Related papers: AME: An Efficient Heterogeneous Agentic Memory Eng…
Large language models (LLMs) deployed on edge servers are increasingly used in latency-sensitive applications such as personalized assistants, recommendation, and content moderation. However, the non-stationary nature of user data…
Human memory is inherently prone to forgetting. To address this, multimodal embedding models have been introduced, which transform diverse real-world data into a unified embedding space. These embeddings can be retrieved efficiently, aiding…
In recent years the PC has been replaced by mobile devices for many security sensitive operations, both from a privacy and a financial standpoint. While security mechanisms are deployed at various levels, these are frequently put under…
The demand for lightweight models in image classification tasks under resource-constrained environments necessitates a balance between computational efficiency and robust feature representation. Traditional attention mechanisms, despite…
In recent years, we have observed a clear trend in the rapid rise of autonomous vehicles, robotics, virtual reality, and augmented reality. The core technology enabling these applications, Simultaneous Localization And Mapping (SLAM),…
Homomorphic encryption (HE) allows direct computations on encrypted data. Despite numerous research efforts, the practicality of HE schemes remains to be demonstrated. In this regard, the enormous size of ciphertexts involved in HE…
Real-time video inference on edge devices like mobile phones and drones is challenging due to the high computation cost of Deep Neural Networks. We present Adaptive Model Streaming (AMS), a new approach to improving performance of efficient…
ARM recently introduced a security feature called Memory Tagging Extension or MTE, which is designed to defend against common memory safety vulnerabilities, such as buffer overflow and use after free. In this paper, we examine three aspects…
Fully Homomorphic Encryption (FHE) is known to be extremely computationally-intensive, application-specific accelerators emerged as a powerful solution to narrow the performance gap. Nonetheless, due to the increasing complexities in FHE…
Modern heterogeneous computing architectures, which couple multi-core CPUs with discrete many-core GPUs (or other specialized hardware accelerators), enable unprecedented peak performance and energy efficiency levels. Unfortunately, though,…
General matrix-matrix multiplication (GEMM) is a fundamental operation in machine learning (ML) applications. We present the first comprehensive performance acceleration of GEMM workloads on AMD's second-generation AIE-ML (AIE2)…
On top of Segment Anything Model (SAM), SAM 2 further extends its capability from image to video inputs through a memory bank mechanism and obtains a remarkable performance compared with previous methods, making it a foundation model for…
Embodied AI agents increasingly rely on large language models (LLMs) for planning, yet per-step LLM calls impose severe latency and cost. In this paper, we show that embodied tasks exhibit strong plan locality, where the next plan is…
Analog Content Addressable Memories (aCAMs) have proven useful for associative in-memory computing applications like Decision Trees, Finite State Machines, and Hyper-dimensional Computing. While non-volatile implementations using FeFETs and…
The efficiency and accuracy of mapping are crucial in a large scene and long-term AR applications. Multi-agent cooperative SLAM is the precondition of multi-user AR interaction. The cooperation of multiple smart phones has the potential to…
Homomorphic Encryption (HE) enables secure computation on encrypted data, addressing privacy concerns in cloud computing. However, the high computational cost of HE operations, particularly matrix multiplication (MM), remains a major…
Splitting the inference model between device, edge server, and cloud can improve the performance of EI greatly. Additionally, the non-orthogonal multiple access (NOMA), which is the key supporting technologies of B5G/6G, can achieve massive…
On-device training for personalized learning is a challenging research problem. Being able to quickly adapt deep prediction models at the edge is necessary to better suit personal user needs. However, adaptation on the edge poses some…
Long-term memory is becoming a central bottleneck for language agents. Exsting RAG and GraphRAG systems largely treat memory graphs as static retrieval middleware, which limits their ability to recover complete evidence chains from partial…
Computational resource constraints on edge devices make it difficult to develop a fully embedded AI companion system with a satisfactory user experience. AI companion and memory systems detailed in existing literature cannot be directly…