Many real-world applications of language models (LMs), such as code autocomplete and writing assistance, involve human-LM interaction, but the main LM benchmarks are non-interactive, where a system produces output without human intervention. To evaluate human-LM interaction, we develop a framework, Human-AI Language-based Interaction Evaluation (H-LINE), that expands non-interactive evaluation along three dimensions, capturing (i) the interactive process, not only the final output; (ii) the first-person subjective experience, not just a third-party assessment; and (iii) notions of preference beyond quality. We then design five tasks ranging from goal-oriented to open-ended to capture different forms of interaction. On four state-of-the-art LMs (three variants of OpenAI's GPT-3 and AI21's J1-Jumbo), we find that non-interactive performance does not always result in better human-LM interaction and that first-person and third-party metrics can diverge, suggesting the importance of examining the nuances of human-LM interaction.

Humans are excellent at understanding language and vision to accomplish a wide range of tasks. In contrast, creating general instruction-following embodied agents remains a difficult challenge. Prior work that uses pure language-only models lack visual grounding, making it difficult to connect language instructions with visual observations. On the other hand, methods that use pre-trained vision-language models typically come with divided language and visual representations, requiring designing specialized network architecture to fuse them together. We propose a simple yet effective model for robots to solve instruction-following tasks in vision-based environments. Our \ours method consists of a multimodal transformer that encodes visual observations and language instructions, and a policy transformer that predicts actions based on encoded representations. The multimodal transformer is pre-trained on millions of image-text pairs and natural language text, thereby producing generic cross-modal representations of observations and instructions. The policy transformer keeps track of the full history of observations and actions, and predicts actions autoregressively. We show that this unified transformer model outperforms all state-of-the-art pre-trained or trained-from-scratch methods in both single-task and multi-task settings. Our model also shows better model scalability and generalization ability than prior work.

表示学习通常通过管理维度的诅咒在加强学习中起关键作用。代表性的算法类别利用了随机过渡动力学的光谱分解，以构建在理想化环境中具有强大理论特性的表示。但是，当前的光谱方法的适用性有限，因为它们是用于仅国家的聚合并源自策略依赖性过渡内核的，而无需考虑勘探问题。为了解决这些问题，我们提出了一种替代光谱方法，光谱分解表示（SPEDER），该方法从动力学中提取了国家行动抽象而不诱导虚假依赖数据收集策略，同时还可以平衡探索访问权分析交易 - 在学习过程中关闭。理论分析确定了在线和离线设置中所提出的算法的样本效率。此外，一项实验研究表明，在几个基准测试中，比当前的最新算法表现出色。

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}）。

AI正在经历范式转变，随着模型的兴起（例如Bert，Dall-E，GPT-3），这些模型经过大规模的数据训练，并且可以适应广泛的下游任务。我们称这些模型基础模型来强调其至关重要但不完整的特征。该报告提供了基础模型的机会和风险的详尽说明，包括其功能（例如语言，愿景，机器人技术，推理，人类互动）和技术原则（例如，模型架构，培训程序，数据，系统，安全，安全性，评估，理论）对其应用（例如法律，医疗保健，教育）和社会影响（例如不平等，滥用，经济和环境影响，法律和道德考虑）。尽管基础模型基于标准的深度学习和转移学习，但它们的规模导致了新的新兴能力，以及它们在许多任务中的有效性都激发了同质化。同质化提供了强大的杠杆作用，但要求谨慎，因为基础模型的缺陷均由下游的所有适应模型继承。尽管即将广泛地部署基础模型，但我们目前对它们的工作方式，失败以及由于其新兴属性的影响而缺乏清晰的了解。为了解决这些问题，我们认为基础模型的许多批判性研究都需要与他们的基本社会技术性质相称。

Retrieval-augmented in-context learning has emerged as a powerful approach for addressing knowledge-intensive tasks using frozen language models (LM) and retrieval models (RM). Existing work has combined these in simple "retrieve-then-read" pipelines in which the RM retrieves passages that are inserted into the LM prompt. To begin to fully realize the potential of frozen LMs and RMs, we propose Demonstrate-Search-Predict (DSP), a framework that relies on passing natural language texts in sophisticated pipelines between an LM and an RM. DSP can express high-level programs that bootstrap pipeline-aware demonstrations, search for relevant passages, and generate grounded predictions, systematically breaking down problems into small transformations that the LM and RM can handle more reliably. We have written novel DSP programs for answering questions in open-domain, multi-hop, and conversational settings, establishing in early evaluations new state-of-the-art in-context learning results and delivering 37-200%, 8-40%, and 80-290% relative gains against vanilla LMs, a standard retrieve-then-read pipeline, and a contemporaneous self-ask pipeline, respectively.

