相关论文: Temporal Inversion for Learning Interval Change in…

In the field of Blind Image Quality Assessment (BIQA), accurately predicting the perceptual quality of authentically distorted images remains highly challenging due to the diverse and complex distortions present in natural environments.…

Vision-language-action (VLA) models trained on large-scale internet data and robot demonstrations have the potential to serve as generalist robot policies. However, despite their large-scale training, VLAs are often brittle to…

Predicting the risk of developing breast cancer is an important clinical tool to guide early intervention and tailoring personalized screening strategies. Early risk models have limited performance and recently machine learning-based…

Popular representation learning methods encourage feature invariance under transformations applied at the input. However, in 3D perception tasks like object localization and segmentation, outputs are naturally equivariant to some…

Artificial intelligence (AI) is disrupting the medical field as advances in modern technology allow common household computers to learn anatomical and pathological features that distinguish between healthy and disease with the accuracy of…

Vision-Language-Action models have recently emerged as a powerful paradigm for general-purpose robot learning, enabling agents to map visual observations and natural-language instructions into executable robotic actions. Though popular,…

Most of current anomaly detection models assume that the normal pattern remains same all the time. However, the normal patterns of Web services change dramatically and frequently. The model trained on old-distribution data is outdated after…

Long-range temporal alignment is critical yet challenging for video restoration tasks. Recently, some works attempt to divide the long-range alignment into several sub-alignments and handle them progressively. Although this operation is…

While the design of blind image quality assessment (IQA) algorithms has improved significantly, the distribution shift between the training and testing scenarios often leads to a poor performance of these methods at inference time. This…

An important component of human analysis of medical images and their context is the ability to relate newly seen things to related instances in our memory. In this paper we mimic this ability by using multi-modal retrieval augmentation and…

Multimodal Large Language Models (MLLMs) have achieved significant advancements in tasks like Visual Question Answering (VQA) by leveraging foundational Large Language Models (LLMs). However, their abilities in specific areas such as visual…

Leveraging temporal information has been regarded as essential for developing video understanding models. However, how to properly incorporate temporal information into the recent successful instance discrimination based contrastive…

Recently, vision model pre-training has evolved from relying on manually annotated datasets to leveraging large-scale, web-crawled image-text data. Despite these advances, there is no pre-training method that effectively exploits the…

Despite advances in Vision-Language-Action (VLA) models, robotic manipulation struggles with fine-grained tasks because current models lack mechanisms for active visual attention allocation. Human gaze naturally encodes intent, planning,…

Although LLMs have demonstrated remarkable capabilities in processing and generating textual data, their pre-trained vocabularies are ill-suited for capturing the nuanced temporal dynamics and patterns inherent in time series. The discrete,…

In sequential recommendation (SR), neural models have been actively explored due to their remarkable performance, but they suffer from inefficiency inherent to their complexity. On the other hand, linear SR models exhibit high efficiency…

Many robotic manipulation tasks require sensing and responding to force signals such as torque to assess whether the task has been successfully completed and to enable closed-loop control. However, current Vision-Language-Action (VLA)…

Radiology is essential to modern healthcare, yet rising demand and staffing shortages continue to pose major challenges. Recent advances in artificial intelligence have the potential to support radiologists and help address these…

Episodic tasks in Reinforcement Learning (RL) often pose challenges due to sparse reward signals and high-dimensional state spaces, which hinder efficient learning. Additionally, these tasks often feature hidden "trap states" --…

Chest X-ray radiographs (CXRs) play a pivotal role in diagnosing and monitoring cardiopulmonary diseases. However, lung opacities in CXRs frequently obscure anatomical structures, impeding clear identification of lung borders and…