Related papers: DIAL: Decentralized I/O AutoTuning via Learned Cli…
Adaptive test-time compute for LLM agents aims to invoke extra computation only when it improves performance. Existing methods typically use confidence-, uncertainty-, or difficulty-based gates, assuming a fixed direction from the gating…
Multimodal transformers integrate diverse data types like images, audio, and text, advancing tasks such as audio-visual understanding and image-text retrieval; yet their high parameterization limits deployment on resource-constrained edge…
Personalized Intelligence (PI) is the problem of providing customized AI experiences tailored to each individual user. In many applications, PI is preferred or even required. Existing personalization approaches involve fine-tuning…
Instruction tuning has shown promising potential for developing general-purpose AI capabilities by using large-scale pre-trained models and boosts growing research to integrate multimodal information for creative applications. However,…
Conventional federated learning (FL) trains one global model for a federation of clients with decentralized data, reducing the privacy risk of centralized training. However, the distribution shift across non-IID datasets, often poses a…
Motivated by the need for adaptive, secure and responsive scheduling in a great range of computing applications, including human-centered and time-critical applications, this paper proposes a scheduling framework that seamlessly adds…
Federated learning (FL) is a promising paradigm to enable collaborative model training with decentralized data. However, the training process of Large Language Models (LLMs) generally incurs the update of significant parameters, which…
There is a huge gap between numerous intriguing applications fostered by on-device large language model (LLM) fine-tuning (FT) from fresh mobile data and the limited resources of a mobile device. While existing server-assisted methods…
This paper introduces a resource allocation framework specifically tailored for addressing the problem of dynamic placement (or pinning) of parallelized applications to processing units. Under the proposed setup each thread of the…
Federated Learning (FL) facilitates collaborative model training across distributed clients while ensuring data privacy. Traditionally, FL relies on a centralized server to coordinate learning, which creates bottlenecks and a single point…
End-to-end autonomous driving is typically built upon imitation learning (IL), yet its performance is constrained by the quality of human demonstrations. To overcome this limitation, recent methods incorporate reinforcement learning (RL)…
The dynamic provisioning of virtualized resources offered by cloud computing infrastructures allows applications deployed in a cloud environment to automatically increase and decrease the amount of used resources. This capability is called…
Autotuning techniques are a promising approach to minimize the otherwise tedious manual effort of optimizing scientific applications for a specific target platform. Ideally, an autotuning approach is capable of reliably identifying the most…
Personalization in federated learning (FL) functions as a coordinator for clients with high variance in data or behavior. Ensuring the convergence of these clients' models relies on how closely users collaborate with those with similar…
Collaboratively fine-tuning (FT) large language models (LLMs) over heterogeneous mobile devices fosters immense potential applications of personalized intelligence. However, such a vision faces critical system challenges. Conventional…
Recent advances in wearable devices and Internet-of-Things (IoT) have led to massive growth in sensor data generated in edge devices. Labeling such massive data for classification tasks has proven to be challenging. In addition, data…
The Distributed Messaging Systems (DMSs) used in IoT systems require timely and reliable data dissemination, which can be achieved through configurable parameters. However, the high-dimensional configuration space makes it difficult for…
In the context of personalized federated learning (FL), the critical challenge is to balance local model improvement and global model tuning when the personal and global objectives may not be exactly aligned. Inspired by Bayesian…
Parameter-efficient transfer learning (PETL) based on large-scale pre-trained foundation models has achieved great success in various downstream applications. Existing tuning methods, such as prompt, prefix, and adapter, perform…
Federated Learning (FL) is a distributed machine learning (ML) paradigm, aiming to train a global model by exploiting the decentralized data across millions of edge devices. Compared with centralized learning, FL preserves the clients'…