We present Muse, a text-to-image Transformer model that achieves state-of-the-art image generation performance while being significantly more efficient than diffusion or autoregressive models. Muse is trained on a masked modeling task in discrete token space: given the text embedding extracted from a pre-trained large language model (LLM), Muse is trained to predict randomly masked image tokens. Compared to pixel-space diffusion models, such as Imagen and DALL-E 2, Muse is significantly more efficient due to the use of discrete tokens and requiring fewer sampling iterations; compared to autoregressive models, such as Parti, Muse is more efficient due to the use of parallel decoding. The use of a pre-trained LLM enables fine-grained language understanding, translating to high-fidelity image generation and the understanding of visual concepts such as objects, their spatial relationships, pose, cardinality etc. Our 900M parameter model achieves a new SOTA on CC3M, with an FID score of 6.06. The Muse 3B parameter model achieves an FID of 7.88 on zero-shot COCO evaluation, along with a CLIP score of 0.32. Muse also directly enables a number of image editing applications without the need to fine-tune or invert the model: inpainting, outpainting, and mask-free editing. More results are available at https://muse-model.github.io

对于许多下游任务（例如，情感分析，关系检测等），脑电图（EEG）和语言已被广泛探索。研究这两个领域的多模式方法尚未得到很好的探索，即使近年来，多模式学习被认为比单峰对应物更强大。在这项研究中，我们希望探索脑电图与语言之间的关系和依赖性，即一个领域如何反映和代表另一个领域。为了研究表示级别的关系，我们引入了MTAM（一种多模式变压器对准模型），以观察两种模式之间的协调表示，因此采用了转换表示来进行下游应用。我们使用各种关系对齐的寻求对准技术，例如规范相关性分析和Wasserstein距离，作为转化低级语言的损失函数，并将EEG特征转化为高级转化的特征。在下游应用程序，情感分析和关系检测上，我们在两个数据集（Zuco和k-emocon）上实现了新的最新结果。我们的方法在K-Emocon的情感分析中获得了16.5％的F1得分提高，对Zuco的情感分析的26.6％，以及对Zuco的关系检测的31.1％。此外，我们通过以下方式提供对性能改进的解释：（1）可视化原始特征分布和变换的特征分布，显示对齐模块发现和编码脑电图与语言之间的关系的有效性； （2）可视化单词级别和句子级的脑电图对齐权重，显示不同语言语义和脑电图频率特征的影响； （3）可视化大脑地形图，以提供有关大脑区域中脑电图和语言反应的连通性的直观演示。

语言模型既展示了定量的改进，又展示了新的定性功能，随着规模的增加。尽管它们具有潜在的变革性影响，但这些新能力的特征却很差。为了为未来的研究提供信息，为破坏性的新模型能力做准备，并改善社会有害的效果，至关重要的是，我们必须了解目前和近乎未来的能力和语言模型的局限性。为了应对这一挑战，我们介绍了超越模仿游戏基准（Big Bench）。 Big Bench目前由204个任务组成，由132家机构的442位作者贡献。任务主题是多样的，从语言学，儿童发展，数学，常识性推理，生物学，物理学，社会偏见，软件开发等等。 Big-Bench专注于被认为超出当前语言模型的功能的任务。我们评估了OpenAI的GPT型号，Google内部密集变压器体系结构和大型基础上的开关稀疏变压器的行为，跨越了数百万到数十亿个参数。此外，一个人类专家评估者团队执行了所有任务，以提供强大的基准。研究结果包括：模型性能和校准都随规模改善，但绝对的术语（以及与评估者的性能相比）；在模型类中的性能非常相似，尽管带有稀疏性。逐渐和预测的任务通常涉及大量知识或记忆成分，而在临界规模上表现出“突破性”行为的任务通常涉及多个步骤或组成部分或脆性指标；社交偏见通常会随着含糊不清的环境而随着规模而增加，但这可以通过提示来改善。

数据增强是自然语言处理（NLP）模型的鲁棒性评估的重要组成部分，以及增强他们培训的数据的多样性。在本文中，我们呈现NL-Cogmenter，这是一种新的参与式Python的自然语言增强框架，它支持创建两个转换（对数据的修改）和过滤器（根据特定功能的数据拆分）。我们描述了框架和初始的117个变换和23个过滤器，用于各种自然语言任务。我们通过使用其几个转换来分析流行自然语言模型的鲁棒性来证明NL-Upmenter的功效。基础架构，Datacards和稳健性分析结果在NL-Augmenter存储库上公开可用（\ url {https://github.com/gem-benchmark/nl-augmenter}）。

我们展示了一个基于逻辑推理的新型对话管理方法的聊天栏。除了帧对话一系列响应生成任务，我们将对话作为协作推断过程，其中扬声器共享信息以实时地合成新知识。我们的Chatbot管道在三个广泛的阶段完成了这种建模。第一阶段将用户话语转换为符号谓词表示。然后，第二阶段与更大的知识库结合使用这种结构化表示来合成使用有效的图形匹配来扫描新谓词。在第三阶段和最后阶段，我们的机器人选择一个小的谓词子集并将它们转化为英语响应。这种方法为了解用户输入的潜在语义，灵活的主动措施以及与对话背景相干的响应。

