Related papers: SkillRater: Untangling Capabilities in Multimodal …

Text-to-image diffusion models, which are theoretically equivalent to score-based generative models, generate images through a multi-step denoising process guided by text embeddings extracted from pretrained vision-language models such as…

A general formulation of optimization problems in which various candidate solutions may use different feature-sets is presented, encompassing supervised classification, automated program learning and other cases. A novel characterization of…

Machine learning has been proven to be effective in various application areas, such as object and speech recognition on mobile systems. Since a critical key to machine learning success is the availability of large training data, many…

Self-supervised learning aims to extract meaningful features from unlabeled data for further downstream tasks. In this paper, we consider classification as a downstream task in phase 2 and develop rigorous theories to realize the factors…

The performance of vision-language models (VLMs), such as CLIP, in visual classification tasks, has been enhanced by leveraging semantic knowledge from large language models (LLMs), including GPT. Recent studies have shown that in zero-shot…

We develop a novel transfer learning framework to tackle the challenge of limited training data in image reconstruction problems. The proposed framework consists of two training steps, both of which are formed as bi-level optimizations. In…

StackOverflow has become an emerging resource for talent recognition in recent years. While users exploit technical language on StackOverflow, recruiters try to find the relevant candidates for jobs using their own terminology. This…

Multi-view clustering has attracted much attention thanks to the capacity of multi-source information integration. Although numerous advanced methods have been proposed in past decades, most of them generally overlook the significance of…

Deep Q-learning jointly learns representations and values within monolithic networks, promising beneficial co-adaptation between features and value estimates. Although this architecture has attained substantial success, the coupling between…

Despite extensive research spanning several decades, class imbalance is still considered a profound difficulty for both machine learning and deep learning models. While data oversampling is the foremost technique to address this issue,…

Large reasoning models such as DeepSeek-R1 and their distilled variants achieve strong performance on complex reasoning tasks. Yet, distilling these models often demands large-scale data for supervised fine-tuning (SFT), motivating the…

Selective classifiers improve model reliability by abstaining on inputs the model deems uncertain. However, few practical approaches achieve the gold-standard performance of a perfect-ordering oracle that accepts examples exactly in order…

The increasing availability of image-text pairs has largely fueled the rapid advancement in vision-language foundation models. However, the vast scale of these datasets inevitably introduces significant variability in data quality, which…

We introduce a novel approach for keypoint detection task that combines handcrafted and learned CNN filters within a shallow multi-scale architecture. Handcrafted filters provide anchor structures for learned filters, which localize, score…

Self-supervised representation learning methods often fail to learn subtle or complex features, which can be dominated by simpler patterns which are much easier to learn. This limitation is particularly problematic in applications to…

Text images contain both visual and linguistic information. However, existing pre-training techniques for text recognition mainly focus on either visual representation learning or linguistic knowledge learning. In this paper, we propose a…

Machine learning classifiers often produce probabilistic predictions that are critical for accurate and interpretable decision-making in various domains. The quality of these predictions is generally evaluated with proper losses, such as…

Image captioning models are typically trained by treating all samples equally, neglecting to account for mismatched or otherwise difficult data points. In contrast, recent work has shown the effectiveness of training models by scheduling…

Supervised and unsupervised homography estimation methods depend on image pairs tailored to specific modalities to achieve high accuracy. However, their performance deteriorates substantially when applied to unseen modalities. To address…

Deep image compression systems mainly contain four components: encoder, quantizer, entropy model, and decoder. To optimize these four components, a joint rate-distortion framework was proposed, and many deep neural network-based methods…