了解视频的时间动态是学习更好的视频表示的重要方面。最近，由于其能力捕获了输入序列的长期依赖性，因此对基于变压器的架构设计进行了广泛的探索。但是，我们发现这些视频变压器仍然有偏见地学习空间动力学而不是时间动力学，而伪造的虚假相关性对于它们的性能至关重要。根据观察结果，我们设计了简单而有效的自我监督任务，以便视频模型更好地学习时间动态。具体而言，对于借鉴空间偏见，我们的方法将视频框架的时间顺序作为额外的自我设计，并强制执行随机洗牌的框架以具有低信心的输出。此外，我们的方法还学习了连续帧之间视频令牌的时间流动方向，以增强与时间动力学的相关性。在各种视频动作识别任务下，我们证明了我们的方法的有效性及其与最先进的视频变压器的兼容性。

最近的自我监督学习（SSL）方法在从未标记的图像中学习视觉表示方面显示出令人印象深刻的结果。本文旨在通过利用基础神经网络的建筑优势进一步提高其性能，因为SSL的当前最新视觉借口任务不享受好处，即它们是架构 - 敏捷的。特别是，我们专注于视觉变形金刚（VIT），这些变压器最近引起了人们的关注，作为更好的建筑选择，通常优于各种视觉任务的卷积网络。 VIT的独特特征在于，它从图像中采取了一系列不交联补丁，并在内部处理补丁级表示。受此启发的启发，我们设计了一个简单而有效的视觉借口任务，创造了自我绘制，以学习更好的补丁级表示。要具体而言，我们对每个贴片及其邻居的不变性执行，即每个贴片都将相似的相邻贴片视为正样品。因此，用自我绘制的培训可以学习斑块之间更有意义的关系（不使用人类通知的标签），这可能是有益的，特别是对密集预测类型的下游任务。尽管它很简单，但我们证明了它可以显着提高现有SSL方法的性能，包括对象检测和语义分割。具体而言，SelfPatch通过在可可对象检测上实现+1.3 AP，在COCO实例段中+1.2 AP显着改善了最新的自我监督的VIT，Dino和+2.9 MIOU在ADE20K语义段中。

半监督学习（SSL）是规避建立高性能模型的昂贵标签成本的最有前途的范例之一。大多数现有的SSL方法常规假定标记和未标记的数据是从相同（类）分布中绘制的。但是，在实践中，未标记的数据可能包括课外样本；那些不能从标签数据中的封闭类中的单热编码标签，即未标记的数据是开放设置。在本文中，我们介绍了Opencos，这是一种基于最新的自我监督视觉表示学习框架来处理这种现实的半监督学习方案。具体而言，我们首先观察到，可以通过自我监督的对比度学习有效地识别开放式未标记数据集中的类外样本。然后，Opencos利用此信息来克服现有的最新半监督方法中的故障模式，通过利用一式旋转伪标签和软标签来为已识别的识别和外部未标记的标签数据分别。我们广泛的实验结果表明了Opencos的有效性，可以修复最新的半监督方法，适合涉及开放式无标记数据的各种情况。

Dataset distillation has emerged as a prominent technique to improve data efficiency when training machine learning models. It encapsulates the knowledge from a large dataset into a smaller synthetic dataset. A model trained on this smaller distilled dataset can attain comparable performance to a model trained on the original training dataset. However, the existing dataset distillation techniques mainly aim at achieving the best trade-off between resource usage efficiency and model utility. The security risks stemming from them have not been explored. This study performs the first backdoor attack against the models trained on the data distilled by dataset distillation models in the image domain. Concretely, we inject triggers into the synthetic data during the distillation procedure rather than during the model training stage, where all previous attacks are performed. We propose two types of backdoor attacks, namely NAIVEATTACK and DOORPING. NAIVEATTACK simply adds triggers to the raw data at the initial distillation phase, while DOORPING iteratively updates the triggers during the entire distillation procedure. We conduct extensive evaluations on multiple datasets, architectures, and dataset distillation techniques. Empirical evaluation shows that NAIVEATTACK achieves decent attack success rate (ASR) scores in some cases, while DOORPING reaches higher ASR scores (close to 1.0) in all cases. Furthermore, we conduct a comprehensive ablation study to analyze the factors that may affect the attack performance. Finally, we evaluate multiple defense mechanisms against our backdoor attacks and show that our attacks can practically circumvent these defense mechanisms.

