Related papers: ZeroDVFS: Zero-Shot LLM-Guided Core and Frequency …

Diffusion-based large language models (dLLMs) rely on bidirectional attention, which prevents lossless KV caching and requires a full forward pass at every denoising step. Existing approximate KV caching methods reduce this cost by…

Latent representations are critical for the performance and robustness of machine learning models, as they encode the essential features of data in a compact and informative manner. However, in vision tasks, these representations are often…

Sensor data streams provide valuable information around activities and context for downstream applications, though integrating complementary information can be challenging. We show that large language models (LLMs) can be used for late…

Heterogeneous embedded systems, with diverse computing elements and accelerators such as FPGAs, offer a promising platform for fast and flexible ML inference, which is crucial for services such as autonomous driving and augmented reality,…

Demand response (DR) programs aim to engage distributed small-scale flexible loads, such as thermostatically controllable loads (TCLs), to provide various grid support services. Linearly Solvable Markov Decision Process (LS-MDP), a variant…

Pre-trained multi-modal vision-language models (VLMs) are becoming increasingly popular due to their exceptional performance on downstream vision applications, particularly in the few- and zero-shot settings. However, selecting the…

The efficiency of large vision-language models (LVLMs) is constrained by the computational bottleneck of the attention mechanism during the prefill phase and the memory bottleneck of fetching the key-value (KV) cache in the decoding phase,…

We propose DFModel, a modeling framework for mapping dataflow computation graphs onto large-scale systems. Mapping a workload to a system requires optimizing dataflow mappings at various levels, including the inter-chip (between chips)…

Diffusion models (DMs) have been adopted across diverse fields with its remarkable abilities in capturing intricate data distributions. In this paper, we propose a Fast Diffusion Model (FDM) to significantly speed up DMs from a stochastic…

To alleviate hardware scarcity in training large deep neural networks (DNNs), particularly large language models (LLMs), we present FusionLLM, a decentralized training system designed and implemented for training DNNs using geo-distributed…

We present CadLLM, a training-free method to accelerate the inference throughput of diffusion-based LLMs (dLLMs). We first investigate the dynamic nature of token unmasking confidence across blocks and steps. Based on this observation, we…

While modern Text-to-Speech (TTS) systems achieve high fidelity for read-style speech, they struggle to generate Autonomous Sensory Meridian Response (ASMR), a specialized, low-intensity speech style essential for relaxation. The inherent…

With the growing prevalence of smart grid technology, short-term load forecasting (STLF) becomes particularly important in power system operations. There is a large collection of methods developed for STLF, but selecting a suitable method…

LLMs have seen rapid adoption in all domains. They need to be trained on high-end high-performance computing (HPC) infrastructures and ingest massive amounts of input data. Unsurprisingly, at such a large scale, unexpected events (e.g.,…

The deployment of ML models on edge devices is challenged by limited computational resources and energy availability. While split computing enables the decomposition of large neural networks (NNs) and allows partial computation on both edge…

Graphics Processing Units (GPUs) support dynamic voltage and frequency scaling (DVFS) in order to balance computational performance and energy consumption. However, there still lacks simple and accurate performance estimation of a given GPU…

Large Language Model (LLM) serving systems remain fundamentally fragile, where frequent hardware faults in hyperscale clusters trigger disproportionate service outages in the software stack. Current recovery mechanisms are prohibitively…

We present an Equation/Variable free machine learning (EVFML) framework for the control of the collective dynamics of complex/multiscale systems modelled via microscopic/agent-based simulators. The approach obviates the need for…

Diffusion Large Language Models (dLLMs) have emerged as a promising alternative to Autoregressive Models (ARMs), utilizing parallel decoding to overcome sequential bottlenecks. However, existing research focuses primarily on kernel-level…

Object goal navigation is a fundamental task in embodied AI, where an agent is instructed to locate a target object in an unexplored environment. Traditional learning-based methods rely heavily on large-scale annotated data or require…