由于服务器客户的通信和设备计算的瓶颈，大多数研究联合学习的研究都集中在小型模型上。在这项工作中，我们利用各种技术来缓解这些瓶颈，以在联合学习的跨设备中训练更大的语言模型。借助部分模型培训，量化，有效的转移学习和沟通效率优化器的系统应用，我们能够培训$ 21 $ M的参数变压器和20.2美元的参数构象异构体，这些构象异构体与类似大小相同或更好的困惑LSTM具有$ \ sim10 \ times $ $较小的客户到服务器通信成本，比文献中常见的较小的LSTMS $ 11 \％$ $ $ $。

我们研究了在通信约束下的分布式平均值估计和优化问题。我们提出了一个相关的量化协议，该协议的误差保证中的主项取决于数据点的平均偏差，而不仅仅是它们的绝对范围。该设计不需要关于数据集的集中属性的任何先验知识，这是在以前的工作中获得这种依赖所必需的。我们表明，在分布式优化算法中应用提出的协议作为子规则会导致更好的收敛速率。我们还在轻度假设下证明了我们的方案的最佳性。实验结果表明，我们提出的算法在各种任务方面优于现有的平均估计协议。

联合学习是一种机器学习技术，可实现分散数据的培训。最近，由于对隐私和安全的焦点增加，联邦学习已成为一个活跃的研究领域。鉴于此，已开发和释放各种开源联合学习库。我们介绍FedJax，一个基于JAX的开源库，用于联合学习模拟，强调易于使用的研究。利用其简单的原语来实现联合学习算法，预先包装的数据集，模型和算法以及快速仿真速度，FedJax旨在使开发和评估联合算法更快，更容易研究研究人员。我们的基准结果表明，FedJax可用于在几分钟内与EMNIST数据集上的联合平均培训模型，并且堆栈溢出数据集在大约一个小时使用TPU的标准超参数。

We present X-Decoder, a generalized decoding model that can predict pixel-level segmentation and language tokens seamlessly. X-Decodert takes as input two types of queries: (i) generic non-semantic queries and (ii) semantic queries induced from text inputs, to decode different pixel-level and token-level outputs in the same semantic space. With such a novel design, X-Decoder is the first work that provides a unified way to support all types of image segmentation and a variety of vision-language (VL) tasks. Further, our design enables seamless interactions across tasks at different granularities and brings mutual benefits by learning a common and rich pixel-level visual-semantic understanding space, without any pseudo-labeling. After pretraining on a mixed set of a limited amount of segmentation data and millions of image-text pairs, X-Decoder exhibits strong transferability to a wide range of downstream tasks in both zero-shot and finetuning settings. Notably, it achieves (1) state-of-the-art results on open-vocabulary segmentation and referring segmentation on eight datasets; (2) better or competitive finetuned performance to other generalist and specialist models on segmentation and VL tasks; and (3) flexibility for efficient finetuning and novel task composition (e.g., referring captioning and image editing). Code, demo, video, and visualization are available at https://x-decoder-vl.github.io.

One of the main limitations of the commonly used Absolute Trajectory Error (ATE) is that it is highly sensitive to outliers. As a result, in the presence of just a few outliers, it often fails to reflect the varying accuracy as the inlier trajectory error or the number of outliers varies. In this work, we propose an alternative error metric for evaluating the accuracy of the reconstructed camera trajectory. Our metric, named Discernible Trajectory Error (DTE), is computed in four steps: (1) Shift the ground-truth and estimated trajectories such that both of their geometric medians are located at the origin. (2) Rotate the estimated trajectory such that it minimizes the sum of geodesic distances between the corresponding camera orientations. (3) Scale the estimated trajectory such that the median distance of the cameras to their geometric median is the same as that of the ground truth. (4) Compute the distances between the corresponding cameras, and obtain the DTE by taking the average of the mean and root-mean-square (RMS) distance. This metric is an attractive alternative to the ATE, in that it is capable of discerning the varying trajectory accuracy as the inlier trajectory error or the number of outliers varies. Using the similar idea, we also propose a novel rotation error metric, named Discernible Rotation Error (DRE), which has similar advantages to the DTE. Furthermore, we propose a simple yet effective method for calibrating the camera-to-marker rotation, which is needed for the computation of our metrics. Our methods are verified through extensive simulations.

