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

Multi-modal entity alignment (MMEA) aims to discover identical entities across different knowledge graphs (KGs) whose entities are associated with relevant images. However, current MMEA algorithms rely on KG-level modality fusion strategies…

Mixture-of-Experts (MoE) architectures enable conditional computation by routing inputs to multiple expert subnetworks and are often motivated as a mechanism for scaling large language models. In this project, we instead study MoE behavior…

Predicting human mobility across multiple cities presents significant challenges due to the complex and diverse spatial-temporal dynamics inherent in different urban environments. In this study, we propose a robust approach to predict human…

Mixture-of-Experts (MoE) models scale large language models through conditional computation, but inference becomes memory-bound once expert weights exceed the capacity of GPU memory. In this case, weights must be offloaded to external…

Mixture of Experts (MoE) models based on Transformer architecture are pushing the boundaries of language and vision tasks. The allure of these models lies in their ability to substantially increase the parameter count without a…

Pedestrian crossing intention prediction is essential for autonomous vehicles to improve pedestrian safety and reduce traffic accidents. However, accurate pedestrian intention prediction in urban environments remains challenging due to the…

Multivariate time series forecasting is crucial across a wide range of domains. While presenting notable progress for the Transformer architecture, iTransformer still lags behind the latest MLP-based models. We attribute this performance…

Empowering Large Multimodal Models (LMMs) with image generation often leads to catastrophic forgetting in understanding tasks due to severe gradient conflicts. While existing paradigms like Mixture-of-Transformers (MoT) mitigate this…

End-to-end models with large capacity have significantly improved multilingual automatic speech recognition, but their computation cost poses challenges for on-device applications. We propose a streaming truly multilingual Conformer…

Mixture-of-Expert (MoE) models outperform conventional models by selectively activating different subnets, named experts, on a per-token basis. This gated computation generates dynamic communications that cannot be determined beforehand,…

Time series forecasting requires capturing patterns across multiple temporal scales while maintaining computational efficiency. This paper introduces AWGformer, a novel architecture that integrates adaptive wavelet decomposition with…

We introduce ET-Former, a novel end-to-end algorithm for semantic scene completion using a single monocular camera. Our approach generates a semantic occupancy map from single RGB observation while simultaneously providing uncertainty…

It has been challenging to model the complex temporal-spatial dependencies between agents for trajectory prediction. As each state of an agent is closely related to the states of adjacent time steps, capturing the local temporal dependency…

With the rapid development of the Intelligent Transportation System (ITS), accurate traffic forecasting has emerged as a critical challenge. The key bottleneck lies in capturing the intricate spatio-temporal traffic patterns. In recent…

Earth Observatory is a growing research area that can capitalize on the powers of AI for short time forecasting, a Now-casting scenario. In this work, we tackle the challenge of weather forecasting using a video transformer network. Vision…

Mixture-of-Experts (MoE) models substantially improve performance by increasing the capacity of dense architectures. However, directly training MoE models requires considerable computational resources and introduces extra overhead in…

Time series forecasting is a long-standing challenge due to the real-world information is in various scenario (e.g., energy, weather, traffic, economics, earthquake warning). However some mainstream forecasting model forecasting result is…

The development of robust and generalisable models for encoding the spatio-temporal dynamics of human brain activity is crucial for advancing neuroscientific discoveries. However, significant individual variation in the organisation of the…

Accurate and reliable motion forecasting is essential for the safe deployment of autonomous vehicles (AVs), particularly in rare but safety-critical scenarios known as corner cases. Existing models often underperform in these situations due…

Building scalable vision-language models to learn from diverse, multimodal data remains an open challenge. In this paper, we introduce an Efficient Vision-languagE foundation model, namely EVE, which is one unified multimodal Transformer…