Related papers: MMEdge: Accelerating On-device Multimodal Inferenc…
The proliferation of large language models (LLMs) is accelerating the integration of multimodal assistants into edge devices, where inference is executed under stringent latency and energy constraints, often exacerbated by intermittent…
Distributed inference serves as a promising approach to enabling the inference of large language models (LLMs) at the network edge. It distributes the inference process to multiple devices to ensure that the LLMs can fit into the device…
Edge-based multimodal medical monitoring requires models that balance diagnostic accuracy with severe energy constraints. Continuous acquisition of ECG, PPG, EMG, and IMU streams rapidly drains wearable batteries, often limiting operation…
In the latest advancements in multimodal learning, effectively addressing the spatial and semantic losses of visual data after encoding remains a critical challenge. This is because the performance of large multimodal models is positively…
Semantic communication is emerging as a key enabler for distributed edge intelligence due to its capability to convey task-relevant meaning. However, achieving communication-efficient training and robust inference over wireless links…
Multivariate time series forecasting (MTSF) plays a vital role in a wide range of real-world applications, such as weather prediction and traffic flow forecasting. Although recent advances have significantly improved the modeling of…
Mobile edge devices (e.g., AR/VR headsets) typically need to complete timely inference tasks while operating with limited on-board computing and energy resources. In this paper, we investigate the problem of collaborative inference in…
Currently, the world experiences an unprecedentedly increasing generation of application data, from sensor measurements to video streams, thanks to the extreme connectivity capability provided by 5G networks. Going beyond 5G technology,…
The combination of Integrated Sensing and Communication (ISAC) and Mobile Edge Computing (MEC) enables devices to simultaneously sense the environment and offload data to the base stations (BS) for intelligent processing, thereby reducing…
How to learn discriminative video representation from unlabeled videos is challenging but crucial for video analysis. The latest attempts seek to learn a representation model by predicting the appearance contents in the masked regions.…
The wide spread use of positioning and photographing devices gives rise to a deluge of traffic trajectory data (e.g., vehicle passage records and taxi trajectory data), with each record having at least three attributes: object ID, location…
IoT and edge-based inference systems require unique solutions to overcome resource limitations and unpredictable environments. In this paper, we propose an environment-aware dynamic pruning system that handles the unpredictability of edge…
MIRGE is a computational approach for scientific computing based on NumPy-like array computation, but using lazy evaluation to recast computation as data-flow graphs, where nodes represent immutable, multi-dimensional arrays. Evaluation of…
While embeddings from multimodal large language models (LLMs) excel as general-purpose representations, their application to dynamic modalities like audio and video remains underexplored. We introduce WAVE (\textbf{u}nified \&…
Adapting to diverse user needs at test time is a key challenge in controllable multi-objective generation. Existing methods are insufficient: merging-based approaches provide indirect, suboptimal control at the parameter level, often…
Understanding complex systems by inferring trajectories from sparse sample snapshots is a fundamental challenge in a wide range of domains, e.g., single-cell biology, meteorology, and economics. Despite advancements in Bridge and Flow…
Multimodal language models (MLMs) integrate visual and textual information by coupling a vision encoder with a large language model through the specific adapter. While existing approaches commonly rely on a single pre-trained vision…
Mixture-of-Experts (MoE) models facilitate edge deployment by decoupling model capacity from active computation, yet their large memory footprint drives the need for GPU systems with near-data processing (NDP) capabilities that offload…
Edge computing is deemed a promising technique to execute latency-sensitive applications by offloading computation-intensive tasks to edge servers. Extensive research has been conducted in the field of end-device to edge server task…
The emergence of large-scale Mixture of Experts (MoE) models represents a significant advancement in artificial intelligence, offering enhanced model capacity and computational efficiency through conditional computation. However, deploying…