Related papers: Randomized-MLP Regularization Improves Domain Adap…

Cross-modal contrastive learning in vision language pretraining (VLP) faces the challenge of (partial) false negatives. In this paper, we study this problem from the perspective of Mutual Information (MI) optimization. It is common sense…

Convolutional networks, transformers, hybrid models, and Mamba-based architectures have demonstrated strong performance across various medical image classification tasks. However, these methods were primarily designed to classify clean…

Understanding what features are encoded by learned directions in LLM activation space requires identifying inputs that strongly activate them. Feature visualization, which optimizes inputs to maximally activate a target direction, offers an…

In recent years, a variety of learned regularization frameworks for solving inverse problems in imaging have emerged. These offer flexible modeling together with mathematical insights. The proposed methods differ in their architectural…

Large Vision-Language Models (LVLMs) extend large language models with visual understanding, but remain vulnerable to hallucination, where outputs are fluent yet inconsistent with images. Recent studies link this issue to language bias-the…

Large-scale contrastive pre-training produces powerful Vision-and-Language Models (VLMs) capable of generating representations (embeddings) effective for a wide variety of visual and multimodal tasks. However, these pretrained embeddings…

Vision Transformers (ViTs) are essential as foundation backbones in establishing the visual comprehension capabilities of Multimodal Large Language Models (MLLMs). Although most ViTs achieve impressive performance through image-text…

Retinal vessel segmentation plays a key role in computer-aided screening, diagnosis, and treatment of various cardiovascular and ophthalmic diseases. Recently, deep learning-based retinal vessel segmentation algorithms have achieved…

Contrastive pretraining can substantially increase model generalisation and downstream performance. However, the quality of the learned representations is highly dependent on the data augmentation strategy applied to generate positive…

Pre-trained large vision-language models (VLMs) like CLIP demonstrate impressive generalization ability. Existing prompt-based and adapter-based works have made significant progress in fine-tuning VLMs but still face the challenges of…

Fine-grained supervision based on object annotations has been widely used for vision and language pre-training (VLP). However, in real-world application scenarios, aligned multi-modal data is usually in the image-caption format, which only…

While Multimodal Large Language Models (MLLMs) excel at vision-language tasks, the cost of their language-driven training on internal visual foundational competence remains unclear. In this paper, we conduct a detailed diagnostic analysis…

The success of deep neural networks is mostly due their ability to learn meaningful features from the data. Features learned in the hidden layers of deep neural networks trained in computer vision tasks have been shown to be similar to…

Fine-tuning contextualized representations learned by pre-trained language models remains a prevalent practice in NLP. However, fine-tuning can lead to representation degradation (also known as representation collapse), which may result in…

The integration of visual and textual data in Vision-Language Pre-training (VLP) models is crucial for enhancing vision-language understanding. However, the adversarial robustness of these models, especially in the alignment of image-text…

Existing deep neural networks, say for image classification, have been shown to be vulnerable to adversarial images that can cause a DNN misclassification, without any perceptible change to an image. In this work, we propose shock absorbing…

Inverse problems lie at the heart of modern imaging science, with broad applications in areas such as medical imaging, remote sensing, and microscopy. Recent years have witnessed a paradigm shift in solving imaging inverse problems, where…

Hallucinations in vision-language models (VLMs) hinder reliability and real-world applicability, usually stemming from distribution shifts between pretraining data and test samples. Existing solutions, such as retraining or fine-tuning on…

Deep learning-based drug response prediction (DRP) methods can accelerate the drug discovery process and reduce R\&D costs. Although the mainstream methods achieve high accuracy in predicting response regression values, the regression-aware…

Vision--language models (VLMs) are increasingly aligned via Group Relative Policy Optimization (GRPO)-style training. However, relying solely on terminal outcome rewards yields sparse credit assignment in multi-step reasoning, weakening the…