我们总结了使用巨大的自动语音识别（ASR）模型的大量努力的结果，该模型使用包含大约一百万小时音频的大型，多样的未标记数据集进行了预训练。我们发现，即使对于拥有数万个小时的标记数据的非常大的任务，预训练，自我培训和扩大模型大小的组合也大大提高了数据效率。特别是，在具有34K小时标记数据的ASR任务上，通过微调80亿个参数预先训练的构象异构体模型，我们可以匹配最先进的（SOTA）性能（SOTA）的性能，只有3％的培训数据和通过完整的训练集可以显着改善SOTA。我们还报告了从使用大型预训练和自我训练的模型来完成一系列下游任务所获得的普遍利益，这些任务涵盖了广泛的语音域，并涵盖了多个数据集大小的大小，包括在许多人中获得SOTA性能公共基准。此外，我们利用预先训练的网络的学会表示，在非ASR任务上实现SOTA结果。

在少数射击域适应（FDA）中，针对目标域的分类器在源域（SD）（SD）中使用可访问的标记数据进行训练，而目标域（TD）中的标记数据很少。但是，数据通常包含当前时代的私人信息，例如分布在个人电话上的数据。因此，如果我们直接访问SD中的数据以训练目标域分类器（FDA方法要求），则将泄漏私人信息。在本文中，为了彻底防止SD中的隐私泄漏，我们考虑了一个非常具有挑战性的问题设置，必须使用很少的标签目标数据和训练有素的SD分类器对TD的分类器进行培训，并将其命名为几个示例的假设适应（FHA）。在FHA中，我们无法访问SD中的数据，因此，SD中的私人信息将得到很好的保护。为此，我们提出了一个目标定向的假设适应网络（TOHAN）来解决FHA问题，在该问题中，我们生成了高度兼容的未标记数据（即中间域），以帮助培训目标域分类器。 Tohan同时保持了两个深网，其中一个专注于学习中间域，而另一个则要照顾中间靶向分布的适应性和目标风险最小化。实验结果表明，Tohan的表现要优于竞争基线。

Large-scale distributed training requires significant communication bandwidth for gradient exchange that limits the scalability of multi-node training, and requires expensive high-bandwidth network infrastructure. The situation gets even worse with distributed training on mobile devices (federated learning), which suffers from higher latency, lower throughput, and intermittent poor connections. In this paper, we find 99.9% of the gradient exchange in distributed SGD are redundant, and propose Deep Gradient Compression (DGC) to greatly reduce the communication bandwidth. To preserve accuracy during this compression, DGC employs four methods: momentum correction, local gradient clipping, momentum factor masking, and warm-up training. We have applied Deep Gradient Compression to image classification, speech recognition, and language modeling with multiple datasets including Cifar10, ImageNet, Penn Treebank, and Librispeech Corpus. On these scenarios, Deep Gradient Compression achieves a gradient compression ratio from 270× to 600× without losing accuracy, cutting the gradient size of ResNet-50 from 97MB to 0.35MB, and for DeepSpeech from 488MB to 0.74MB. Deep gradient compression enables large-scale distributed training on inexpensive commodity 1Gbps Ethernet and facilitates distributed training on mobile. The code is available at: https://github.com/synxlin/ deep-gradient-compression.

State-of-the-art deep neural networks (DNNs) have hundreds of millions of connections and are both computationally and memory intensive, making them difficult to deploy on embedded systems with limited hardware resources and power budgets. While custom hardware helps the computation, fetching weights from DRAM is two orders of magnitude more expensive than ALU operations, and dominates the required power.Previously proposed 'Deep Compression' makes it possible to fit large DNNs (AlexNet and VGGNet) fully in on-chip SRAM. This compression is achieved by pruning the redundant connections and having multiple connections share the same weight. We propose an energy efficient inference engine (EIE) that performs inference on this compressed network model and accelerates the resulting sparse matrix-vector multiplication with weight sharing. Going from DRAM to SRAM gives EIE 120× energy saving; Exploiting sparsity saves 10×; Weight sharing gives 8×; Skipping zero activations from ReLU saves another 3×. Evaluated on nine DNN benchmarks, EIE is 189× and 13× faster when compared to CPU and GPU implementations of the same DNN without compression. EIE has a processing power of 102 GOPS/s working directly on a compressed network, corresponding to 3 TOPS/s on an uncompressed network, and processes FC layers of AlexNet at 1.88×10 4 frames/sec with a power dissipation of only 600mW. It is 24,000× and 3,400× more energy efficient than a CPU and GPU respectively. Compared with DaDianNao, EIE has 2.9×, 19× and 3× better throughput, energy efficiency and area efficiency.

Neural networks are both computationally intensive and memory intensive, making them difficult to deploy on embedded systems with limited hardware resources. To address this limitation, we introduce "deep compression", a three stage pipeline: pruning, trained quantization and Huffman coding, that work together to reduce the storage requirement of neural networks by 35× to 49× without affecting their accuracy. Our method first prunes the network by learning only the important connections. Next, we quantize the weights to enforce weight sharing, finally, we apply Huffman coding. After the first two steps we retrain the network to fine tune the remaining connections and the quantized centroids. Pruning, reduces the number of connections by 9× to 13×; Quantization then reduces the number of bits that represent each connection from 32 to 5. On the ImageNet dataset, our method reduced the storage required by AlexNet by 35×, from 240MB to 6.9MB, without loss of accuracy. Our method reduced the size of VGG-16 by 49× from 552MB to 11.3MB, again with no loss of accuracy. This allows fitting the model into on-chip SRAM cache rather than off-chip DRAM memory. Our compression method also facilitates the use of complex neural networks in mobile applications where application size and download bandwidth are constrained. Benchmarked on CPU, GPU and mobile GPU, compressed network has 3× to 4× layerwise speedup and 3× to 7× better energy efficiency.