirically and structurally. We show that task-specific LoRA adapters in CL exhibit significant low-rank redundancy: the subspaces spanned by adapters trained on different tasks substantially overlap, and in many cases earlier adapters can faithfully represent later tasks. Building on this observation, we propose LiteLoRA, a plug-and-play gating mechanism that learns at train time whether to recruit a new adapter or reuse existing low-rank representations. Our method reduces the number of active adapters by 20-70% while matching or exceeding state-of-the-art performance on standard CL benchmarks, revealing that structural redundancy is pervasive and that selective learning is sufficient to achieve stability without sacrificing plasticity.

View free PDFSource page

Related papers

arxivcs.LG2026-07-18

MultiLoReFT: Decoupling Shared and Modality-Specific Subspaces in Multimodal Learning via Low-Rank Representation Fine-Tuning

Sana Tonekaboni, Viktoria Schuster, Caroline Uhler

Real-world perception and decision making are inherently multimodal, integrating complementary signals across modalities. However, training multimodal models faces two main obstacles. First, collecting large-scale, well-aligned paired multimodal datasets is often impractical, mak…

View free PDFSource page
arxivcs.ARcs.ETcs.LG2026-07-19

ThRIve: Thermally Robust CNN Inference via Low-Rank Adaptation in Heterogeneous PIM Architectures

Vibhanshu Sharma, Pratyush Dhingra, Janardhan Rao Doppa, Partha Pratim Pande

Processing-In-Memory (PIM) has emerged as a promising technology for accelerating machine learning (ML) workloads. Specifically, non-volatile memory-based PIM architectures have enabled effective ML acceleration due to their ability to perform energy-efficient matrix-vector multi…

View free PDFSource page
arxivcs.LGcs.AI2026-07-20

Federated Lightweight Fine-Tuning

Radhakrishna Achanta, Will Reed

Federated fine-tuning is bottlenecked by communication: FedAvg and pseudo-gradient schemes transmit a payload that scales with the model, and gradient compression shrinks it by only a constant factor. We take a different lever. Mapping networks generate a network's weights from a…

View free PDFSource page
arxivcs.CRcs.AIcs.CYcs.LG2026-07-20

Adversarial Robustness of Phishing Email Detection: A Comparative Study of TF-IDF + Logistic Regression and Fine-Tuned DistilBERT

Tanveer Ahmed, Seyedali Pourmoafil

Phishing emails remain one of the most persistent cybersecurity threats, and machine-learning classifiers are widely used to detect them. Most reported detection accuracies, however, are measured on clean, in-distribution test data rather than on emails deliberately altered to ev…

View free PDFSource page
arxivcs.DCcs.LG2026-07-20

AutoEncoder-Compressed Parallel Split Learning for Pre-trained Model Fine-Tuning

Bas Meuwissen, Vasileios Tsouvalas, Nirvana Meratnia

Distributed Fine-Tuning (DFT) of large-scale Foundation Models (FMs) on resource-constrained edge devices is limited by local compute constraints and communication overhead. Parallel Split Learning (PSL) reduces client-side computation by keeping few model layers on each client a…

View free PDFSource page
arxivcs.LG2026-07-16

A Continuous-Time Reinforcement Learning Framework for Fine-Tuning Discrete Diffusion Models

Zikun Zhang, Jiayuan Sheng, David D. Yao, Wenpin Tang

We formulate reinforcement learning (RL) in continuous time with discrete state spaces and possibly arbitrary action spaces via a stochastic control approach, where the state dynamics are modeled as a controlled continuous-time Markov chain (CTMC). We consider policy optimization…

View free PDFSource page