CSULoRA is a post-hoc method that corrects trained LoRA adapters by estimating a safety-aligned subspace and solving a penalized minimum-change problem to attenuate unsafe update directions while pres…

This paper investigates the application of Parameter-Efficient Fine-Tuning (PEFT) methods, specifically adapters and LoRA, to large pretrained models for instance segmentation, demonstrating that thes…

This paper derives a method to predict and mitigate intruder dimensions caused by LoRA fine-tuning in deep learning models, improving performance and reducing forgetting.

The paper introduces NaRA, a noise-aware LoRA technique that dynamically adapts fine-tuning parameters based on the noise level during diffusion, significantly improving the performance of Diffusion L…

This paper provides a theoretical explanation for why low-rank adaptation (LoRA) is effective in fine-tuning large pretrained models.

The paper proposes a lightweight, self-adaptive framework using LoRA to efficiently extract and aggregate radio frequency fingerprints for robust open-set authentication in dynamic wireless environmen…

The paper demonstrates that Low-Rank Adaptation (LoRA) is an effective and superior method for adapting large, pretrained Transformer surrogates for automotive aerodynamics to new vehicle families usi…

The paper proposes DP-SelFT, a novel framework for differentially private selective fine-tuning that significantly improves the privacy-utility trade-off for LLMs by intelligently selecting robust par…

The paper investigates whether using fine-grained, tensorized adapters (CP components) instead of standard LoRA ranks improves the accuracy-budget trade-off in PEFT, finding that while they fill budge…

The paper introduces FoLoRA, a novel optimization framework that uses a generalized Rayleigh quotient to achieve a superior balance between adapting foundation models to specific tasks and preserving…

The paper proposes oracle-guided fine-tuning to improve post-editing of ASR transcripts by using curated pools of corrections, regularizers, and hard negatives.

LayerRoute introduces a lightweight, input-conditioned adapter that selectively skips transformer blocks in agentic language models, achieving significant FLOPs reduction while improving performance.

This paper introduces READ, a method to combine multiple independently trained adapters into a single model without interference or retraining.

The paper quantifies the exact parametric memory capacity of LLMs using LoRA and proposes a new optimization strategy, MemFT, to enhance memory fidelity.

TailLoR is a new parameter-efficient finetuning method that uses the singular bases of pre-trained weights to learn low-rank updates, specifically penalizing updates along dominant directions to impro…

The paper proposes a novel safety fine-tuning method that uses the target model's own rollouts to identify and train on the hardest prompts, significantly reducing jailbreak success rates while mainta…