Related papers: Accurate selfcorrection of errors in long reads us…
While Large Language Models (LLMs) have demonstrated remarkable capabilities, their reliability is significantly compromised by hallucinations. Existing intrinsic self-correction methods attempt to address this, but often fail due to…
Large Language Models (LLMs) have recently demonstrated remarkable performance in various Natural Language Processing (NLP) applications, such as sentiment analysis, content generation, and personalized recommendations. Despite their…
Unsupervised automatic readability assessment (ARA) methods have important practical and research applications (e.g., ensuring medical or educational materials are suitable for their target audiences). In this paper, we propose a new…
Low-Rank Adaptation (LoRA) has become a standard technique for parameter-efficient fine-tuning of large language models, enabling large libraries of LoRAs, each for a specific task or domain. Efficiently selecting the correct LoRA adapter…
Parameter-efficient fine-tuning (PEFT) is essential for adapting large language models (LLMs), with low-rank adaptation (LoRA) being the most popular approach. However, LoRA suffers from slow convergence, and some recent LoRA variants, such…
Despite the success and popularity of oligonucleotide arrays as a high-throughput technique for measuring mRNA expression levels, quantitative calibration studies have until now been limited. The main reason is that suitable data was not…
The focus of our paper is the identification and correction of non-word errors in OCR text. Such errors may be the result of incorrect insertion, deletion, or substitution of a character, or the transposition of two adjacent characters…
Low-rank adaptation (LoRA) is a parameter-efficient fine-tuning (PEFT) method widely used in large language models (LLMs). It approximates the update of a pretrained weight matrix $W\in\mathbb{R}^{m\times n}$ by the product of two low-rank…
Efficient long-sequence generation is a critical challenge for Large Language Models. While recent sparse decoding methods improve efficiency, they suffer from KV cache misalignment, where approximation errors accumulate and degrade…
Large-scale biobanks are being collected around the world in efforts to better understand human health and risk factors for disease. They often survey hundreds of thousands of individuals, combining questionnaires with clinical, genetic,…
This study examines whether Low-Rank Adaptation (LoRA) fine-tuned Large Language Models (LLMs) can approximate the performance of fully fine-tuned models in generating human-interpretable decisions and explanations for malware…
O1/R1 style large reasoning models (LRMs) signal a substantial leap forward over conventional instruction-following LLMs. By applying test-time scaling to generate extended reasoning paths, they establish many SOTAs across a wide range of…
We proposed a novel dense line spectrum super-resolution algorithm, the DMRA, that leverages dynamical multi-resolution of atoms technique to address the limitation of traditional compressed sensing methods when handling dense point-source…
We present LongLoRA, an efficient fine-tuning approach that extends the context sizes of pre-trained large language models (LLMs), with limited computation cost. Typically, training LLMs with long context sizes is computationally expensive,…
Fine-tuning has become a popular approach to adapting large foundational models to specific tasks. As the size of models and datasets grows, parameter-efficient fine-tuning techniques are increasingly important. One of the most widely used…
DNA sequencing is the physical/biochemical process of identifying the location of the four bases (Adenine, Guanine, Cytosine, Thymine) in a DNA strand. As semiconductor technology revolutionized computing, modern DNA sequencing technology…
Empirical studies suggest that machine learning models trained with empirical risk minimization (ERM) often rely on attributes that may be spuriously correlated with the class labels. Such models typically lead to poor performance during…
Automatic program repair (APR) techniques have the potential to reduce manual efforts in uncovering and repairing program defects during the code review (CR) process. However, the limited accuracy and considerable time costs associated with…
Deep learning-based watermarking has emerged as a promising solution for robust image authentication and protection. However, existing models are limited by low embedding capacity and vulnerability to bit-level errors, making them…
The main challenge in de novo assembly of NGS data is certainly to deal with repeats that are longer than the reads. This is particularly true for RNA- seq data, since coverage information cannot be used to flag repeated sequences, of which…