According to the rapid development of drone technologies, drones are widely used in many applications including military domains. In this paper, a novel situation-aware DRL- based autonomous nonlinear drone mobility control algorithm in cyber-physical loitering munition applications. On the battlefield, the design of DRL-based autonomous control algorithm is not straightforward because real-world data gathering is generally not available. Therefore, the approach in this paper is that cyber-physical virtual environment is constructed with Unity environment. Based on the virtual cyber-physical battlefield scenarios, a DRL-based automated nonlinear drone mobility control algorithm can be designed, evaluated, and visualized. Moreover, many obstacles exist which is harmful for linear trajectory control in real-world battlefield scenarios. Thus, our proposed autonomous nonlinear drone mobility control algorithm utilizes situation-aware components those are implemented with a Raycast function in Unity virtual scenarios. Based on the gathered situation-aware information, the drone can autonomously and nonlinearly adjust its trajectory during flight. Therefore, this approach is obviously beneficial for avoiding obstacles in obstacle-deployed battlefields. Our visualization-based performance evaluation shows that the proposed algorithm is superior from the other linear mobility control algorithms.

Multivariate time series forecasting with hierarchical structure is pervasive in real-world applications, demanding not only predicting each level of the hierarchy, but also reconciling all forecasts to ensure coherency, i.e., the forecasts should satisfy the hierarchical aggregation constraints. Moreover, the disparities of statistical characteristics between levels can be huge, worsened by non-Gaussian distributions and non-linear correlations. To this extent, we propose a novel end-to-end hierarchical time series forecasting model, based on conditioned normalizing flow-based autoregressive transformer reconciliation, to represent complex data distribution while simultaneously reconciling the forecasts to ensure coherency. Unlike other state-of-the-art methods, we achieve the forecasting and reconciliation simultaneously without requiring any explicit post-processing step. In addition, by harnessing the power of deep model, we do not rely on any assumption such as unbiased estimates or Gaussian distribution. Our evaluation experiments are conducted on four real-world hierarchical datasets from different industrial domains (three public ones and a dataset from the application servers of Alipay's data center) and the preliminary results demonstrate efficacy of our proposed method.

Large language models (LLMs) have demonstrated impressive capabilities in natural language understanding and generation, but the quality bar for medical and clinical applications is high. Today, attempts to assess models' clinical knowledge typically rely on automated evaluations on limited benchmarks. There is no standard to evaluate model predictions and reasoning across a breadth of tasks. To address this, we present MultiMedQA, a benchmark combining six existing open question answering datasets spanning professional medical exams, research, and consumer queries; and HealthSearchQA, a new free-response dataset of medical questions searched online. We propose a framework for human evaluation of model answers along multiple axes including factuality, precision, possible harm, and bias. In addition, we evaluate PaLM (a 540-billion parameter LLM) and its instruction-tuned variant, Flan-PaLM, on MultiMedQA. Using a combination of prompting strategies, Flan-PaLM achieves state-of-the-art accuracy on every MultiMedQA multiple-choice dataset (MedQA, MedMCQA, PubMedQA, MMLU clinical topics), including 67.6% accuracy on MedQA (US Medical License Exam questions), surpassing prior state-of-the-art by over 17%. However, human evaluation reveals key gaps in Flan-PaLM responses. To resolve this we introduce instruction prompt tuning, a parameter-efficient approach for aligning LLMs to new domains using a few exemplars. The resulting model, Med-PaLM, performs encouragingly, but remains inferior to clinicians. We show that comprehension, recall of knowledge, and medical reasoning improve with model scale and instruction prompt tuning, suggesting the potential utility of LLMs in medicine. Our human evaluations reveal important limitations of today's models, reinforcing the importance of both evaluation frameworks and method development in creating safe, helpful LLM models for clinical applications.

