社交媒体帖子包含有关医疗条件和与健康相关行为的潜在有价值的信息。生物重建VII任务3专注于通过识别推文中的药物和膳食补充剂的提及来挖掘这些信息。我们通过精细调整多个BERT样式语言模型来执行此任务以执行令牌级分类，并将它们组合成集合以生成最终预测。我们最好的系统由五个Megatron-Bert-345M型号组成，在看不见的测试数据上实现了0.764的严格F1得分。

生物重建VII Track-2挑战包括命名实体识别，实体链接（或实体 - 归一化），主题索引任务 - 与实体和主题限制为这项挑战的化学品。命名实体识别是一个完善的问题，我们通过基于Bert的生物群体模型实现了我们的最佳性能。我们将基于BERT的方法扩展到实体链接任务。在预先预订Biobert的第二阶段，通过称为自对准预先训练（SAP）的度量学习损失策略，我们将基于其SAP-Biobert Word Embeddings之间的余弦相似性链接实体。尽管我们的命名实体识别实验取得了成功，但我们发现化学指数任务一般更具挑战性。除了传统的NER方法之外，我们还尝试使用基于新颖的文本或“提示”方法的命名实体识别和实体链接，该方法使用生成语言模型，例如T5和GPT。我们通过这种新方法实现了令人鼓舞的结果。

在Bircocrive VII的Track-1中，要求参与者识别药物/化学品和蛋白质之间的相互作用。提供每个药物/化学和蛋白质的内部名称实体注释，必须自动预测14个不同的相互作用中的一种。对于此关系提取任务，我们尝试两种基于BERT的句子分类方法，以及使用T5模型的更新文本到文本方法。我们发现基于BERT的模型一般表现更好，我们的生物综太基模型实现了所有指标的最高分，实现了0.74 F1得分。虽然我们的小说T5文本到文本方法没有表现出基于BERT的大多数模型，但它表现出在类似数据上培训的那些，呈现出有希望的结果，实现0.65 F1得分。我们认为，与关系提取的文本文本方法有一些竞争优势，并且有很多研究进步的空间。

Cohn and Umans proposed a framework for developing fast matrix multiplication algorithms based on the embedding computation in certain groups algebras. In subsequent work with Kleinberg and Szegedy, they connected this to the search for combinatorial objects called strong uniquely solvable puzzles (strong USPs). We begin a systematic computer-aided search for these objects. We develop and implement constraint-based algorithms build on reductions to $\mathrm{SAT}$ and $\mathrm{IP}$ to verify that puzzles are strong USPs, and to search for large strong USPs. We produce tight bounds on the maximum size of a strong USP for width $k \le 5$, construct puzzles of small width that are larger than previous work, and improve the upper bounds on strong USP size for $k \le 12$. Although our work only deals with puzzles of small-constant width, the strong USPs we find imply matrix multiplication algorithms that run in $O(n^\omega)$ time with exponent $\omega \le 2.66$. While our algorithms do not beat the fastest algorithms, our work provides evidence and, perhaps, a path to finding families of strong USPs that imply matrix multiplication algorithms that are more efficient than those currently known.

Recent years have seen a proliferation of research on adversarial machine learning. Numerous papers demonstrate powerful algorithmic attacks against a wide variety of machine learning (ML) models, and numerous other papers propose defenses that can withstand most attacks. However, abundant real-world evidence suggests that actual attackers use simple tactics to subvert ML-driven systems, and as a result security practitioners have not prioritized adversarial ML defenses. Motivated by the apparent gap between researchers and practitioners, this position paper aims to bridge the two domains. We first present three real-world case studies from which we can glean practical insights unknown or neglected in research. Next we analyze all adversarial ML papers recently published in top security conferences, highlighting positive trends and blind spots. Finally, we state positions on precise and cost-driven threat modeling, collaboration between industry and academia, and reproducible research. We believe that our positions, if adopted, will increase the real-world impact of future endeavours in adversarial ML, bringing both researchers and practitioners closer to their shared goal of improving the security of ML systems.

Data deprivation, or the lack of easily available and actionable information on the well-being of individuals, is a significant challenge for the developing world and an impediment to the design and operationalization of policies intended to alleviate poverty. In this paper we explore the suitability of data derived from OpenStreetMap to proxy for the location of two crucial public services: schools and health clinics. Thanks to the efforts of thousands of digital humanitarians, online mapping repositories such as OpenStreetMap contain millions of records on buildings and other structures, delineating both their location and often their use. Unfortunately much of this data is locked in complex, unstructured text rendering it seemingly unsuitable for classifying schools or clinics. We apply a scalable, unsupervised learning method to unlabeled OpenStreetMap building data to extract the location of schools and health clinics in ten countries in Africa. We find the topic modeling approach greatly improves performance versus reliance on structured keys alone. We validate our results by comparing schools and clinics identified by our OSM method versus those identified by the WHO, and describe OSM coverage gaps more broadly.

