Related papers: SAMP: A Model Inference Toolkit of Post-Training Q…

The Pachinko Allocation Machine (PAM) is a deep topic model that allows representing rich correlation structures among topics by a directed acyclic graph over topics. Because of the flexibility of the model, however, approximate inference…

Conformal prediction has emerged as a powerful tool for building prediction intervals that are valid in a distribution-free way. However, its evaluation may be computationally costly, especially in the high-dimensional setting where the…

Diffusion transformers have demonstrated remarkable capabilities in generating videos. However, their practical deployment is severely constrained by high memory usage and computational cost. Post-Training Quantization provides a practical…

Transfer learning, particularly approaches that combine multi-task learning with pre-trained contextualized embeddings and fine-tuning, have advanced the field of Natural Language Processing tremendously in recent years. In this paper we…

Mixed-precision quantization is a promising approach for compressing large language models under tight memory budgets. However, existing mixed-precision methods typically suffer from one of two limitations: they either rely on expensive…

This paper presents a machine learning-accelerated optimization framework for RF power amplifier design that reduces simulation requirements by 65% while maintaining $\pm0.4$ dBm accuracy for the majority of the modes. The proposed method…

Promptable foundation models, particularly Segment Anything Model (SAM), have emerged as a promising alternative to the traditional task-specific supervised learning for image segmentation. However, many evaluation studies have found that…

Improving the deployment efficiency of transformer-based language models has been challenging given their high computation and memory cost. While INT8 quantization has recently been shown to be effective in reducing both the memory cost and…

Large language models (LLMs) have demonstrated remarkable capabilities in various kinds of tasks, while the billion or even trillion parameters bring storage and efficiency bottlenecks for inference. Quantization, particularly…

Recently, large pre-trained neural language models have attained remarkable performance on many downstream natural language processing (NLP) applications via fine-tuning. In this paper, we target at how to further improve the token…

Segment Anything Model (SAM) has gained significant recognition in the field of semantic segmentation due to its versatile capabilities and impressive performance. Despite its success, SAM faces two primary limitations: (1) it relies…

Non-ideal measurement computed tomography (NICT) employs suboptimal imaging protocols to expand CT applications. However, the resulting trade-offs degrade image quality, limiting clinical acceptability. Although deep learning methods have…

We report on aggressive quantization strategies that greatly accelerate inference of Recurrent Neural Network Transducers (RNN-T). We use a 4 bit integer representation for both weights and activations and apply Quantization Aware Training…

Infrared small object detection urgently requires semi-supervised paradigms due to the high cost of annotation. However, existing methods like SAM face significant challenges of domain gaps, inability of encoding physical priors, and…

In this paper, we propose the Matting Anything Model (MAM), an efficient and versatile framework for estimating the alpha matte of any instance in an image with flexible and interactive visual or linguistic user prompt guidance. MAM offers…

While transformer-based pre-trained language models (PLMs) have dominated a number of NLP applications, these models are heavy to deploy and expensive to use. Therefore, effectively compressing large-scale PLMs becomes an increasingly…

In this work, we propose Asynchronous Perception Machine (APM), a computationally-efficient architecture for test-time-training (TTT). APM can process patches of an image one at a time in any order asymmetrically and still encode…

Inspired by the developments in quantum computing, building domain-specific classical hardware to solve computationally hard problems has received increasing attention. Here, by introducing systematic sparsification techniques, we…

Split Computing enables collaborative inference between edge devices and the cloud by partitioning a deep neural network into an edge-side head and a server-side tail, reducing latency and limiting exposure of raw input data. However,…

Quantization is a powerful tool for accelerating large language model (LLM) inference, but the accuracy-performance trade-offs across different formats remain unclear. In this paper, we conduct the most comprehensive empirical study to…