Related papers: Generalization from Low- to Moderate-Resolution Sp…

The reliable application of deep learning models to software engineering tasks hinges on high-quality training data. Yet, large-scale repositories inevitably introduce noisy or mislabeled examples that degrade both accuracy and robustness.…

In the era of exploding survey volumes, traditional methods of spectroscopic analysis are being pushed to their limits. In response, we develop deep-REMAP, a novel deep learning framework that utilizes a regularized, multi-task approach to…

Fine-tuning pre-trained language models such as BERT has become a common practice dominating leaderboards across various NLP tasks. Despite its recent success and wide adoption, this process is unstable when there are only a small number of…

Purpose: This work proposes a novel self-supervised noise-adaptive image denoising framework, called Repetition to Repetition (Rep2Rep) learning, for low-field (<1T) MRI applications. Methods: Rep2Rep learning extends the Noise2Noise…

Large language models (LLMs) have achieved remarkable progress, with post-training playing a crucial role in enhancing their reasoning capabilities. Among post-training paradigms, supervised fine-tuning (SFT) is widely used: it leverages…

Neural Radiance Fields (NeRF) are an advanced technology that creates highly realistic images by learning about scenes through a neural network model. However, NeRF often encounters issues when there are not enough images to work with,…

Parameter-Efficient transfer learning with Adapters have been studied in Natural Language Processing (NLP) as an alternative to full fine-tuning. Adapters are memory-efficient and scale well with downstream tasks by training small…

Fine-tuning is becoming widely used for leveraging the power of pre-trained foundation models in new downstream tasks. While there are many successes of fine-tuning on various tasks, recent studies have observed challenges in the…

The Large Sky Area Multi-Object Fiber Spectroscopic Telescope (LAMOST) has acquired tens of millions of low-resolution spectra of stars. This paper investigated the parameter estimation problem for these spectra. To this end, we proposed a…

In this paper we present a generalized Deep Learning-based approach for solving ill-posed large-scale inverse problems occuring in medical image reconstruction. Recently, Deep Learning methods using iterative neural networks and cascaded…

Efficiently post-training large language models remains a challenging task due to the vast computational resources required. We present Spectrum, a method that accelerates LLM training by selectively targeting layer modules based on their…

Large pretrained language models (PLMs) are often domain- or task-adapted via fine-tuning or prompting. Finetuning requires modifying all of the parameters and having enough data to avoid overfitting while prompting requires no training and…

Vision-Language Pretrained (VLP) models have achieved impressive performance on multimodal tasks, including text-image retrieval, based on dense representations. Meanwhile, Learned Sparse Retrieval (LSR) has gained traction in text-only…

Quasar photometric redshifts are essential for studying cosmology and large-scale structures. However, their complex spectral energy distributions cause significant redshift-color degeneracy, limiting the accuracy of traditional methods. To…

City models and height maps of urban areas serve as a valuable data source for numerous applications, such as disaster management or city planning. While this information is not globally available, it can be substituted by digital surface…

Recent advances in neural rendering have achieved impressive results on photorealistic shading and relighting, by using a multilayer perceptron (MLP) as a regression model to learn the rendering equation from a real-world dataset. Such…

In this work we study generalization of neural networks in gradient-based meta-learning by analyzing various properties of the objective landscapes. We experimentally demonstrate that as meta-training progresses, the meta-test solutions,…

Deep learning has shown great promise in diverse areas of computer vision, such as image classification, object detection and semantic segmentation, among many others. However, as it has been repeatedly demonstrated, deep learning methods…

Head MRI pre-processing involves converting raw images to an intensity-normalized, skull-stripped brain in a standard coordinate space. In this paper, we propose an end-to-end weakly supervised learning approach, called Neural…

We propose a self-supervised machine learning (SSML) framework for multi-fidelity learning and extended predictive soil spectroscopy based on latent space embeddings. A self-supervised representation was pretrained with the large MIR…