基础模型正在成为主要的深度学习技术。由于模型参数和训练数据集的大规模，预处理基础模型始终耗时。除了计算密集型外，培训过程还非常密集和沟通密集。这些功能使得需要应用3D并行性，该平行性整合数据并行性，管道模型并行性和张量模型并行性，以实现高训练效率。为了实现这一目标，开发了一些自定义软件框架，例如Megatron-LM和DeepSpeed。但是，当前的3D平行框架仍然符合两个问题：i）它们对模型开发人员不透明，这些开发人员需要手动修改模型以并行化培训。 ii）它们对计算，GPU存储器和网络带宽的利用不足。我们提出了Merak，这是一个自动化的3D并行性深度学习培训框架，并具有高度资源利用。 Merak会自动使用自动模型分区仪部署，该分区仪在模型的代理表示上使用图形sharding算法。 Merak还提出了非侵入性的API，用于通过最小的代码修改来扩展基础模型培训。此外，我们在Merak设计了高性能的3D平行运行时引擎。它使用多种技术来利用可用的培训资源，包括移动的关键路径管道时间表，该计划带来了更高的计算利用率，阶段感知的重新计算，可利用空闲工作者的记忆以及子额定张量的模型并行性，这些模型并联与通信和计算重叠。 64 GPU的实验显示，Merak可以加快在最新的3D平行性框架上，具有1.5、2.5、8.3和20亿的模型框架，最高可达1.42x，1.39x，1.43x和1.61 x分别。

分布式随机梯度下降（SGD）方法已广泛应用于大型深度学习，梯度集体方法至关重要，以确保分布式深度学习系统的培训可扩展性。已广泛采用分布式SGD过程广泛采用诸如解释的集体通信，以减少通信时间。但是，allreduce会引发大带宽资源，而在许多情况下大多数梯度稀疏，因为许多梯度值是零，并且应该有效地压缩以用于节省带宽。为了减少稀疏梯度通信开销，我们提出了一种稀疏的剪影减速器（S2减速器），这是一种具有收敛保证的新型草图的稀疏梯度聚合方法。 S2减速机仅通过Count-Sketch和Bitmap压缩非零梯度来降低通信成本，并实现有效的已有SGD培训的有效恢复运算符。我们在五种培训模型中对四种最先进的方法进行广泛的评估。我们的结果表明，S2减速机收敛到相同的准确性，降低了81 \％稀疏通信开销，与最先进的方法相比，实现了1.8 $ \ times $ Speedup。

As natural language processing (NLP) for gender bias becomes a significant interdisciplinary topic, the prevalent data-driven techniques such as large-scale language models suffer from data inadequacy and biased corpus, especially for languages with insufficient resources such as Chinese. To this end, we propose a Chinese cOrpus foR Gender bIas Probing and Mitigation CORGI-PM, which contains 32.9k sentences with high-quality labels derived by following an annotation scheme specifically developed for gender bias in the Chinese context. Moreover, we address three challenges for automatic textual gender bias mitigation, which requires the models to detect, classify, and mitigate textual gender bias. We also conduct experiments with state-of-the-art language models to provide baselines. To our best knowledge, CORGI-PM is the first sentence-level Chinese corpus for gender bias probing and mitigation.

We present Second Thought, a new learning paradigm that enables language models (LMs) to re-align with human values. By modeling the chain-of-edits between value-unaligned and value-aligned text, with LM fine-tuning and additional refinement through reinforcement learning, Second Thought not only achieves superior performance in three value alignment benchmark datasets but also shows strong human-value transfer learning ability in few-shot scenarios. The generated editing steps also offer better interpretability and ease for interactive error correction. Extensive human evaluations further confirm its effectiveness.

Three-dimensional (3D) ultrasound imaging technique has been applied for scoliosis assessment, but current assessment method only uses coronal projection image and cannot illustrate the 3D deformity and vertebra rotation. The vertebra detection is essential to reveal 3D spine information, but the detection task is challenging due to complex data and limited annotations. We propose VertMatch, a two-step framework to detect vertebral structures in 3D ultrasound volume by utilizing unlabeled data in semi-supervised manner. The first step is to detect the possible positions of structures on transverse slice globally, and then the local patches are cropped based on detected positions. The second step is to distinguish whether the patches contain real vertebral structures and screen the predicted positions from the first step. VertMatch develops three novel components for semi-supervised learning: for position detection in the first step, (1) anatomical prior is used to screen pseudo labels generated from confidence threshold method; (2) multi-slice consistency is used to utilize more unlabeled data by inputting multiple adjacent slices; (3) for patch identification in the second step, the categories are rebalanced in each batch to solve imbalance problem. Experimental results demonstrate that VertMatch can detect vertebra accurately in ultrasound volume and outperforms state-of-the-art methods. VertMatch is also validated in clinical application on forty ultrasound scans, and it can be a promising approach for 3D assessment of scoliosis.

