CORTEXA
← Browse
arxivcs.LG2026-07-20

Manifold-Constrained Hyper-Connections for Parameter-Efficient Finetuning

Valentijn Oldenburg, Floris de Kam, Bente Zuijdam, Lieve Eberson, Nicky van Zutphen, Stef de Wildt, Ivo Verhoeven

Most parameter-efficient finetuning (PEFT) methods adapt weights or activations, thus leaving one of the key Transformer components unchanged: residual connections. This paper investigates Manifold-Constrained Hyper-Connections (mHC), a generalisation of residual connections, as a novel PEFT approach, wrapping frozen OLMo-2 backbones with learned residual routing modules. We find that mHC can finetune frozen Transformers, but that its role differs fundamentally from the original pre-training setting: in finetuning, fixing the residual mixing matrix to identity often improves performance. As a standalone PEFT method, mHC does not consistently outperform LoRA. However, at matched trainable parameter budgets, mHC+LoRA combinations improve language-modelling loss and show task-dependent benchmark gains at both 1B and 7B scale. Overall, our results identify residual routing as a distinct and promising novel PEFT axis.

View free PDFSource page

Related papers

arxiveess.IVcs.CVcs.LG2026-07-31

MoPET: Parameter-Efficient Mixture-of-Experts for Unified Medical Image Classification

Sebastian Doerrich, Daniel Würtinger, Francesco Di Salvo, Shyam Nandan Rai, Christian Ledig

Adapting deep learning models to profound clinical heterogeneity typically relies on parameter-efficient fine-tuning (PEFT) to avoid the severe overfitting associated with full end-to-end network updates. Although PEFT successfully navigates limited data scenarios, it inherently…

View free PDFSource page
arxivcs.LG2026-07-23

How Many Bits Can an Adapter Write? Measuring the Capacity and Memorization of Parameter-Efficient Fine-Tuning

Kaizhen Tan, Heqing Du, Yang Feng

A LoRA adapter is a few megabytes that almost everyone treats as a skill rather than a record of the data behind it. We put that assumption on a scale. Extending compression-based memorization analysis to the frozen-base setting, we measure directly, in bits, how much a low-rank…

View free PDFSource page
arxivcs.LGcs.NI2026-07-23

Three-Pronged Spectral Control for Federated Parameter Efficient Fine Tuning

Shiva Raj Pokhrel, Dipsan Bhattarai, Anwar Walid

Federated parameter-efficient fine-tuning (PEFT) enables communication-efficient adaptation of large pretrained models on decentralized edge data, but it remains fragile under non-IID client heterogeneity. In low-rank adaptation (LoRA), different clients may learn locally useful…

View free PDFSource page
arxivcs.LG2026-07-31

The Parts Are Greater Than the Sum: Automated Task Sequencing for Efficient Training of Multi-Policy LLMs

Jiajia Tang, Sizhe Yuen, Francisco Gomez Medina, Yali Du, Adam Sobey

Parameter-Efficient Fine-Tuning (PEFT) commonly adapts large language models using a single shared Low-Rank Adapter (LoRA). This shared optimization space often suffers from interference when adapting heterogeneous task sequences, leading to poor transfer and catastrophic forgett…

View free PDFSource page
arxivstat.MLcs.LGeess.SP2026-07-24

Variational Low-rank Tensor Decomposition for Multisubject Spatiotemporal Data Analysis

Laura M. Montaldo, Ricardo A. Borsoi, Sebastian Miron, Tulay Adali

Modeling shared and subject-specific structure in multisubject spatiotemporal data remains challenging, particularly in neuroimaging, where both spatial and temporal patterns exhibit rich variability across subjects. Existing matrix and tensor decompositions provide interpretable…

View free PDFSource page