Related papers: ReCCur: A Recursive Corner-Case Curation Framework…

Recent large language models (LLMs) are rapidly extending their context windows, yet inference throughput lags due to increasing GPU memory and bandwidth demands. This is because the key-value (KV) cache, an intermediate structure storing…

We present a novel approach to adjust global image properties such as colour, saturation, and luminance using human-interpretable image enhancement curves, inspired by the Photoshop curves tool. Our method, dubbed neural CURve Layers…

Large Language Models have become the de facto approach to sequence-to-sequence text generation tasks, but for specialized tasks/domains, a pretrained LLM lacks specific capabilities to produce accurate or well-formatted responses.…

The use of Recurrent Neural Networks for video captioning has recently gained a lot of attention, since they can be used both to encode the input video and to generate the corresponding description. In this paper, we present a recurrent…

Deep convolutional neural networks (CNNs) learned on large-scale labeled samples have achieved remarkable progress in computer vision, such as image/video classification. The cheapest way to obtain a large body of labeled visual data is to…

Limited view tomographic reconstruction aims to reconstruct a tomographic image from a limited number of sinogram or projection views arising from sparse view or limited angle acquisitions that reduce radiation dose or shorten scanning…

The high capacity of deep learning models to learn complex patterns poses a significant challenge when confronted with label noise. The inability to differentiate clean and noisy labels ultimately results in poor generalization. We approach…

Existing benchmarks treat multi-turn conversation and reasoning-intensive retrieval separately, yet real-world information seeking requires both. To bridge this gap, we present a benchmark for reasoning-based conversational information…

We present recursive recurrent neural networks with attention modeling (R$^2$AM) for lexicon-free optical character recognition in natural scene images. The primary advantages of the proposed method are: (1) use of recursive convolutional…

Contrastively-trained Vision-Language Models (VLMs), such as CLIP, have become the standard approach for learning discriminative vision-language representations. However, these models often exhibit shallow language understanding,…

Learning with noisy labels has aroused much research interest since data annotations, especially for large-scale datasets, may be inevitably imperfect. Recent approaches resort to a semi-supervised learning problem by dividing training…

Over the long history of machine learning, which dates back several decades, recurrent neural networks (RNNs) have been used mainly for sequential data and time series and generally with 1D information. Even in some rare studies on 2D…

The data appetite for Vision-Language Models (VLMs) has continuously scaled up from the early millions to billions today, which faces an untenable trade-off with data quality and inevitably introduces Noisy Correspondence (NC) samples.…

Image recaptioning is widely used to generate training datasets with enhanced quality for various multimodal tasks. Existing recaptioning methods typically rely on powerful multimodal large language models (MLLMs) to enhance textual…

Benchmark datasets in computer vision often contain off-topic images, near duplicates, and label errors, leading to inaccurate estimates of model performance. In this paper, we revisit the task of data cleaning and formalize it as either a…

Deep learning has achieved excellent performance in various computer vision tasks, but requires a lot of training examples with clean labels. It is easy to collect a dataset with noisy labels, but such noise makes networks overfit seriously…

Given the vast amounts of video available online, and recent breakthroughs in object detection with static images, object detection in video offers a promising new frontier. However, motion blur and compression artifacts cause substantial…

Despite the success of large-scale pretrained Vision-Language Models (VLMs) especially CLIP in various open-vocabulary tasks, their application to semantic segmentation remains challenging, producing noisy segmentation maps with…

Cross-modal retrieval is gaining increasing efficacy and interest from the research community, thanks to large-scale training, novel architectural and learning designs, and its application in LLMs and multimodal LLMs. In this paper, we move…

Recurrent neural networks (RNNs) have shown the ability to improve scene parsing through capturing long-range dependencies among image units. In this paper, we propose dense RNNs for scene labeling by exploring various long-range semantic…