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

Accurate fine-grained geospatial scene classification using remote sensing imagery is essential for a wide range of applications. However, existing approaches often rely on manually zooming remote sensing images at different scales to…

Integrating the different data modalities of cancer patients can significantly improve the predictive performance of patient survival. However, most existing methods ignore the simultaneous utilization of rich semantic features at different…

Automatic Modulation Classification (AMC) plays a vital role in time series analysis, such as signal classification and identification within wireless communications. Deep learning-based AMC models have demonstrated significant potential in…

As a prominent data modality task, time series forecasting plays a pivotal role in diverse applications. With the remarkable advancements in Large Language Models (LLMs), the adoption of LLMs as the foundational architecture for time series…

Mixture-of-Experts (MoE) enhances model performance while maintaining computational efficiency, making it well-suited for large-scale applications. Conventional mixture-of-experts (MoE) architectures suffer from suboptimal coordination…

Time series forecasting (TSF) is critical in domains like energy, finance, healthcare, and logistics, requiring models that generalize across diverse datasets. Large pre-trained models such as Chronos and Time-MoE show strong zero-shot (ZS)…

Accurate prediction of the next point of interest (POI) within human mobility trajectories is essential for location-based services, as it enables more timely and personalized recommendations. In particular, with the rise of these…

Moving Object Detection (MOD) is a crucial task for the Autonomous Driving pipeline. MOD is usually handled via 2-stream convolutional architectures that incorporates both appearance and motion cues, without considering the inter-relations…

Recent advancements in general-purpose or domain-specific multimodal large language models (LLMs) have witnessed remarkable progress for medical decision-making. However, they are designated for specific classification or generative tasks,…

Modern applications increasingly involve many heterogeneous input streams, such as clinical sensors, wearable device data, imaging, and text, each with distinct measurement models, sampling rates, and noise characteristics. We define this…

Recent advancements in Mixture of Experts (MoE) models have significantly increased their parameter scale as well as model performance. Extensive offloading techniques have been proposed to address the GPU memory limitations of MoE…

Dynamic link prediction plays a crucial role in diverse applications including social network analysis, communication forecasting, and financial modeling. While recent Transformer-based approaches have demonstrated promising results in…

Predicting human gaze is important in Human-Computer Interaction (HCI). However, to practically serve HCI applications, gaze prediction models must be scalable, fast, and accurate in their spatial and temporal gaze predictions. Recent…

Trust prediction provides valuable support for decision-making, risk mitigation, and system security enhancement. Recently, Graph Neural Networks (GNNs) have emerged as a promising approach for trust prediction, owing to their ability to…

Trajectory prediction is crucial for the reliability and safety of autonomous driving systems, yet it remains a challenging task in complex interactive scenarios due to noisy trajectory observations and intricate agent interactions.…

Predicting future trajectories of surrounding vehicles heavily relies on what contextual information is given to a motion prediction model. The context itself can be static (lanes, regulatory elements, etc) or dynamic (traffic…

Large Language Models (LLMs) are increasingly deployed as Internet/Web services (LLM-as-a-Service) with strict latency Service-Level Objectives (SLOs) under tight GPU memory budgets. Mixture-of-Experts (MoE) models improve quality and…

This paper introduces a novel architecture for trajectory-conditioned forecasting of future 3D scene occupancy. In contrast to methods that rely on variational autoencoders (VAEs) to generate discrete occupancy tokens, which inherently…

Micro-expression recognition (MER), a critical subfield of affective computing, presents greater challenges than macro-expression recognition due to its brief duration and low intensity. While incorporating prior knowledge has been shown to…

Mixture-of-experts based models, which use language experts to extract language-specific representations effectively, have been well applied in code-switching automatic speech recognition. However, there is still substantial space to…