Related papers: Accelerating Latency-Critical Applications with AI…

Advances in hybrid bonding and packaging have driven growing interest in 3D DRAM-stacked accelerators with higher memory bandwidth and capacity. As LLMs scale to hundreds of billions or trillions of parameters, distributed inference across…

Anderson Acceleration (AA) is a method to accelerate the convergence of fixed point iterations for nonlinear, algebraic systems of equations. Due to the requirement of solving a least squares problem at each iteration and a reliance on…

Large Transformer networks are increasingly used in settings where low inference latency can improve the end-user experience and enable new applications. However, autoregressive inference is resource intensive and requires parallelism for…

Fine-tuning large language models (LLMs) on private, on-device data can empower tailored personalized AI agents. However, fine-tuning LLMs on resource-constrained edge devices faces significant challenges, including excessive computation…

Scaling the amount of data used for supervied fine-tuning(SFT) does not guarantee the proportional gains in model performance, highlighting a critical need to understand what makes training samples effective. This work identifies two…

Low-Rank Adaptation (LoRA) is one of the most widely used techniques for fine-tuning large language models (LLMs). By introducing a small number of trainable low-rank weight matrices, LoRA substantially reduces the number of parameters that…

An efficient hardware implementation for Simultaneous Localization and Mapping (SLAM) methods is of necessity for mobile autonomous robots with limited computational resources. In this paper, we propose a resource-efficient FPGA…

Serverless computing has grown rapidly for serving Large Language Model (LLM) inference due to its pay-as-you-go pricing, fine-grained GPU usage, and rapid scaling. However, our analysis reveals that current serverless can effectively serve…

Large language models (LLMs) have demonstrated exceptional proficiency in understanding and generating human language, but efficient inference on resource-constrained embedded devices remains challenging due to large model sizes and…

Test-Time Scaling (TTS) has proven effective in improving the performance of Large Language Models (LLMs) during inference. However, existing research has overlooked the efficiency of TTS from a latency-sensitive perspective. Through a…

Large language models (LLMs) with different architectures and sizes have been developed. Serving each LLM with dedicated GPUs leads to resource waste and service inefficiency due to the varying demand of LLM requests. A common practice is…

Real-time artificial intelligence (AI) applications mapped onto edge computing need to perform data capture, process data, and device actuation within given bounds while using the available devices. Task synchronization across the devices…

The discussion around AI-Engineering, that is, Software Engineering (SE) for AI-enabled Systems, cannot ignore a crucial class of software systems that are increasingly becoming AI-enhanced: Those used to enable or support the SE process,…

Multi-Head Latent Attention (MLA), introduced in DeepSeek-V2, improves the efficiency of large language models by projecting query, key, and value tensors into a compact latent space. This architectural change reduces the KV-cache size and…

Speaker-Attributed Automatic Speech Recognition (SAA) enhances traditional ASR systems by incorporating relative speaker identity tags directly into the transcript (e.g., [Speaker 1]:, [Speaker 2]:). In this work, we extend the capabilities…

Augmenting large language models (LLM) to use external tools enhances their performance across a variety of tasks. However, prior works over-rely on task-specific demonstration of tool use that limits their generalizability and…

With a recent trend of using Large Language Models (LLMs) for different applications within smart cities, there is a need for pushing these models toward the edge of network while still preserving their performance. Edge Computing (EC) as a…

The remarkable capabilities of Large Language Models (LLMs) often need to be tailored for specific applications, requiring the integration of new knowledge or the acquisition of new skills. While full fine-tuning is a powerful adaptation…

Failure Analysis (FA) is a highly intricate and knowledge-intensive process. The integration of AI components within the computational infrastructure of FA labs has the potential to automate a variety of tasks, including the detection of…

Multimodal Large Language Models (MLLMs) achieve strong performance through instruction tuning, but real-world deployment requires them to continually expand their capabilities, making Multimodal Continual Instruction Tuning (MCIT)…