最近，许多研究表明，通过使用多模式的训练预训练目标扩展BERT体系结构，在各种视觉语言多模式任务（例如图像字幕和视觉问题）上进行了令人印象深刻的表现。在这项工作中，我们探讨了医学领域中的一系列多模式表示任务，专门使用放射学图像和非结构化报告。我们提出了医学视觉语言学习者（MEDVILL），该语言学习者采用基于BERT的建筑与一种新型的多模式注意掩盖方案相结合，以最大程度地提高概括性能，以实现视力语言理解任务（诊断分类，医疗图像报告，医学视觉，医疗视觉效果问答）和视觉生成任务（放射学报告生成）。通过统计和严格评估四个下游任务的拟议模型，该模型具有三个X光摄影图像报告数据集（Mimic-CXR，Open-I和VQA-RAD），我们从经验上凭经验证明了MEDVILL的卓越下游任务，包括各种基准，包括任务 - 特定体系结构。源代码可公开可用：https：//github.com/supersupermoon/medvill

通过其高能量效率，加工存储器（PIM）阵列越来越多地用于卷积神经网络（CNN）推断。在基于PIM的CNN推断中，计算延迟和能量取决于CNN权重映射到PIM阵列的方式。最近的一项研究建议的移位和重复的内核（SDK）映射，其用一个并行窗口的单位重用输入特征映射，其与重复的内核卷积以并行获得多个输出元素。但是，现有的基于SDK的映射算法并不总是导致最小计算周期，因为它只将方形的并联窗口与整个通道映射。在本文中，我们介绍了一种名为可变窗口SDK（VW-SDK）的新型映射算法，其自适应地确定了对给定卷积层和PIM阵列的最小计算周期的并行窗口的形状。通过允许具有部分通道的矩形窗口，VW-SDK更有效地利用PIM阵列，从而进一步减少计算周期的数量。与512x512 PIM阵列和RESET-18的仿真显示，与现有的基于SDK的算法相比，VW-SDK将推理速度提高1.69倍。

Training agents via off-policy deep reinforcement learning (RL) requires a large memory, named replay memory, that stores past experiences used for learning. These experiences are sampled, uniformly or non-uniformly, to create the batches used for training. When calculating the loss function, off-policy algorithms assume that all samples are of the same importance. In this paper, we hypothesize that training can be enhanced by assigning different importance for each experience based on their temporal-difference (TD) error directly in the training objective. We propose a novel method that introduces a weighting factor for each experience when calculating the loss function at the learning stage. In addition to improving convergence speed when used with uniform sampling, the method can be combined with prioritization methods for non-uniform sampling. Combining the proposed method with prioritization methods improves sampling efficiency while increasing the performance of TD-based off-policy RL algorithms. The effectiveness of the proposed method is demonstrated by experiments in six environments of the OpenAI Gym suite. The experimental results demonstrate that the proposed method achieves a 33%~76% reduction of convergence speed in three environments and an 11% increase in returns and a 3%~10% increase in success rate for other three environments.

Neural fields, also known as coordinate-based or implicit neural representations, have shown a remarkable capability of representing, generating, and manipulating various forms of signals. For video representations, however, mapping pixel-wise coordinates to RGB colors has shown relatively low compression performance and slow convergence and inference speed. Frame-wise video representation, which maps a temporal coordinate to its entire frame, has recently emerged as an alternative method to represent videos, improving compression rates and encoding speed. While promising, it has still failed to reach the performance of state-of-the-art video compression algorithms. In this work, we propose FFNeRV, a novel method for incorporating flow information into frame-wise representations to exploit the temporal redundancy across the frames in videos inspired by the standard video codecs. Furthermore, we introduce a fully convolutional architecture, enabled by one-dimensional temporal grids, improving the continuity of spatial features. Experimental results show that FFNeRV yields the best performance for video compression and frame interpolation among the methods using frame-wise representations or neural fields. To reduce the model size even further, we devise a more compact convolutional architecture using the group and pointwise convolutions. With model compression techniques, including quantization-aware training and entropy coding, FFNeRV outperforms widely-used standard video codecs (H.264 and HEVC) and performs on par with state-of-the-art video compression algorithms.

Data compression is becoming critical for storing scientific data because many scientific applications need to store large amounts of data and post process this data for scientific discovery. Unlike image and video compression algorithms that limit errors to primary data, scientists require compression techniques that accurately preserve derived quantities of interest (QoIs). This paper presents a physics-informed compression technique implemented as an end-to-end, scalable, GPU-based pipeline for data compression that addresses this requirement. Our hybrid compression technique combines machine learning techniques and standard compression methods. Specifically, we combine an autoencoder, an error-bounded lossy compressor to provide guarantees on raw data error, and a constraint satisfaction post-processing step to preserve the QoIs within a minimal error (generally less than floating point error). The effectiveness of the data compression pipeline is demonstrated by compressing nuclear fusion simulation data generated by a large-scale fusion code, XGC, which produces hundreds of terabytes of data in a single day. Our approach works within the ADIOS framework and results in compression by a factor of more than 150 while requiring only a few percent of the computational resources necessary for generating the data, making the overall approach highly effective for practical scenarios.

