We present Mu$^{2}$SLAM, a multilingual sequence-to-sequence model pre-trained jointly on unlabeled speech, unlabeled text and supervised data spanning Automatic Speech Recognition (ASR), Automatic Speech Translation (AST) and Machine Translation (MT), in over 100 languages. By leveraging a quantized representation of speech as a target, Mu$^{2}$SLAM trains the speech-text models with a sequence-to-sequence masked denoising objective similar to T5 on the decoder and a masked language modeling (MLM) objective on the encoder, for both unlabeled speech and text, while utilizing the supervised tasks to improve cross-lingual and cross-modal representation alignment within the model. On CoVoST AST, Mu$^{2}$SLAM establishes a new state-of-the-art for models trained on public datasets, improving on xx-en translation over the previous best by 1.9 BLEU points and on en-xx translation by 1.1 BLEU points. On Voxpopuli ASR, our model matches the performance of an mSLAM model fine-tuned with an RNN-T decoder, despite using a relatively weaker sequence-to-sequence architecture. On text understanding tasks, our model improves by more than 6\% over mSLAM on XNLI, getting closer to the performance of mT5 models of comparable capacity on XNLI and TydiQA, paving the way towards a single model for all speech and text understanding tasks.

This paper introduces the use of evolutionary algorithms for solving differential equations. The solution is obtained by optimizing a deep neural network whose loss function is defined by the residual terms from the differential equations. Recent studies have used stochastic gradient descent (SGD) variants to train these physics-informed neural networks (PINNs), but these methods can struggle to find accurate solutions due to optimization challenges. When solving differential equations, it is important to find the globally optimum parameters of the network, rather than just finding a solution that works well during training. SGD only searches along a single gradient direction, so it may not be the best approach for training PINNs with their accompanying complex optimization landscapes. In contrast, evolutionary algorithms perform a parallel exploration of different solutions in order to avoid getting stuck in local optima and can potentially find more accurate solutions. However, evolutionary algorithms can be slow, which can make them difficult to use in practice. To address this, we provide a set of five benchmark problems with associated performance metrics and baseline results to support the development of evolutionary algorithms for enhanced PINN training. As a baseline, we evaluate the performance and speed of using the widely adopted Covariance Matrix Adaptation Evolution Strategy (CMA-ES) for solving PINNs. We provide the loss and training time for CMA-ES run on TensorFlow, and CMA-ES and SGD run on JAX (with GPU acceleration) for the five benchmark problems. Our results show that JAX-accelerated evolutionary algorithms, particularly CMA-ES, can be a useful approach for solving differential equations. We hope that our work will support the exploration and development of alternative optimization algorithms for the complex task of optimizing PINNs.

We introduce the MAsked Generative VIdeo Transformer, MAGVIT, to tackle various video synthesis tasks with a single model. We introduce a 3D tokenizer to quantize a video into spatial-temporal visual tokens and propose an embedding method for masked video token modeling to facilitate multi-task learning. We conduct extensive experiments to demonstrate the quality, efficiency, and flexibility of MAGVIT. Our experiments show that (i) MAGVIT performs favorably against state-of-the-art approaches and establishes the best-published FVD on three video generation benchmarks, including the challenging Kinetics-600. (ii) MAGVIT outperforms existing methods in inference time by two orders of magnitude against diffusion models and by 60x against autoregressive models. (iii) A single MAGVIT model supports ten diverse generation tasks and generalizes across videos from different visual domains. The source code and trained models will be released to the public at https://magvit.cs.cmu.edu.

Large language models (LLMs) have been shown to be able to perform new tasks based on a few demonstrations or natural language instructions. While these capabilities have led to widespread adoption, most LLMs are developed by resource-rich organizations and are frequently kept from the public. As a step towards democratizing this powerful technology, we present BLOOM, a 176B-parameter open-access language model designed and built thanks to a collaboration of hundreds of researchers. BLOOM is a decoder-only Transformer language model that was trained on the ROOTS corpus, a dataset comprising hundreds of sources in 46 natural and 13 programming languages (59 in total). We find that BLOOM achieves competitive performance on a wide variety of benchmarks, with stronger results after undergoing multitask prompted finetuning. To facilitate future research and applications using LLMs, we publicly release our models and code under the Responsible AI License.

Video super-resolution is one of the most popular tasks on mobile devices, being widely used for an automatic improvement of low-bitrate and low-resolution video streams. While numerous solutions have been proposed for this problem, they are usually quite computationally demanding, demonstrating low FPS rates and power efficiency on mobile devices. In this Mobile AI challenge, we address this problem and propose the participants to design an end-to-end real-time video super-resolution solution for mobile NPUs optimized for low energy consumption. The participants were provided with the REDS training dataset containing video sequences for a 4X video upscaling task. The runtime and power efficiency of all models was evaluated on the powerful MediaTek Dimensity 9000 platform with a dedicated AI processing unit capable of accelerating floating-point and quantized neural networks. All proposed solutions are fully compatible with the above NPU, demonstrating an up to 500 FPS rate and 0.2 [Watt / 30 FPS] power consumption. A detailed description of all models developed in the challenge is provided in this paper.

