Recent advances in 1-bit Large Language Models (LLMs), such as BitNet and BitNet b1.58, present a promising approach to enhancing the efficiency of LLMs in terms of speed and energy consumption. These developments also enable local LLM deployment across a broad range of devices. In this work, we introduce bitnet.cpp, a tailored software stack designed to unlock the full potential of 1-bit LLMs. Specifically, we develop a set of kernels to support fast and lossless inference of ternary BitNet b1.58 LLMs on CPUs. Extensive experiments demonstrate that bitnet.cpp achieves significant speedups, ranging from 2.37x to 6.17x on x86 CPUs and from 1.37x to 5.07x on ARM CPUs, across various model sizes. The code is available at https://github.com/microsoft/BitNet.

The astonishing successes of ML have raised growing concern for the fairness of modern methods when deployed in real world settings. However, studies on fairness have mostly focused on supervised ML, while unsupervised outlier detection (OD), with numerous applications in finance, security, etc., have attracted little attention. While a few studies proposed fairness-enhanced OD algorithms, they remain agnostic to the underlying driving mechanisms or sources of unfairness. Even within the supervised ML literature, there exists debate on whether unfairness stems solely from algorithmic biases (i.e. design choices) or from the biases encoded in the data on which they are trained. To close this gap, this work aims to shed light on the possible sources of unfairness in OD by auditing detection models under different data-centric factors. By injecting various known biases into the input data -- as pertain to sample size disparity, under-representation, feature measurement noise, and group membership obfuscation -- we find that the OD algorithms under the study all exhibit fairness pitfalls, although differing in which types of data bias they are more susceptible to. Most notable of our study is to demonstrate that OD algorithm bias is not merely a data bias problem. A key realization is that the data properties that emerge from bias injection could as well be organic -- as pertain to natural group differences w.r.t. sparsity, base rate, variance, and multi-modality. Either natural or biased, such data properties can give rise to unfairness as they interact with certain algorithmic design choices.

AI is revolutionizing MRI along the acquisition and processing chain. Advanced AI frameworks have been developed to apply AI in various successive tasks, such as image reconstruction, quantitative parameter map estimation, and image segmentation. Existing frameworks are often designed to perform tasks independently or are focused on specific models or datasets, limiting generalization. We introduce ATOMMIC, an open-source toolbox that streamlines AI applications for accelerated MRI reconstruction and analysis. ATOMMIC implements several tasks using DL networks and enables MultiTask Learning (MTL) to perform related tasks integrated, targeting generalization in the MRI domain. We first review the current state of AI frameworks for MRI through a comprehensive literature search and by parsing 12,479 GitHub repositories. We benchmark 25 DL models on eight publicly available datasets to present distinct applications of ATOMMIC on accelerated MRI reconstruction, image segmentation, quantitative parameter map estimation, and joint accelerated MRI reconstruction and image segmentation utilizing MTL. Our findings demonstrate that ATOMMIC is the only MTL framework with harmonized complex-valued and real-valued data support. Evaluations on single tasks show that physics-based models, which enforce data consistency by leveraging the physical properties of MRI, outperform other models in reconstructing highly accelerated acquisitions. Physics-based models that produce high reconstruction quality can accurately estimate quantitative parameter maps. When high-performing reconstruction models are combined with robust segmentation networks utilizing MTL, performance is improved in both tasks. ATOMMIC facilitates MRI reconstruction and analysis by standardizing workflows, enhancing data interoperability, integrating unique features like MTL, and effectively benchmarking DL models.

We learn rich natural sound representations by capitalizing on large amounts of unlabeled sound data collected in the wild. We leverage the natural synchronization between vision and sound to learn an acoustic representation using two-million unlabeled videos. Unlabeled video has the advantage that it can be economically acquired at massive scales, yet contains useful signals about natural sound. We propose a student-teacher training procedure which transfers discriminative visual knowledge from well established visual recognition models into the sound modality using unlabeled video as a bridge. Our sound representation yields significant performance improvements over the state-of-the-art results on standard benchmarks for acoustic scene/object classification. Visualizations suggest some high-level semantics automatically emerge in the sound network, even though it is trained without ground truth labels.

But in some cases, we cant get static frame because lighting can change, or some objects will be moved by someone, or always exist movement, etc. In such cases we are saving some number of frames and trying to figure out which of the pixels are the same for most of them, then this pixels becoming part of background_layer. Difference generally in how we get this background_layer and additional filtering that we use to make selection more accurate.

Adam is the super star optimization algorithm of Deep Learning. Optimization algorithms aim to find optimum weights, minimize error and maximize accuracy. We find partial derivative of total error with respect to each weight and use this calculation to update weights. This is common because it works slowly but surely. In 2015, Adam optimization algorithm is raised. The name of the algorithm refers to adaptive moment estimation.

We have developed an autonomous robot system that takes well-composed photographs of people at social events, such as weddings and conference receptions. In this article, we outline the overall architecture of the system and describe how the various components interrelate. We also describe our experiences deploying the robot photographer at a number of real-world events. The system is capable of operating in unaltered environments and has been deployed at a number of real-world events. This article gives an overview of the entire robot photographer system, and provides details of the architecture underlying the implementation.

From a computer science and artificial intelligence perspective, robotics often appears as a collection of disjoint, sometimes antagonistic subfields. The lack of a coherent and unified presentation of the field negatively affects teaching, especially to undergraduates. This article presents an alternative synthesis of the various subfields of AI robotics and shows how these traditional subfields fit into the whole. Finally, it presents a curriculum based on these ideas. An examination of the current robotics textbooks (McKerrow 1991; Arkin 1998; Dudek and Jenkin 2000; Murphy 2000; Niku 2001; Siegwart and Nourbakhsh 2004; Craig 2005; Choset et al. 2005) indicates that these subfields are traditional planning-based robotics, behavior-based robotics, probabilistic robotics, mobile robotics, and engineering robotics.