Mix-up training approaches have proven to be effective in improving the generalization ability of Deep Neural Networks. Over the years, the research community expands mix-up methods into two directions, with extensive efforts to improve saliency-guided procedures but minimal focus on the arbitrary path, leaving the randomization domain unexplored. In this paper, inspired by the superior qualities of each direction over one another, we introduce a novel method that lies at the junction of the two routes. By combining the best elements of randomness and saliency utilization, our method balances speed, simplicity, and accuracy. We name our method R-Mix following the concept of "Random Mix-up". We demonstrate its effectiveness in generalization, weakly supervised object localization, calibration, and robustness to adversarial attacks. Finally, in order to address the question of whether there exists a better decision protocol, we train a Reinforcement Learning agent that decides the mix-up policies based on the classifier's performance, reducing dependency on human-designed objectives and hyperparameter tuning. Extensive experiments further show that the agent is capable of performing at the cutting-edge level, laying the foundation for a fully automatic mix-up. Our code is released at [https://github.com/minhlong94/Random-Mixup].

Natural language explanations promise to offer intuitively understandable explanations of a neural network's decision process in complex vision-language tasks, as pursued in recent VL-NLE models. While current models offer impressive performance on task accuracy and explanation plausibility, they suffer from a range of issues: Some models feature a modular design where the explanation generation module is poorly integrated with a separate module for task-answer prediction, employ backbone models trained on limited sets of tasks, or incorporate ad hoc solutions to increase performance on single datasets. We propose to evade these limitations by applying recent advances in large-scale multi-task pretraining of generative Transformer models to the problem of VL-NLE tasks. Our approach outperforms recent models by a large margin, with human annotators preferring the generated explanations over the ground truth in two out of three evaluated datasets. As a novel challenge in VL-NLE research, we propose the problem of multi-task VL-NLE and show that jointly training on multiple tasks can increase the explanation quality. We discuss the ethical implications of high-quality NLE generation and other issues in recent VL-NLE research.

While witnessing the noisy intermediate-scale quantum (NISQ) era and beyond, quantum federated learning (QFL) has recently become an emerging field of study. In QFL, each quantum computer or device locally trains its quantum neural network (QNN) with trainable gates, and communicates only these gate parameters over classical channels, without costly quantum communications. Towards enabling QFL under various channel conditions, in this article we develop a depth-controllable architecture of entangled slimmable quantum neural networks (eSQNNs), and propose an entangled slimmable QFL (eSQFL) that communicates the superposition-coded parameters of eS-QNNs. Compared to the existing depth-fixed QNNs, training the depth-controllable eSQNN architecture is more challenging due to high entanglement entropy and inter-depth interference, which are mitigated by introducing entanglement controlled universal (CU) gates and an inplace fidelity distillation (IPFD) regularizer penalizing inter-depth quantum state differences, respectively. Furthermore, we optimize the superposition coding power allocation by deriving and minimizing the convergence bound of eSQFL. In an image classification task, extensive simulations corroborate the effectiveness of eSQFL in terms of prediction accuracy, fidelity, and entropy compared to Vanilla QFL as well as under different channel conditions and various data distributions.

Our long term goal is to use image-based depth completion to quickly create 3D models from sparse point clouds, e.g. from SfM or SLAM. Much progress has been made in depth completion. However, most current works assume well distributed samples of known depth, e.g. Lidar or random uniform sampling, and perform poorly on uneven samples, such as from keypoints, due to the large unsampled regions. To address this problem, we extend CSPN with multiscale prediction and a dilated kernel, leading to much better completion of keypoint-sampled depth. We also show that a model trained on NYUv2 creates surprisingly good point clouds on ETH3D by completing sparse SfM points.

Multilayer perceptrons (MLPs) learn high frequencies slowly. Recent approaches encode features in spatial bins to improve speed of learning details, but at the cost of larger model size and loss of continuity. Instead, we propose to encode features in bins of Fourier features that are commonly used for positional encoding. We call these Quantized Fourier Features (QFF). As a naturally multiresolution and periodic representation, our experiments show that using QFF can result in smaller model size, faster training, and better quality outputs for several applications, including Neural Image Representations (NIR), Neural Radiance Field (NeRF) and Signed Distance Function (SDF) modeling. QFF are easy to code, fast to compute, and serve as a simple drop-in addition to many neural field representations.