Related papers: CAT-MoEformer: Context-Aware Temporal MoE Transfor…

We present a semantics modulated, multi scale Transformer for 3D gaze estimation. Our model conditions CLIP global features with learnable prototype banks (illumination, head pose, background, direction), fuses these prototype-enriched…

Mixture-of-Experts (MoE) models improve transformer efficiency but lack a unified theoretical explanation, especially when both feed-forward and attention layers are allowed to specialize. To this end, we study the Mixture-of-Transformers…

Transformer-based models have recently made significant advances in accurate time-series forecasting, but even these architectures struggle to scale efficiently while capturing long-term temporal dynamics. Mixture-of-Experts (MoE) layers…

Mixture-of-Experts (MoE) has emerged as a powerful paradigm for scaling model capacity while preserving computational efficiency. Despite its notable success in large language models (LLMs), existing attempts to apply MoE to Diffusion…

Recent advances in Earth Observation have focused on large-scale foundation models. However, these models are computationally expensive, limiting their accessibility and reuse for downstream tasks. In this work, we investigate compact…

Wireless communications at high-frequency bands with large antenna arrays face challenges in beam management, which can potentially be improved by multimodality sensing information from cameras, LiDAR, radar, and GPS. In this paper, we…

Accurate beam prediction is essential for maintaining reliable links and high spectral efficiency in dynamic low-altitude wireless networks. However, existing approaches often fail to capture the deep correlations across heterogeneous…

In this paper, we present DiT-MoE, a sparse version of the diffusion Transformer, that is scalable and competitive with dense networks while exhibiting highly optimized inference. The DiT-MoE includes two simple designs: shared expert…

Although gait recognition has drawn increasing research attention recently, since the silhouette differences are quite subtle in spatial domain, temporal feature representation is crucial for gait recognition. Inspired by the observation…

Accurate univariate forecasting remains a pressing need in real-world systems, such as energy markets, hydrology, retail demand, and IoT monitoring, where signals are often intermittent and horizons span both short- and long-term. While…

Mixture-of-Experts (MoE) models have emerged as a promising direction for scaling vision architectures efficiently. Among them, Soft MoE improves training stability by assigning each token to all experts via continuous dispatch weights.…

Neural operators have been increasingly used as data-driven surrogates for time-marching predictions of turbulent flows. However, long-horizon autoregressive prediction is sensitive to error accumulation and the choice of prediction…

Long-term weather forecasting is critical for socioeconomic planning and disaster preparedness. While recent approaches employ finetuning to extend prediction horizons, they remain constrained by the issues of catastrophic forgetting, error…

The unique complementarity of frame-based and event cameras for high frame rate object tracking has recently inspired some research attempts to develop multi-modal fusion approaches. However, these methods directly fuse both modalities and…

Entropy estimation is essential for the performance of learned image compression. It has been demonstrated that a transformer-based entropy model is of critical importance for achieving a high compression ratio, however, at the expense of a…

Climate change stands as one of the most pressing global challenges of the twenty-first century, with far-reaching consequences such as rising sea levels, melting glaciers, and increasingly extreme weather patterns. Accurate forecasting is…

Gaze estimation methods commonly use facial appearances to predict the direction of a person gaze. However, previous studies show three major challenges with convolutional neural network (CNN)-based, transformer-based, and contrastive…

Spatio-temporal forecasting is crucial in transportation, logistics, and supply chain management. However, current methods struggle with large, complex datasets. We propose a dynamic, multi-modal approach that integrates the strengths of…

Deep learning based semantic communication has achieved significant progress in wireless image transmission, but most existing schemes rely on fixed models and thus lack robustness to diverse image contents and dynamic channel conditions.…

Channel estimation is essential to massive multiple-input multiple-output (MIMO) systems. While recent generative model-based approaches using lightweight diffusion models (DMs) have achieved superior performance, they typically rely on a…