High-quality traffic flow generation is the core module in building simulators for autonomous driving. However, the majority of available simulators are incapable of replicating traffic patterns that accurately reflect the various features of real-world data while also simulating human-like reactive responses to the tested autopilot driving strategies. Taking one step forward to addressing such a problem, we propose Realistic Interactive TrAffic flow (RITA) as an integrated component of existing driving simulators to provide high-quality traffic flow for the evaluation and optimization of the tested driving strategies. RITA is developed with fidelity, diversity, and controllability in consideration, and consists of two core modules called RITABackend and RITAKit. RITABackend is built to support vehicle-wise control and provide traffic generation models from real-world datasets, while RITAKit is developed with easy-to-use interfaces for controllable traffic generation via RITABackend. We demonstrate RITA's capacity to create diversified and high-fidelity traffic simulations in several highly interactive highway scenarios. The experimental findings demonstrate that our produced RITA traffic flows meet all three design goals, hence enhancing the completeness of driving strategy evaluation. Moreover, we showcase the possibility for further improvement of baseline strategies through online fine-tuning with RITA traffic flows.

Existing deep learning based HDRTV reconstruction methods assume one kind of tone mapping operators (TMOs) as the degradation procedure to synthesize SDRTV-HDRTV pairs for supervised training. In this paper, we argue that, although traditional TMOs exploit efficient dynamic range compression priors, they have several drawbacks on modeling the realistic degradation: information over-preservation, color bias and possible artifacts, making the trained reconstruction networks hard to generalize well to real-world cases. To solve this problem, we propose a learning-based data synthesis approach to learn the properties of real-world SDRTVs by integrating several tone mapping priors into both network structures and loss functions. In specific, we design a conditioned two-stream network with prior tone mapping results as a guidance to synthesize SDRTVs by both global and local transformations. To train the data synthesis network, we form a novel self-supervised content loss to constraint different aspects of the synthesized SDRTVs at regions with different brightness distributions and an adversarial loss to emphasize the details to be more realistic. To validate the effectiveness of our approach, we synthesize SDRTV-HDRTV pairs with our method and use them to train several HDRTV reconstruction networks. Then we collect two inference datasets containing both labeled and unlabeled real-world SDRTVs, respectively. Experimental results demonstrate that, the networks trained with our synthesized data generalize significantly better to these two real-world datasets than existing solutions.

Localizing anatomical landmarks are important tasks in medical image analysis. However, the landmarks to be localized often lack prominent visual features. Their locations are elusive and easily confused with the background, and thus precise localization highly depends on the context formed by their surrounding areas. In addition, the required precision is usually higher than segmentation and object detection tasks. Therefore, localization has its unique challenges different from segmentation or detection. In this paper, we propose a zoom-in attentive network (ZIAN) for anatomical landmark localization in ocular images. First, a coarse-to-fine, or "zoom-in" strategy is utilized to learn the contextualized features in different scales. Then, an attentive fusion module is adopted to aggregate multi-scale features, which consists of 1) a co-attention network with a multiple regions-of-interest (ROIs) scheme that learns complementary features from the multiple ROIs, 2) an attention-based fusion module which integrates the multi-ROIs features and non-ROI features. We evaluated ZIAN on two open challenge tasks, i.e., the fovea localization in fundus images and scleral spur localization in AS-OCT images. Experiments show that ZIAN achieves promising performances and outperforms state-of-the-art localization methods. The source code and trained models of ZIAN are available at https://github.com/leixiaofeng-astar/OMIA9-ZIAN.

由于其交易实体的伪匿名性质，比特币比任何其他金融资产都更频繁地进行非法活动。理想的检测模型有望实现（i）早期检测，（ii）良好的解释性和（iii）多功能性的所有三个特性。但是，现有的解决方案无法满足所有这些要求，因为它们中的大多数都在不满意的情况下严重依赖深度学习，并且仅用于对特定非法类型的回顾性分析。首先，我们提出资产转移路径，旨在描述解决早期特征。接下来，采用基于决策树的特征选择和分割策略，我们将整个观察期分为不同的段，并将每个段作为段向量进行编码。聚集了所有这些段向量后，我们获得了全局状态向量，本质上是描述整体意图的基本单元。最后，一个层次自我注意力预测指标可以实时预测给定地址的标签。生存模块告诉预测因子何时停止并提出状态序列，即意图。 ％依赖类型的选择策略和全球状态向量，我们的模型可用于检测具有强大解释性的各种非法活动。精心设计的预测指标和特定的损失功能可以进一步增强模型的预测速度和解释性。在三个现实世界数据集上进行的广泛实验表明，我们提出的算法优于最先进的方法。此外，其他案例研究证明我们的模型不仅可以解释现有的非法模式，还可以找到新的可疑字符。

机器人钉孔组装是机器人自动化研究中的重要任务。加强学习（RL）与深度神经网络（DNN）相结合，导致了这一领域的非凡成就。但是，在融合应用程序的独特环境和任务要求下，当前基于RL的方法几乎无法表现出色。因此，我们提出了一种新设计的基于RL的方法。此外，与其他方法不同，我们专注于DNN的结构而不是RL模型的创新。从RGB摄像机和力/扭矩（F/T）传感器中输入的数据，将其输入到多输入分支网络中，并且当前状态中的最佳动作是由网络输出的。所有训练和实验都是在现实的环境中进行的，从实验结果中，这种多传感器融合方法已显示在不确定和不稳定的环境中具有0.1mm精度的刚性钉钉组装任务中很好地工作。