Vision Transformers have shown great promise recently for many vision tasks due to the insightful architecture design and attention mechanism. By revisiting the self-attention responses in Transformers, we empirically observe two interesting issues. First, Vision Transformers present a queryirrelevant behavior at deep layers, where the attention maps exhibit nearly consistent contexts in global scope, regardless of the query patch position (also head-irrelevant). Second, the attention maps are intrinsically sparse, few tokens dominate the attention weights; introducing the knowledge from ConvNets would largely smooth the attention and enhance the performance. Motivated by above observations, we generalize self-attention formulation to abstract a queryirrelevant global context directly and further integrate the global context into convolutions. The resulting model, a Fully Convolutional Vision Transformer (i.e., FCViT), purely consists of convolutional layers and firmly inherits the merits of both attention mechanism and convolutions, including dynamic property, weight sharing, and short- and long-range feature modeling, etc. Experimental results demonstrate the effectiveness of FCViT. With less than 14M parameters, our FCViT-S12 outperforms related work ResT-Lite by 3.7% top1 accuracy on ImageNet-1K. When scaling FCViT to larger models, we still perform better than previous state-of-the-art ConvNeXt with even fewer parameters. FCViT-based models also demonstrate promising transferability to downstream tasks, like object detection, instance segmentation, and semantic segmentation. Codes and models are made available at: https://github.com/ma-xu/FCViT.

Language models (LMs) have demonstrated remarkable performance on downstream tasks, using in-context exemplars or human instructions. Recent works have shown that chain-of-thought (CoT) prompting can elicit models to solve complex reasoning tasks, step-by-step. However, the efficacy of prompt-based CoT methods is restricted to very large LMs such as GPT-3 (175B), thus limiting deployability. In this paper, we revisit the fine-tuning approach to enable complex reasoning in smaller LMs, optimized to efficiently perform a specific task. We propose Fine-tune-CoT, a method that leverages the capabilities of very large LMs to generate reasoning samples and teach smaller models via fine-tuning. We evaluate our method on publicly available LMs across a wide range of complex tasks and model sizes. We find that Fine-tune-CoT enables substantial reasoning capability in small models, whereas previous prompt-based baselines exhibit near-random performance. Student models can even outperform the teacher in some tasks while reducing model size requirements by several orders of magnitude. We conduct extensive ablations and sample studies to understand the reasoning capabilities of student models. We also identify several important nuances that have been overlooked in concurrent fine-tuning works on CoT and address them in our analysis.

In recent years, vision-centric perception has flourished in various autonomous driving tasks, including 3D detection, semantic map construction, motion forecasting, and depth estimation. Nevertheless, the latency of vision-centric approaches is too high for practical deployment (e.g., most camera-based 3D detectors have a runtime greater than 300ms). To bridge the gap between ideal research and real-world applications, it is necessary to quantify the trade-off between performance and efficiency. Traditionally, autonomous-driving perception benchmarks perform the offline evaluation, neglecting the inference time delay. To mitigate the problem, we propose the Autonomous-driving StreAming Perception (ASAP) benchmark, which is the first benchmark to evaluate the online performance of vision-centric perception in autonomous driving. On the basis of the 2Hz annotated nuScenes dataset, we first propose an annotation-extending pipeline to generate high-frame-rate labels for the 12Hz raw images. Referring to the practical deployment, the Streaming Perception Under constRained-computation (SPUR) evaluation protocol is further constructed, where the 12Hz inputs are utilized for streaming evaluation under the constraints of different computational resources. In the ASAP benchmark, comprehensive experiment results reveal that the model rank alters under different constraints, suggesting that the model latency and computation budget should be considered as design choices to optimize the practical deployment. To facilitate further research, we establish baselines for camera-based streaming 3D detection, which consistently enhance the streaming performance across various hardware. ASAP project page: https://github.com/JeffWang987/ASAP.