Related papers: AdaFlow: Opportunistic Inference on Asynchronous M…

Federated Learning (FL) in mobile environments faces significant communication bottlenecks. Gradient compression has proven as an effective solution to this issue, offering substantial benefits in environments with limited bandwidth and…

With the growing workload of inference tasks on mobile devices, state-of-the-art neural architectures (NAs) are typically designed through Neural Architecture Search (NAS) to identify NAs with good tradeoffs between accuracy and efficiency…

To support latency-sensitive AI applications ranging from autonomous driving to industrial robot manipulation, 6G envisions distributed ML with computational resources in mobile, edge, and cloud connected over hyper-reliable low-latency…

Deep learning methods have shown promising performance in fault diagnosis for multimode process. Most existing studies assume that the collected health state categories from different operating modes are identical. However, in real…

Data heterogeneity hinders clinical deployment of medical image analysis models, and generative data augmentation helps mitigate this issue. However, recent diffusion-based methods that synthesize image-mask pairs often ignore distribution…

Data assimilation (DA) integrates observations with a dynamical model to estimate states of PDE-governed systems. Model-driven methods (e.g., Kalman, particle) presuppose full knowledge of the true dynamics, which is not always satisfied in…

Mobile-centric AI applications have high requirements for resource-efficiency of model inference. Input filtering is a promising approach to eliminate the redundancy so as to reduce the cost of inference. Previous efforts have tailored…

A simultaneous enhancement of accuracy and diversity of predictions remains a challenge in ambiguous medical image segmentation (AMIS) due to the inherent trade-offs. While truncated diffusion probabilistic models (TDPMs) hold strong…

To generate accurate and reliable predictions, modern AI systems need to combine data from multiple modalities, such as text, images, audio, spreadsheets, and time series. Multi-modal data introduces new opportunities and challenges for…

The surface pressure field of transportation systems, including cars, trains, and aircraft, is critical for aerodynamic analysis and design. In recent years, deep neural networks have emerged as promising and efficient methods for modeling…

Federated Retrieval (FR) routes queries across multiple external knowledge sources, to mitigate hallucinations of LLMs, when necessary external knowledge is distributed. However, existing methods struggle to retrieve high-quality and…

Although neural networks are conventionally optimized towards zero training loss, it has been recently learned that targeting a non-zero training loss threshold, referred to as a flood level, often enables better test time generalization.…

With the rapid development of imaging sensor technology in the field of remote sensing, multi-modal remote sensing data fusion has emerged as a crucial research direction for land cover classification tasks. While diffusion models have made…

Multimodal foundation models have achieved impressive progress across a wide range of vision-language tasks. However, existing approaches often adopt fixed or task-specific fusion strategies, neglecting the intrinsic variability of modality…

The prevalence of networked sensors and actuators in many real-world systems such as smart buildings, factories, power plants, and data centers generate substantial amounts of multivariate time series data for these systems. The rich sensor…

With the rapid development of deep learning, recent research on intelligent and interactive mobile applications (e.g., health monitoring, speech recognition) has attracted extensive attention. And these applications necessitate the mobile…

Multimodal Large Language Models (MLLMs) have shown impressive capabilities in visual reasoning, yet come with substantial computational cost, limiting their deployment in resource-constrained settings. Despite recent effort on improving…

Scene flow prediction is a crucial underlying task in understanding dynamic scenes as it offers fundamental motion information. However, contemporary scene flow methods encounter three major challenges. Firstly, flow estimation solely based…

Modern software systems generate extensive heterogeneous log data with dynamic formats, fragmented event sequences, and varying temporal patterns, making anomaly detection both crucial and challenging. To address these complexities, we…

Uncertainty-aware prediction is essential for safe motion planning, especially when using learned models to forecast the behavior of surrounding agents. Conformal prediction is a statistical tool often used to produce uncertainty-aware…