相关论文: MOPAR: A Model Partitioning Framework for Deep Lea…

Mixture of Experts (MoE) has become a mainstream architecture for building Large Language Models (LLMs) by reducing per-token computation while enabling model scaling. It can be viewed as partitioning a large Feed-Forward Network (FFN) at…

Deep learning based intrusion detection systems (DL-based IDS) have emerged as one of the best choices for providing security solutions against various network intrusion attacks. However, due to the emergence and development of adversarial…

The paradigm of large language model (LLM) reasoning is shifting from parameter scaling to test-time compute scaling, yet many existing approaches still rely on uniform brute-force sampling (for example, fixed best-of-N or self-consistency)…

Along with the fast evolution of deep neural networks, the hardware system is also developing rapidly. As a promising solution achieving high scalability and low manufacturing cost, multi-accelerator systems widely exist in data centers,…

Inference scaling methods for LLMs often rely on decomposing problems into steps (or groups of tokens), followed by sampling and selecting the best next steps. However, these steps and their sizes are often predetermined or manually…

Multi-Chip-Modules (MCMs) reduce the design and fabrication cost of machine learning (ML) accelerators while delivering performance and energy efficiency on par with a monolithic large chip. However, ML compilers targeting MCMs need to…

The proliferation of resourceful mobile devices that store rich, multidimensional and privacy-sensitive user data motivate the design of federated learning (FL), a machine-learning (ML) paradigm that enables mobile devices to produce an ML…

Deep learning (DL) has been widely adopted those last years but they are computing-intensive method. Therefore, scientists proposed diverse optimization to accelerate their predictions for end-user applications. However, no single inference…

Serverless computing paradigm has become more ingrained into the industry, as it offers a cheap alternative for application development and deployment. This new paradigm has also created new kinds of problems for the developer, who needs to…

Sequential recommendation (SR) systems have evolved significantly over the past decade, transitioning from traditional collaborative filtering to deep learning approaches and, more recently, to large language models (LLMs). While the…

The edge intelligence (EI) has been widely applied recently. Spliting the model between device, edge server, and cloud can improve the performance of EI greatly. The model segmentation without user mobility has been investigated deeply by…

Collaborative Machine Learning is a paradigm in the field of distributed machine learning, designed to address the challenges of data privacy, communication overhead, and model heterogeneity. There have been significant advancements in…

One of the early weaknesses identified in deep neural networks trained for image classification tasks was their inability to provide low confidence predictions on out-of-distribution (OOD) data that was significantly different from the…

In this paper, we propose DEEPSERVE, a scalable and serverless AI platform designed to efficiently serve large language models (LLMs) at scale in cloud environments. DEEPSERVE addresses key challenges such as resource allocation, serving…

The growing demand for large artificial intelligence model (LAIM) services is driving a paradigm shift from traditional cloud-based inference to edge-based inference for low-latency, privacy-preserving applications. In particular,…

Online learning, where feature spaces can change over time, offers a flexible learning paradigm that has attracted considerable attention. However, it still faces three significant challenges. First, the heterogeneity of real-world data…

Differentiable architecture search is prevalent in the field of NAS because of its simplicity and efficiency, where two paradigms, multi-path algorithms and single-path methods, are dominated. Multi-path framework (e.g. DARTS) is intuitive…

Mixture of Experts (MoE) architectures significantly enhance the capacity of LLMs without proportional increases in computation, but at the cost of a vast parameter size. Offloading MoE expert parameters to host memory and leveraging both…

IoT applications increasingly rely on on-device AI accelerators to ensure high performance, especially in low-connectivity and safety-critical scenarios. However, the limited on-chip memory of these accelerators forces inference runtimes to…

Federated Learning (FL) is a privacy-preserving machine learning technique that allows decentralized collaborative model training across a set of distributed clients, by avoiding raw data exchange. A fundamental component of FL is the…