Related papers: Modeling variable guide efficiency in pooled CRISP…

Data augmentation is crucial for pixel-wise annotation tasks like semantic segmentation, where labeling requires significant effort and intensive labor. Traditional methods, involving simple transformations such as rotations and flips,…

Prompt-guided generative AI models have rapidly expanded across vision and language domains, producing realistic and diverse outputs from textual inputs. The growing variety of such models, trained with different data and architectures,…

Deep learning techniques have dominated the literature on aspect-based sentiment analysis (ABSA), achieving state-of-the-art performance. However, deep models generally suffer from spurious correlations between input features and output…

We focus on building robustness in the convolutions of neural visual classifiers, especially against natural perturbations like elastic deformations, occlusions and Gaussian noise. Existing CNNs show outstanding performance on clean images,…

Deep Learning based methods have emerged as the indisputable leaders for virtually all image restoration tasks. Especially in the domain of microscopy images, various content-aware image restoration (CARE) approaches are now used to improve…

Prompt learning is a parameter-efficient approach for vision-language models, yet its robustness under label noise is less investigated. Visual content contains richer and more reliable semantic information, which remains more robust under…

Language models can use verifiable rewards to improve at a wide variety of reasoning tasks. However, both parametric (e.g. RLVR) and non-parametric (e.g. prompt optimization) approaches to doing so typically require hundreds of training…

Genome editing allows scientists to change an organism's DNA. One promising genome editing protocol, already validated in living organisms, is based on clustered regularly interspaced short palindromic repeats (CRISPR)/Cas protein-nucleic…

Contrastive Language-Image Pre-training (CLIP) has significantly improved performance in various vision-language tasks by expanding the dataset with image-text pairs obtained from websites. This paper further explores CLIP from the…

Instrumental variable methods are among the most commonly used causal inference approaches to deal with unmeasured confounders in observational studies. The presence of invalid instruments is the primary concern for practical applications,…

Biological signals of interest in high-dimensional data are often masked by dominant variation shared across conditions. This variation, arising from baseline biological structure or technical effects, can prevent standard dimensionality…

Recent generative models can synthesize "views" of artificial images that mimic real-world variations, such as changes in color or pose, simply by learning from unlabeled image collections. Here, we investigate whether such views can be…

In this paper we propose a novel modification of Contrastive Language-Image Pre-Training (CLIP) guidance for the task of unsupervised backlit image enhancement. Our work builds on the state-of-the-art CLIP-LIT approach, which learns a…

Stochastic Natural Gradient Variational Inference (NGVI) is a widely used method for approximating posterior distribution in probabilistic models. Despite its empirical success and foundational role in variational inference, its theoretical…

Vision-language foundation models have exhibited remarkable success across a multitude of downstream tasks due to their scalability on extensive image-text paired data. However, these models also display significant limitations when applied…

Virtual cell (VC) models aim to predict cellular responses to any perturbations in silico and have emerged as a promising approach for drug discovery and precision medicine. Yet, a clear gap still remains: while models routinely reported…

Visual prompting (VP) has emerged as a promising parameter-efficient fine-tuning approach for adapting pre-trained vision models to downstream tasks without modifying model parameters. Despite offering advantages like negligible…

This paper presents a simple and effective visual prompting method for adapting pre-trained models to downstream recognition tasks. Our method includes two key designs. First, rather than directly adding together the prompt and the image,…

This paper presents a novel approach for deep visualization via a generative network, offering an improvement over existing methods. Our model simplifies the architecture by reducing the number of networks used, requiring only a generator…

Blind deconvolution is an ill-posed problem arising in various fields ranging from microscopy to astronomy. The ill-posed nature of the problem requires adequate priors to arrive to a desirable solution. Recently, it has been shown that…