Neural radiance fields (NeRF) have demonstrated the potential of coordinate-based neural representation (neural fields or implicit neural representation) in neural rendering. However, using a multi-layer perceptron (MLP) to represent a 3D scene or object requires enormous computational resources and time. There have been recent studies on how to reduce these computational inefficiencies by using additional data structures, such as grids or trees. Despite the promising performance, the explicit data structure necessitates a substantial amount of memory. In this work, we present a method to reduce the size without compromising the advantages of having additional data structures. In detail, we propose using the wavelet transform on grid-based neural fields. Grid-based neural fields are for fast convergence, and the wavelet transform, whose efficiency has been demonstrated in high-performance standard codecs, is to improve the parameter efficiency of grids. Furthermore, in order to achieve a higher sparsity of grid coefficients while maintaining reconstruction quality, we present a novel trainable masking approach. Experimental results demonstrate that non-spatial grid coefficients, such as wavelet coefficients, are capable of attaining a higher level of sparsity than spatial grid coefficients, resulting in a more compact representation. With our proposed mask and compression pipeline, we achieved state-of-the-art performance within a memory budget of 2 MB. Our code is available at https://github.com/daniel03c1/masked_wavelet_nerf.

A fundamental challenge to providing edge-AI services is the need for a machine learning (ML) model that achieves personalization (i.e., to individual clients) and generalization (i.e., to unseen data) properties concurrently. Existing techniques in federated learning (FL) have encountered a steep tradeoff between these objectives and impose large computational requirements on edge devices during training and inference. In this paper, we propose SplitGP, a new split learning solution that can simultaneously capture generalization and personalization capabilities for efficient inference across resource-constrained clients (e.g., mobile/IoT devices). Our key idea is to split the full ML model into client-side and server-side components, and impose different roles to them: the client-side model is trained to have strong personalization capability optimized to each client's main task, while the server-side model is trained to have strong generalization capability for handling all clients' out-of-distribution tasks. We analytically characterize the convergence behavior of SplitGP, revealing that all client models approach stationary points asymptotically. Further, we analyze the inference time in SplitGP and provide bounds for determining model split ratios. Experimental results show that SplitGP outperforms existing baselines by wide margins in inference time and test accuracy for varying amounts of out-of-distribution samples.

Fusion-in-Decoder (FiD) is a powerful retrieval-augmented language model that sets the state-of-the-art on many knowledge-intensive NLP tasks. However, FiD suffers from very expensive inference. We show that the majority of inference time results from memory bandwidth constraints in the decoder, and propose two simple changes to the FiD architecture to speed up inference by 7x. The faster decoder inference then allows for a much larger decoder. We denote FiD with the above modifications as FiDO, and show that it strongly improves performance over existing FiD models for a wide range of inference budgets. For example, FiDO-Large-XXL performs faster inference than FiD-Base and achieves better performance than FiD-Large.

When designing a new API for a large project, developers need to make smart design choices so that their code base can grow sustainably. To ensure that new API components are well designed, developers can learn from existing API components. However, the lack of standardized method for comparing API designs makes this learning process time-consuming and difficult. To address this gap we developed the API-Spector, to the best of our knowledge one of the first API-to-API specification recommendation engines. API-Spector retrieves relevant specification components written in OpenAPI (a widely adopted language used to describe web APIs). API-Spector presents several significant contributions, including: (1) novel methods of processing and extracting key information from OpenAPI specifications, (2) innovative feature extraction techniques that are optimized for the highly technical API specification domain, and (3) a novel log-linear probabilistic model that combines multiple signals to retrieve relevant and high quality OpenAPI specification components given a query specification. We evaluate API-Spector in both quantitative and qualitative tasks and achieve an overall of 91.7% recall@1 and 56.2% F1, which surpasses baseline performance by 15.4% in recall@1 and 3.2% in F1. Overall, API-Spector will allow developers to retrieve relevant OpenAPI specification components from a public or internal database in the early stages of the API development cycle, so that they can learn from existing established examples and potentially identify redundancies in their work. It provides the guidance developers need to accelerate development process and contribute thoughtfully designed APIs that promote code maintainability and quality.

We tackle the problem of generating long-term 3D human motion from multiple action labels. Two main previous approaches, such as action- and motion-conditioned methods, have limitations to solve this problem. The action-conditioned methods generate a sequence of motion from a single action. Hence, it cannot generate long-term motions composed of multiple actions and transitions between actions. Meanwhile, the motion-conditioned methods generate future motions from initial motion. The generated future motions only depend on the past, so they are not controllable by the user's desired actions. We present MultiAct, the first framework to generate long-term 3D human motion from multiple action labels. MultiAct takes account of both action and motion conditions with a unified recurrent generation system. It repetitively takes the previous motion and action label; then, it generates a smooth transition and the motion of the given action. As a result, MultiAct produces realistic long-term motion controlled by the given sequence of multiple action labels. The code will be released.