Related papers: Caduceus: Bi-Directional Equivariant Long-Range DN…

Sufficient cross-task interaction is crucial for success in multi-task dense prediction. However, sufficient interaction often results in high computational complexity, forcing existing methods to face the trade-off between interaction…

As genome sequencing is finding utility in a wide variety of domains beyond the confines of traditional medical settings, its computational pipeline faces two significant challenges. First, the creation of up to 0.5 GB of data per minute…

Deep learning models like Convolutional Neural Networks and transformers have shown impressive capabilities in speech verification, gaining considerable attention in the research community. However, CNN-based approaches struggle with…

Sequential modeling has demonstrated remarkable capabilities in offline reinforcement learning (RL), with Decision Transformer (DT) being one of the most notable representatives, achieving significant success. However, RL trajectories…

In this study, we focus on video captioning by fully open multimodal large language models (MLLMs). The comprehension of visual sequences is challenging because of their intricate temporal dependencies and substantial sequence length. The…

Biological sequences encode fundamental instructions for the building blocks of life, in the form of DNA, RNA, and proteins. Modeling these sequences is key to understand disease mechanisms and is an active research area in computational…

Accurate segmentation of the pancreas and its lesions in CT scans is crucial for the precise diagnosis and treatment of pancreatic cancer. However, it remains a highly challenging task due to several factors such as low tissue contrast with…

Inspired by the tremendous success of Large Language Models (LLMs), existing Radiology report generation methods attempt to leverage large models to achieve better performance. They usually adopt a Transformer to extract the visual features…

Cracks pose safety risks to infrastructure and cannot be overlooked. The prevailing structures in existing crack segmentation networks predominantly consist of CNNs or Transformers. However, CNNs exhibit a deficiency in global modeling…

We present a generative framework for inverse design of five-layer transmissive Huygens' metasurfaces (HMSs), addressing a longstanding challenge in achieving full-phase, high-efficiency unit cell designs with minimal full-wave simulations.…

Medical time series, such as electrocardiograms (ECG) and electroencephalograms (EEG), exhibit complex temporal dynamics and structured cross-channel dependencies, posing fundamental challenges for automated analysis. Conventional…

Multimodal embedding models, built upon causal Vision Language Models (VLMs), have shown promise in various tasks. However, current approaches face three key limitations: the use of causal attention in VLM backbones is suboptimal for…

Recent works have shown the remarkable superiority of transformer models in reinforcement learning (RL), where the decision-making problem is formulated as sequential generation. Transformer-based agents could emerge with self-improvement…

Precise alignment of multi-modal images with inherent feature discrepancies poses a pivotal challenge in deformable image registration. Traditional learning-based approaches often consider registration networks as black boxes without…

Substantial efforts have been applied to engineer CA with desired emergent properties, such as supporting gliders. Recent work in continuous CA has generated a wide variety of compelling bioreminiscent patterns, and the expansion of CA…

Fake artefacts for discriminating between bonafide and fake audio can exist in both short- and long-range segments. Therefore, combining local and global feature information can effectively discriminate between bonafide and fake audio. This…

In the past decade, Convolutional Neural Networks (CNNs) and Transformers have achieved wide applicaiton in semantic segmentation tasks. Although CNNs with Transformer models greatly improve performance, the global context modeling remains…

We introduce LocoMamba, a vision-driven cross-modal DRL framework built on selective state-space models, specifically leveraging Mamba, that achieves near-linear-time sequence modeling, effectively captures long-range dependencies, and…

Sequential recommendation methods are crucial in modern recommender systems for their remarkable capability to understand a user's changing interests based on past interactions. However, a significant challenge faced by current methods…

In a real-world traffic scenario, varying-scale objects are usually distributed in a cluttered background, which poses great challenges to accurate detection. Although current Mamba-based methods can efficiently model long-range…