To reproduce the success of text-to-image (T2I) generation, recent works in text-to-video (T2V) generation employ large-scale text-video dataset for fine-tuning. However, such paradigm is computationally expensive. Humans have the amazing ability to learn new visual concepts from just one single exemplar. We hereby study a new T2V generation problem$\unicode{x2014}$One-Shot Video Generation, where only a single text-video pair is presented for training an open-domain T2V generator. Intuitively, we propose to adapt the T2I diffusion model pretrained on massive image data for T2V generation. We make two key observations: 1) T2I models are able to generate images that align well with the verb terms; 2) extending T2I models to generate multiple images concurrently exhibits surprisingly good content consistency. To further learn continuous motion, we propose Tune-A-Video with a tailored Sparse-Causal Attention, which generates videos from text prompts via an efficient one-shot tuning of pretrained T2I diffusion models. Tune-A-Video is capable of producing temporally-coherent videos over various applications such as change of subject or background, attribute editing, style transfer, demonstrating the versatility and effectiveness of our method.

We introduce \textsc{PoliteRewrite} -- a dataset for polite language rewrite which is a novel sentence rewrite task. Compared with previous text style transfer tasks that can be mostly addressed by slight token- or phrase-level edits, polite language rewrite requires deep understanding and extensive sentence-level edits over an offensive and impolite sentence to deliver the same message euphemistically and politely, which is more challenging -- not only for NLP models but also for human annotators to rewrite with effort. To alleviate the human effort for efficient annotation, we first propose a novel annotation paradigm by a collaboration of human annotators and GPT-3.5 to annotate \textsc{PoliteRewrite}. The released dataset has 10K polite sentence rewrites annotated collaboratively by GPT-3.5 and human, which can be used as gold standard for training, validation and test; and 100K high-quality polite sentence rewrites by GPT-3.5 without human review. We wish this work (The dataset (10K+100K) will be released soon) could contribute to the research on more challenging sentence rewrite, and provoke more thought in future on resource annotation paradigm with the help of the large-scaled pretrained models.

Summary quality assessment metrics have two categories: reference-based and reference-free. Reference-based metrics are theoretically more accurate but are limited by the availability and quality of the human-written references, which are both difficulty to ensure. This inspires the development of reference-free metrics, which are independent from human-written references, in the past few years. However, existing reference-free metrics cannot be both zero-shot and accurate. In this paper, we propose a zero-shot but accurate reference-free approach in a sneaky way: feeding documents, based upon which summaries generated, as references into reference-based metrics. Experimental results show that this zero-shot approach can give us the best-performing reference-free metrics on nearly all aspects on several recently-released datasets, even beating reference-free metrics specifically trained for this task sometimes. We further investigate what reference-based metrics can benefit from such repurposing and whether our additional tweaks help.

Photorealistic style transfer aims to transfer the artistic style of an image onto an input image or video while keeping photorealism. In this paper, we think it's the summary statistics matching scheme in existing algorithms that leads to unrealistic stylization. To avoid employing the popular Gram loss, we propose a self-supervised style transfer framework, which contains a style removal part and a style restoration part. The style removal network removes the original image styles, and the style restoration network recovers image styles in a supervised manner. Meanwhile, to address the problems in current feature transformation methods, we propose decoupled instance normalization to decompose feature transformation into style whitening and restylization. It works quite well in ColoristaNet and can transfer image styles efficiently while keeping photorealism. To ensure temporal coherency, we also incorporate optical flow methods and ConvLSTM to embed contextual information. Experiments demonstrates that ColoristaNet can achieve better stylization effects when compared with state-of-the-art algorithms.

The success of deep learning heavily relies on large-scale data with comprehensive labels, which is more expensive and time-consuming to fetch in 3D compared to 2D images or natural languages. This promotes the potential of utilizing models pretrained with data more than 3D as teachers for cross-modal knowledge transferring. In this paper, we revisit masked modeling in a unified fashion of knowledge distillation, and we show that foundational Transformers pretrained with 2D images or natural languages can help self-supervised 3D representation learning through training Autoencoders as Cross-Modal Teachers (ACT). The pretrained Transformers are transferred as cross-modal 3D teachers using discrete variational autoencoding self-supervision, during which the Transformers are frozen with prompt tuning for better knowledge inheritance. The latent features encoded by the 3D teachers are used as the target of masked point modeling, wherein the dark knowledge is distilled to the 3D Transformer students as foundational geometry understanding. Our ACT pretrained 3D learner achieves state-of-the-art generalization capacity across various downstream benchmarks, e.g., 88.21% overall accuracy on ScanObjectNN. Codes will be released at https://github.com/RunpeiDong/ACT.