Related papers: EPD-Serve: A Flexible Multimodal EPD Disaggregatio…
Edge computing allows Service Providers (SPs) to enhance user experience by placing their services closer to the network edge. Determining the optimal provisioning of edge resources to meet the varying and uncertain demand cost-effectively…
The context window of large language models (LLMs) is rapidly increasing, leading to a huge variance in resource usage between different requests as well as between different phases of the same request. Restricted by static parallelism…
Unified multimodal embedding spaces underpin practical applications such as cross-modal retrieval and zero-shot recognition. In many real deployments, however, supervision is available only for a small subset of modality pairs (e.g.,…
We propose a communication-efficient collaborative inference framework in the domain of edge inference, focusing on the efficient use of vision transformer (ViT) models. The partitioning strategy of conventional collaborative inference…
Echo State Network (ESN) presents a distinguished kind of recurrent neural networks. It is built upon a sparse, random and large hidden infrastructure called reservoir. ESNs have succeeded in dealing with several non-linear problems such as…
Seismic data interpolation is a critical pre-processing step for improving seismic imaging quality and remains a focus of academic innovation. To address the computational inefficiencies caused by extensive iterative resampling in current…
Radar sensors offer power-efficient solutions for always-on smart devices, but processing the data streams on resource-constrained embedded platforms remains challenging. This paper presents novel techniques that leverage the temporal…
The Audio-Visual Video Parsing task aims to recognize and temporally localize all events occurring in either the audio or visual stream, or both. Capturing accurate event semantics for each audio/visual segment is vital. Prior works…
Attentio-FFN disaggregation (AFD) is an emerging architecture for LLM decoding that separates state-heavy, KV-cache-dominated Attention computation from stateless, compute-intensive FFN computation, connected by per-step communication.…
Sleep staging is essential for sleep assessment and plays a vital role as a health indicator. Many recent studies have devised various machine learning as well as deep learning architectures for sleep staging. However, two key challenges…
Text-to-image generation using diffusion models has gained increasing popularity due to their ability to produce high-quality, realistic images based on text prompts. However, efficiently serving these models is challenging due to their…
One of the primary areas of interest in High Performance Computing is the improvement of performance of parallel workloads. Nowadays, compilable source code-based optimization tasks that employ deep learning often exploit LLVM Intermediate…
Diffusion-based generation is increasingly powering production content pipelines; however, deploying these models at scale remains a significant challenge. Model weights frequently exceed the memory capacity of commodity GPUs, while the…
Mobile edge caching (MEC) has received much attention as a promising technique to overcome the stringent latency and data hungry requirements in the future generation wireless networks. Meanwhile, full-duplex (FD) transmission can…
Aggressively quantized large language models (LLMs), such as BitNet-style 1.58-bit Transformers with ternary weights, make it feasible to deploy generative AI on low-power edge FPGAs. However, as prompts grow to tens of thousands of tokens,…
Cross-modality magnetic resonance (MR) image synthesis can be used to generate missing modalities from given ones. Existing (supervised learning) methods often require a large number of paired multi-modal data to train an effective…
Cascade systems, consisting of a lightweight model processing all samples and a heavier, high-accuracy model refining challenging samples, have become a widely-adopted distributed inference approach to achieving high accuracy and…
Diffusion models (DMs) excel in image generation but suffer from slow inference and training-inference discrepancies. Although gradient-based solvers for DMs accelerate denoising inference, they often lack theoretical foundations in…
The emergence of large-scale Mixture of Experts (MoE) models represents a significant advancement in artificial intelligence, offering enhanced model capacity and computational efficiency through conditional computation. However, deploying…
Prevailing LLM serving engines employ expert parallelism (EP) to implement multi-device inference of massive MoE models. However, the efficiency of expert parallel inference is largely bounded by inter-device communication, as EP embraces…