Related papers: TacMamba: A Tactile History Compression Adapter Br…

In the realm of computer graphics, the ability to learn continuously from non-stationary data streams while adapting to new visual patterns and mitigating catastrophic forgetting is of paramount importance. Existing approaches often…

Applying pre-trained models to assist point cloud understanding has recently become a mainstream paradigm in 3D perception. However, existing application strategies are straightforward, utilizing only the final output of the pre-trained…

The Transformer architecture is widely deployed in many popular and impactful Large Language Models. At its core is the attention mechanism for calculating correlations between pairs of tokens. Performing an attention computation takes…

Accurate Autism Spectrum Disorder (ASD) diagnosis is vital for early intervention. This study presents a hybrid deep learning framework combining Vision Transformers (ViT) and Vision Mamba to detect ASD using eye-tracking data. The model…

MambaVoiceCloning (MVC) asks whether the conditioning path of diffusion-based TTS can be made fully SSM-only at inference, removing all attention and explicit RNN-style recurrence layers across text, rhythm, and prosody, while preserving or…

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.…

Recently, the state space model (SSM) represented by Mamba has shown remarkable performance in long-term sequence modeling tasks, including speech enhancement. However, due to substantial differences in sub-band features, applying the same…

Transformer-based segmentation methods face the challenge of efficient inference when dealing with high-resolution images. Recently, several linear attention architectures, such as Mamba and RWKV, have attracted much attention as they can…

Accurate 3D medical image segmentation requires a delicate balance between fine-grained local details and global contextual understanding. While spatial-domain models often struggle with long-range dependencies, existing frequency-based…

Foundation models learn transferable representations, motivating growing interest in their application to wireless systems. Existing wireless foundation models are predominantly based on transformer architectures, whose quadratic…

Time series prediction, a crucial task across various domains, faces significant challenges due to the inherent complexities of time series data, including non-stationarity, multi-scale periodicity, and transient dynamics, particularly when…

Efficient long-context language modeling remains a significant challenge in Natural Language Processing (NLP). While Transformers dominate language tasks, they struggle with long sequences due to quadratic computational complexity in…

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…

Enhancing and preserving the readability of document images, particularly historical ones, is crucial for effective document image analysis. Numerous models have been proposed for this task, including convolutional-based, transformer-based,…

In electrical equipment, even minor contact issues can lead to arc faults. Traditional methods often struggle to balance the accuracy and rapid response required for effective arc fault detection. To address this challenge, we introduce…

Video understanding requires the extraction of rich spatio-temporal representations, which transformer models achieve through self-attention. Unfortunately, self-attention poses a computational burden. In NLP, Mamba has surfaced as an…

Human motion understanding is a fundamental task with diverse practical applications, facilitated by the availability of large-scale motion capture datasets. Recent studies focus on text-motion tasks, such as text-based motion generation,…

Transformer-based methods for 3D human pose estimation face significant computational challenges due to the quadratic growth of self-attention mechanism complexity with sequence length. Recently, the Mamba model has substantially reduced…

Dexterous manipulation requires precise geometric reasoning, yet existing visuo-tactile learning methods struggle with sub-millimeter precision tasks that are routine for traditional model-based approaches. We identify a key limitation:…

Human engagement estimation in conversational scenarios is essential for applications such as adaptive tutoring, remote healthcare assessment, and socially aware human--computer interaction. Engagement is a dynamic, multimodal signal…