Light guide plates are essential optical components widely used in a diverse range of applications ranging from medical lighting fixtures to back-lit TV displays. In this work, we introduce a fully-integrated, high-throughput, high-performance deep learning-driven workflow for light guide plate surface visual quality inspection (VQI) tailored for real-world manufacturing environments. To enable automated VQI on the edge computing within the fully-integrated VQI system, a highly compact deep anti-aliased attention condenser neural network (which we name LightDefectNet) tailored specifically for light guide plate surface defect detection in resource-constrained scenarios was created via machine-driven design exploration with computational and "best-practices" constraints as well as L_1 paired classification discrepancy loss. Experiments show that LightDetectNet achieves a detection accuracy of ~98.2% on the LGPSDD benchmark while having just 770K parameters (~33X and ~6.9X lower than ResNet-50 and EfficientNet-B0, respectively) and ~93M FLOPs (~88X and ~8.4X lower than ResNet-50 and EfficientNet-B0, respectively) and ~8.8X faster inference speed than EfficientNet-B0 on an embedded ARM processor. As such, the proposed deep learning-driven workflow, integrated with the aforementioned LightDefectNet neural network, is highly suited for high-throughput, high-performance light plate surface VQI within real-world manufacturing environments.

As AI systems become more capable, we would like to enlist their help to supervise other AIs. We experiment with methods for training a harmless AI assistant through self-improvement, without any human labels identifying harmful outputs. The only human oversight is provided through a list of rules or principles, and so we refer to the method as 'Constitutional AI'. The process involves both a supervised learning and a reinforcement learning phase. In the supervised phase we sample from an initial model, then generate self-critiques and revisions, and then finetune the original model on revised responses. In the RL phase, we sample from the finetuned model, use a model to evaluate which of the two samples is better, and then train a preference model from this dataset of AI preferences. We then train with RL using the preference model as the reward signal, i.e. we use 'RL from AI Feedback' (RLAIF). As a result we are able to train a harmless but non-evasive AI assistant that engages with harmful queries by explaining its objections to them. Both the SL and RL methods can leverage chain-of-thought style reasoning to improve the human-judged performance and transparency of AI decision making. These methods make it possible to control AI behavior more precisely and with far fewer human labels.

Text-guided image editing can have a transformative impact in supporting creative applications. A key challenge is to generate edits that are faithful to input text prompts, while consistent with input images. We present Imagen Editor, a cascaded diffusion model built, by fine-tuning Imagen on text-guided image inpainting. Imagen Editor's edits are faithful to the text prompts, which is accomplished by using object detectors to propose inpainting masks during training. In addition, Imagen Editor captures fine details in the input image by conditioning the cascaded pipeline on the original high resolution image. To improve qualitative and quantitative evaluation, we introduce EditBench, a systematic benchmark for text-guided image inpainting. EditBench evaluates inpainting edits on natural and generated images exploring objects, attributes, and scenes. Through extensive human evaluation on EditBench, we find that object-masking during training leads to across-the-board improvements in text-image alignment -- such that Imagen Editor is preferred over DALL-E 2 and Stable Diffusion -- and, as a cohort, these models are better at object-rendering than text-rendering, and handle material/color/size attributes better than count/shape attributes.

Realistic synthetic image data rendered from 3D models can be used to augment image sets and train image classification semantic segmentation models. In this work, we explore how high quality physically-based rendering and domain randomization can efficiently create a large synthetic dataset based on production 3D CAD models of a real vehicle. We use this dataset to quantify the effectiveness of synthetic augmentation using U-net and Double-U-net models. We found that, for this domain, synthetic images were an effective technique for augmenting limited sets of real training data. We observed that models trained on purely synthetic images had a very low mean prediction IoU on real validation images. We also observed that adding even very small amounts of real images to a synthetic dataset greatly improved accuracy, and that models trained on datasets augmented with synthetic images were more accurate than those trained on real images alone. Finally, we found that in use cases that benefit from incremental training or model specialization, pretraining a base model on synthetic images provided a sizeable reduction in the training cost of transfer learning, allowing up to 90\% of the model training to be front-loaded.