Related papers: Responsive DNN Adaptation for Video Analytics agai…
Pervasive mobile AI applications primarily employ one of the two learning paradigms: cloud-based learning (with powerful large models) or on-device learning (with lightweight small models). Despite their own advantages, neither paradigm can…
The Mixture of Experts architecture allows for outrageously large neural networks by scaling model parameter size independently from computational demand (FLOPs). However, current DNN frameworks cannot effectively support the dynamic data…
The recent ground-breaking advances in deep learning networks ( DNNs ) make them attractive for embedded systems. However, it can take a long time for DNNs to make an inference on resource-limited embedded devices. Offloading the…
The burgeoning field of Multimodal Large Language Models (MLLMs) has exhibited remarkable performance in diverse tasks such as captioning, commonsense reasoning, and visual scene understanding. However, the deployment of these large-scale…
Text-to-video diffusion models have enabled high-quality video synthesis, yet often fail to generate temporally coherent and physically plausible motion. A key reason is the models' insufficient understanding of complex motions that natural…
Prior to the deployment of robotic systems, pre-training the deep-recognition models on all potential visual cases is infeasible in practice. Hence, test-time adaptation (TTA) allows the model to adapt itself to novel environments and…
The performance of deep learning models depends heavily on test samples at runtime, and shifts from the training data distribution can significantly reduce accuracy. Test-time adaptation (TTA) addresses this by adapting models during…
We explore the potential of feed-forward deep neural networks (DNNs) for emulating cloud superparameterization in realistic geography, using offline fits to data from the Super Parameterized Community Atmospheric Model. To identify the…
Large organizations have seamlessly incorporated data-driven decision making in their operations. However, as data volumes increase, expensive big data infrastructures are called to rescue. In this setting, analytics tasks become very…
We present a motion-adaptive temporal attention mechanism for parameter-efficient video generation built upon frozen Stable Diffusion models. Rather than treating all video content uniformly, our method dynamically adjusts temporal…
Parameter efficient adaptation methods have become a key mechanism to train large pre-trained models for downstream tasks. However, their per-task parameter overhead is considered still high when the number of downstream tasks to adapt for…
The wide adoption of multimedia service capable mobile devices, the availability of better networks with higher bandwidths, and the availability of platforms offering digital content has led to an increasing popularity of multimedia…
The conventional deep learning paradigm often involves training a deep model on a server and then deploying the model or its distilled ones to resource-limited edge devices. Usually, the models shall remain fixed once deployed (at least for…
Vision large language models (VLLMs) are focusing primarily on handling complex and fine-grained visual information by incorporating advanced vision encoders and scaling up visual models. However, these approaches face high training and…
Indoor localization using machine learning has gained traction due to the growing demand for location-based services. However, its long-term reliability is hindered by hardware/software variations across mobile devices, which shift the…
Deploying DNNs on System-on-Chips (SoC) with multiple heterogeneous acceleration engines is challenging, and the majority of deployment frameworks cannot fully exploit heterogeneity. We present MATCHA, a unified DNN deployment framework…
Conventionally, DNN models are trained once in the cloud and deployed in edge devices such as cars, robots, or unmanned aerial vehicles (UAVs) for real-time inference. However, there are many cases that require the models to adapt to new…
Domain adaptation, a pivotal branch of transfer learning, aims to enhance the performance of machine learning models when deployed in target domains with distinct data distributions. This is particularly critical for object detection tasks,…
Graph neural networks (GNNs) are gaining popularity for processing graph-structured data. In real-world scenarios, graph data within the same dataset can vary significantly in scale. This variability leads to depth-sensitivity, where the…
Deep Neural Networks are allowing mobile devices to incorporate a wide range of features into user applications. However, the computational complexity of these models makes it difficult to run them effectively on resource-constrained mobile…