Related papers: Naga: Vedic Encoding for Deep State Space Models

Guided depth super-resolution (GDSR) reconstructs HR depth maps from LR inputs with HR RGB guidance. Existing methods either model each modality independently or rely on computationally expensive attention mechanisms with quadratic…

Long-range dependencies are critical for understanding genomic structure and function, yet most conventional methods struggle with them. Widely adopted transformer-based models, while excelling at short-context tasks, are limited by the…

Recent years have witnessed significant advancements in light field image super-resolution (LFSR) owing to the progress of modern neural networks. However, these methods often face challenges in capturing long-range dependencies (CNN-based)…

In recent years, Transformers have become the de-facto architecture for long-term sequence forecasting (LTSF), but faces challenges such as quadratic complexity and permutation invariant bias. A recent model, Mamba, based on selective state…

Structured State Space Models (SSMs) have emerged as a transformative paradigm in sequence modeling, addressing critical limitations of Recurrent Neural Networks (RNNs) and Transformers, namely, vanishing gradients, sequential computation…

The recent surge in State Space Models (SSMs), particularly the emergence of Mamba, has established them as strong alternatives or complementary modules to Transformers across diverse domains. In this work, we aim to explore the potential…

Surgical phase recognition is crucial for enhancing the efficiency and safety of computer-assisted interventions. One of the fundamental challenges involves modeling the long-distance temporal relationships present in surgical videos.…

Sequences and time-series often arise in robot tasks, e.g., in activity recognition and imitation learning. In recent years, deep neural networks (DNNs) have emerged as an effective data-driven methodology for processing sequences given…

Lightweight and efficient deep joint source-channel coding (JSCC) is a key technology for semantic communications. In this paper, we design a novel JSCC scheme named MambaJSCC, which utilizes a visual state space model with channel…

Detecting navigable space is the first and also a critical step for successful robot navigation. In this work, we treat the visual navigable space segmentation as a scene decomposition problem and propose a new network, NSS-VAEs (Navigable…

Multivariate Time series forecasting is crucial in domains such as transportation, meteorology, and finance, especially for predicting extreme weather events. State-of-the-art methods predominantly rely on Transformer architectures, which…

Brain computer interface (BCI) has been popular as a key approach to monitor our brains recent year. Mental states monitoring is one of the most important BCI applications and becomes increasingly accessible. However, the mental state…

In recent years, Transformers have become the de-facto architecture for sequence modeling on text and a variety of multi-dimensional data, such as images and video. However, the use of self-attention layers in a Transformer incurs…

Modeling of music audio semantics has been previously tackled through learning of mappings from audio data to high-level tags or latent unsupervised spaces. The resulting semantic spaces are theoretically limited, either because the chosen…

As one of the most effective methods for cardiovascular disease (CVD) diagnosis, multi-lead Electrocardiogram (ECG) signals present a characteristic multi-sensor information fusion challenge that has been continuously researched in deep…

The diversity and complexity of Indic languages present unique challenges for natural language processing (NLP) tasks, particularly in the domain of question answering (QA).To address these challenges, this paper explores the application of…

Semantic scene completion (SSC) is essential for achieving comprehensive perception in autonomous driving systems. However, existing SSC methods often overlook the high deployment costs in real-world applications. Traditional architectures,…

Denoising is a crucial preprocessing step for hyperspectral images (HSIs) due to noise arising from intra-imaging mechanisms and environmental factors. Long-range spatial-spectral correlation modeling is beneficial for HSI denoising but…

Deep forecasting models often suffer from attenuated periodic perception and entangled trend-noise representations as network depth increases. Moreover, the widely adopted channel-independent paradigm, while improving training stability,…

Surrogate strategies are used widely for uncertainty quantification of groundwater models in order to improve computational efficiency. However, their application to dynamic multiphase flow problems is hindered by the curse of…