Related papers: CURE: Curriculum-guided Multi-task Training for Re…
Curriculum learning has emerged as a promising approach for training complex robotics tasks, yet current applications predominantly rely on manually designed curricula, which demand significant engineering effort and can suffer from…
Large language models (LLMs) often solve challenging math exercises yet fail to apply the concept right when the problem requires genuine understanding. Popular Reinforcement Learning with Verifiable Rewards (RLVR) pipelines reinforce final…
Quantifying uncertainty of predictions has been identified as one way to develop more trustworthy artificial intelligence (AI) models beyond conventional reporting of performance metrics. When considering their role in a clinical decision…
Robots are increasingly operating in open-world environments where safe behavior depends on context: the same hallway may require different navigation strategies when crowded versus empty, or during an emergency versus normal operations.…
Clinicians usually combine information from multiple sources to achieve the most accurate diagnosis, and this has sparked increasing interest in leveraging multimodal deep learning for diagnosis. However, in real clinical scenarios, due to…
Reward models (RMs) are fundamental to aligning Large Language Models (LLMs) via human feedback, yet they often suffer from reward hacking. They tend to latch on to superficial or spurious attributes, such as response length or formatting,…
Establishing reliable image correspondences is essential for many robotic vision problems. However, existing methods often struggle in challenging scenarios with large viewpoint changes or textureless regions, where incorrect cor-…
Radiology report generation is critical for efficiency but current models lack the structured reasoning of experts, hindering clinical trust and explainability by failing to link visual findings to precise anatomical locations. This paper…
Automatic radiology report generation has been an attracting research problem towards computer-aided diagnosis to alleviate the workload of doctors in recent years. Deep learning techniques for natural image captioning are successfully…
Generating clinical reports from raw recordings such as X-rays and electroencephalogram (EEG) is an essential and routine task for doctors. However, it is often time-consuming to write accurate and detailed reports. Most existing methods…
Course-based undergraduate research experiences (CUREs) increase students' access to research. This lesson plan describes an interdisciplinary CURE developed to be able to involve over 60 students per semester in original research using…
Causal Representation Learning (CRL) aims to uncover the data-generating process and identify the underlying causal variables and relations, whose evaluation remains inherently challenging due to the requirement of known ground-truth causal…
Identifying high-quality and easily accessible annotated samples poses a notable challenge in medical image analysis. Transfer learning techniques, leveraging pre-training data, offer a flexible solution to this issue. However, the impact…
Machine learning models for graphs in real-world applications are prone to two primary types of uncertainty: (1) those that arise from incomplete and noisy data and (2) those that arise from uncertainty of the model in its output. These…
Face manipulation techniques develop rapidly and arouse widespread public concerns. Despite that vanilla convolutional neural networks achieve acceptable performance, they suffer from the overfitting issue. To relieve this issue, there is a…
While large-scale language models (LLMs) have demonstrated remarkable capabilities in specific natural language processing (NLP) tasks, they may still lack proficiency compared to specialized models in certain domains, such as grammatical…
Cardiac magnetic resonance imaging (CMR), considered the gold standard for noninvasive cardiac assessment, is a diverse and complex modality requiring a wide variety of image processing tasks for comprehensive assessment of cardiac…
Medical image grounding aims to align natural language phrases with specific regions in medical images, serving as a foundational task for intelligent diagnosis, visual question answering (VQA), and automated report generation (MRG).…
Automatic radiology report generation is critical in clinics which can relieve experienced radiologists from the heavy workload and remind inexperienced radiologists of misdiagnosis or missed diagnose. Existing approaches mainly formulate…
Computed tomography (CT) report generation is crucial to assist radiologists in interpreting CT volumes, which can be time-consuming and labor-intensive. Existing methods primarily only consider the global features of the entire volume,…