Low Rank Adaptation
PulseAugur coverage of Low Rank Adaptation — every cluster mentioning Low Rank Adaptation across labs, papers, and developer communities, ranked by signal.
9 day(s) with sentiment data
-
PEFT techniques enhance SAM for liver tumor segmentation
Researchers have explored parameter-efficient fine-tuning (PEFT) techniques for segmenting liver tumors in CT scans using the Segment Anything Model (SAM). The study compared several PEFT methods, including LoRA, QLoRA,…
-
New DROS method enhances foundation model adaptation for remote sensing
Researchers have developed a new method called Domain-aware Relaxed Orthogonal Subspace adaptation (DROS) to improve the efficiency of fine-tuning large foundation models for remote sensing tasks. This approach addresse…
-
New benchmark and survey advance remote sensing image segmentation
Researchers have introduced VPRef, a new benchmark for referring remote sensing image segmentation designed to address performance degradation caused by visual and textual domain drift. This benchmark, featuring over 46…
-
LoRA-RC: Low-Rank Adaptation for Stable Reservoir Computing
Researchers have introduced LoRA-RC, a novel method for adapting reservoir computing systems using low-rank corrections. This approach addresses the degradation of static reservoirs due to system drift by enabling onlin…
-
New framework proves trainability of attention and LoRA models
Researchers have established a rigorous framework for the stochastic training of multi-headed attention mechanisms and Low Rank Adaptation (LoRA) in machine learning models. Their work proves that for certain regulariza…
-
LLM simulates user knowledge using search history data
A new study published on arXiv explores the potential of using individual text corpora, such as search histories, to simulate user-specific knowledge. Researchers found that the Qwen3-1.7B large language model, when fin…
-
AI model adapts to Alzheimer's MRI tasks with minimal retraining
Researchers have developed a generalizable feature extractor for Alzheimer's disease-related brain MRI tasks, demonstrating the effectiveness of transfer learning in neuroimaging. By adapting a pre-trained 3D convolutio…
-
New Vision-Language Model Enhances Lunar Crater Detection
Researchers have developed a new vision-language model for accurate crater detection on the Moon, utilizing the OWLv2 model based on a Vision Transformer. This approach was fine-tuned using a dataset from the IMPACT pro…
-
SAM3-LoRA adapts foundation model for defect segmentation using parameter-efficient technique
Researchers have developed SAM3-LoRA, a parameter-efficient adaptation technique for the SAM3 foundation model, specifically for multi-class structural defect segmentation. This method utilizes Low-Rank Adaptation (LoRA…
-
New research reveals sparse and structured nature of effective LoRA writes
Researchers have found that effective Low-Rank Adaptation (LoRA) updates in language models are surprisingly sparse and structured, rather than uniformly distributed across parameters. Using a technique called Learned-B…
-
New LUViT approach bridges LLM and Vision Transformer modality gap
Researchers have developed Language-Unlocked Vision Transformers (LUViT), a novel approach to integrate Large Language Models (LLMs) with Vision Transformers (ViTs) for visual tasks. LUViT addresses the modality mismatc…
-
LLMs adapted for Swedish journalism using continued pre-training
Researchers have adapted large language models (LLMs) for Swedish journalism through continued pre-training on a curated dataset of millions of news articles. This adaptation process showed improvements in generation qu…
-
LLMs adapted for Swedish journalism using continued pre-training
Researchers explored adapting large language models for Swedish journalism through continued pre-training. They curated a dataset of millions of news articles and developed a domain-specific benchmark to evaluate perfor…
-
New methods enhance LoRA efficiency and stability for model adaptation
Researchers have developed two new methods to improve the efficiency and stability of Low-Rank Adaptation (LoRA) techniques used in parameter-efficient model adaptation. Normalized Low-Rank Adaptation (NoRA) normalizes …
-
MixLoRA-DSI offers efficient generative retrieval model updates
Researchers have developed MixLoRA-DSI, a new framework designed to efficiently update generative retrieval models with new documents without requiring full retraining. This method employs an expandable mixture of Low-R…
-
AI University framework enhances engineering education with LLM learning assistants
Researchers have developed "AI University" (AI-U), a framework designed to create AI-powered learning assistants tailored for engineering courses. This system utilizes a fine-tuned large language model (LLM) combined wi…
-
New FSCIL framework enhances malware detection with LoRA and SSL
Researchers have developed a novel framework for Few-Shot Class-Incremental Learning (FSCIL) specifically designed for malicious packet recognition. This approach utilizes a Self-Supervised Learning backbone, pre-traine…
-
PEFT boosts LLM hate speech detection in Roman Urdu to over 93% F1
A new research paper explores the effectiveness of Parameter-Efficient Fine-Tuning (PEFT) methods, specifically Low-Rank Adaptation (LoRA), for hate speech detection in Roman Urdu. The study found that while zero-shot i…
-
New methods improve AI-generated image detection generalization
Researchers are developing new methods to detect AI-generated images, addressing the challenge of generalization across different generation techniques and datasets. One approach, "Prior-Conditioned Gaussian Discriminan…
-
New SCLoRA Method Enhances Model Adaptation and Reduces Forgetting
Researchers have introduced SCLoRA, a novel method for low-rank adaptation (LoRA) in machine learning models. This technique leverages singular value decomposition (SVD) to analyze pre-trained weights, identifying that …