arXiv Machine Learning August 4, 2026 By Srinivas Anumasa, Dianbo Liu

EulerLoRA: Rank-Driven Jump Dynamics for Calibrated Parameter-Efficient Fine-Tuning

Read the original on arXiv Machine Learning →

arXiv:2608. 01142v1 Announce Type: new Abstract: Low-Rank Adaptation (LoRA) enables parameter-efficient fine-tuning, but standard LoRA produces a single deterministic model and does not directly support predictive uncertainty estimation.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv AI

Jul 23

LAARA: Layer-Aware Adaptive Rank Allocation for Parameter-Efficient Fine-Tuning

arXiv:2607. 19391v1 Announce Type: cross Abstract: Low-Rank Adaptation is widely used for parameter-efficient fine-tuning, yet existing methods typically assign the same adapter rank to every transformer layer despite their heterogeneous adaptation requirements.

By Ashutosh Tripathi, Surya Deep Singh, Pranab Sahoo, Sriparna Saha

llms fine-tuning benchmarks

arXiv Machine Learning

Jun 2

OP-LoRA: The Blessing of Dimensionality

arXiv:2412. 10362v2 Announce Type: replace Abstract: Low-rank adapters (LoRA) enable finetuning of large models with only a small number of parameters.

By Piotr Teterwak, Kate Saenko, Bryan A. Plummer, Ser-Nam Lim

diffusion fine-tuning

arXiv Machine Learning

Aug 4

Breaking Diversity Collapse in Spiking Pseudo-Ensembles for Efficient OOD Detection in Remote Sensing

arXiv:2608. 01090v1 Announce Type: new Abstract: Spiking Neural Networks (SNNs) are attractive for resource-constrained remote-sensing systems, but reliable out-of-distribution (OOD) detection remains challenging.

By Srinivas Anumasa, Rushi Shah, Qiran Zou, Dianbo Liu

arXiv Machine Learning

Jul 28

Controllable Diversity in Normalization-Based Implicit Ensembles via Softmax-Temperature Modulation

arXiv:2607. 23860v1 Announce Type: new Abstract: Deep ensembles provide the most reliable uncertainty estimates in deep learning, but their cost grows linearly with the number of members.

By Mihai Suteu, Ovidiu Serban

llms fine-tuning

arXiv Machine Learning

Jul 27

IFCLoRA: Topology-Aware Rank Allocation for Parameter-Efficient Fine-Tuning

arXiv:2607. 22251v1 Announce Type: new Abstract: Low-Rank Adaptation (LoRA) is a widely used parameter-efficient fine-tuning method for large language models, but its performance depends strongly on how a fixed rank budget is distributed across Transformer modules.

By Wei Zhang, Xinwu Liu, Yihang Cheng

llms fine-tuning

arXiv AI

Jun 10

Fisher-Guided Progressive Parameter Selection for Adaptive Fine-Tuning

arXiv:2606. 10196v1 Announce Type: cross Abstract: Parameter-efficient fine-tuning (PEFT) aims to adapt pretrained models with a small trainable parameter subset, however, most existing methods choose this subset from fixed architectural heuristics rather than using dynamic, task-aware criteria.

By Ghodsiyeh Rostami, Po-Han Chen, Mahdi S. Hosseini

computer-vision fine-tuning

Related stories

LAARA: Layer-Aware Adaptive Rank Allocation for Parameter-Efficient Fine-Tuning

OP-LoRA: The Blessing of Dimensionality

Breaking Diversity Collapse in Spiking Pseudo-Ensembles for Efficient OOD Detection in Remote Sensing

Controllable Diversity in Normalization-Based Implicit Ensembles via Softmax-Temperature Modulation

IFCLoRA: Topology-Aware Rank Allocation for Parameter-Efficient Fine-Tuning

Fisher-Guided Progressive Parameter Selection for Adaptive Fine-Tuning