Related papers: DAMO: Deep Agile Mask Optimization for Full Chip S…
Over the past few years, as large language models have ushered in an era of intelligence emergence, there has been an intensified focus on scaling networks. Currently, many network architectures are designed manually, often resulting in…
Direct Preference Optimisation (DPO) has emerged as a powerful method for aligning Large Language Models (LLMs) with human preferences, offering a stable and efficient alternative to approaches that use Reinforcement learning via Human…
Modern very large-scale integration (VLSI) design requires the implementation of integrated circuits using electronic design automation (EDA) tools. Due to the complexity of EDA algorithms, the vast parameter space poses a huge challenge to…
Patients regularly continue assessment or treatment in other facilities than they began them in, receiving their previous imaging studies as a CD-ROM and requiring clinical staff at the new hospital to import these studies into their local…
The study of approximate matching in the Massively Parallel Computations (MPC) model has recently seen a burst of breakthroughs. Despite this progress, however, we still have a far more limited understanding of maximal matching which is one…
Large language models have achieved remarkable success, but their extensive parameter size necessitates substantial memory for training, thereby setting a high threshold. While the recently proposed low-memory optimization (LOMO) reduces…
Inference scaling empowers LLMs with unprecedented reasoning ability, with reinforcement learning as the core technique to elicit complex reasoning. However, key technical details of state-of-the-art reasoning LLMs are concealed (such as in…
The Dynamical Graph Grammar (DGG) formalism can describe complex system dynamics with graphs that are mapped into a master equation. An exact stochastic simulation algorithm may be used, but it is slow for large systems. To overcome this…
MIMO technology is one of the most significant advances in the past decade to increase channel capacity and has a great potential to improve network capacity for mesh networks. In a MIMO-based mesh network, the links outgoing from each node…
Vision-Language Models (VLMs) show promise in medical image analysis, yet their capacity for structured reasoning in complex domains like dermatology is often limited by data scarcity and the high computational cost of advanced training…
The Graphical Lasso (GLasso) algorithm is fast and widely used for estimating sparse precision matrices (Friedman et al., 2008). Its central role in the literature of high-dimensional covariance estimation rivals that of Lasso regression…
Advancements in chip design and manufacturing have enabled the processing of complex tasks such as deep learning and natural language processing, paving the way for the development of artificial general intelligence (AGI). AI, on the other…
In dynamically varying optical wireless communication (OWC) links, conventional quadrature amplitude modulation (QAM) in optical orthogonal frequency-division multiplexing (OFDM) requires frequent channel estimation and equalization,…
Many machine learning models, such as logistic regression~(LR) and support vector machine~(SVM), can be formulated as composite optimization problems. Recently, many distributed stochastic optimization~(DSO) methods have been proposed to…
Direct Preference Optimization (DPO) has shown effectiveness in aligning multi-modal large language models (MLLM) with human preferences. However, existing methods exhibit an imbalanced responsiveness to the data of varying hardness,…
DaCapo is a specialized deep learning library tailored to expedite the training and application of existing machine learning approaches on large, near-isotropic image data. In this correspondence, we introduce DaCapo's unique features…
Perspective distortion (PD) leads to substantial alterations in the shape, size, orientation, angles, and spatial relationships of visual elements in images. Accurately determining camera intrinsic and extrinsic parameters is challenging,…
This paper develops a new deep neural network optimized equalization framework for massive multiple input multiple output orthogonal frequency division multiplexing (MIMOOFDM) systems that employ low-resolution analog-to-digital converters…
Large Language Models (LLMs) fine-tuning techniques not only improve the adaptability to diverse downstream tasks, but also mitigate adverse effects of model quantization. Despite this, conventional quantization suffers from its structural…
Simultaneous Localization and Mapping (SLAM) is considered an ever-evolving problem due to its usage in many applications. Evaluation of SLAM is done typically using publicly available datasets which are increasing in number and the level…