Semi-supervised learning (SSL) has made significant strides in the field of remote sensing. Finding a large number of labeled datasets for SSL methods is uncommon, and manually labeling datasets is expensive and time-consuming. Furthermore, accurately identifying remote sensing satellite images is more complicated than it is for conventional images. Class-imbalanced datasets are another prevalent phenomenon, and models trained on these become biased towards the majority classes. This becomes a critical issue with an SSL model's subpar performance. We aim to address the issue of labeling unlabeled data and also solve the model bias problem due to imbalanced datasets while achieving better accuracy. To accomplish this, we create "artificial" labels and train a model to have reasonable accuracy. We iteratively redistribute the classes through resampling using a distribution alignment technique. We use a variety of class imbalanced satellite image datasets: EuroSAT, UCM, and WHU-RS19. On UCM balanced dataset, our method outperforms previous methods MSMatch and FixMatch by 1.21% and 0.6%, respectively. For imbalanced EuroSAT, our method outperforms MSMatch and FixMatch by 1.08% and 1%, respectively. Our approach significantly lessens the requirement for labeled data, consistently outperforms alternative approaches, and resolves the issue of model bias caused by class imbalance in datasets.

Identifying the production dates of historical manuscripts is one of the main goals for paleographers when studying ancient documents. Automatized methods can provide paleographers with objective tools to estimate dates more accurately. Previously, statistical features have been used to date digitized historical manuscripts based on the hypothesis that handwriting styles change over periods. However, the sparse availability of such documents poses a challenge in obtaining robust systems. Hence, the research of this article explores the influence of data augmentation on the dating of historical manuscripts. Linear Support Vector Machines were trained with k-fold cross-validation on textural and grapheme-based features extracted from historical manuscripts of different collections, including the Medieval Paleographical Scale, early Aramaic manuscripts, and the Dead Sea Scrolls. Results show that training models with augmented data improve the performance of historical manuscripts dating by 1% - 3% in cumulative scores. Additionally, this indicates further enhancement possibilities by considering models specific to the features and the documents' scripts.

Vehicle trajectory data has received increasing research attention over the past decades. With the technological sensing improvements such as high-resolution video cameras, in-vehicle radars and lidars, abundant individual and contextual traffic data is now available. However, though the data quantity is massive, it is by itself of limited utility for traffic research because of noise and systematic sensing errors, thus necessitates proper processing to ensure data quality. We draw particular attention to extracting high-resolution vehicle trajectory data from video cameras as traffic monitoring cameras are becoming increasingly ubiquitous. We explore methods for automatic trajectory data reconciliation, given "raw" vehicle detection and tracking information from automatic video processing algorithms. We propose a pipeline including a) an online data association algorithm to match fragments that are associated to the same object (vehicle), which is formulated as a min-cost network flow problem of a graph, and b) a trajectory reconciliation method formulated as a quadratic program to enhance raw detection data. The pipeline leverages vehicle dynamics and physical constraints to associate tracked objects when they become fragmented, remove measurement noise on trajectories and impute missing data due to fragmentations. The accuracy is benchmarked on a sample of manually-labeled data, which shows that the reconciled trajectories improve the accuracy on all the tested input data for a wide range of measures. An online version of the reconciliation pipeline is implemented and will be applied in a continuous video processing system running on a camera network covering a 4-mile stretch of Interstate-24 near Nashville, Tennessee.

We introduce a linguistically enhanced combination of pre-training methods for transformers. The pre-training objectives include POS-tagging, synset prediction based on semantic knowledge graphs, and parent prediction based on dependency parse trees. Our approach achieves competitive results on the Natural Language Inference task, compared to the state of the art. Specifically for smaller models, the method results in a significant performance boost, emphasizing the fact that intelligent pre-training can make up for fewer parameters and help building more efficient models. Combining POS-tagging and synset prediction yields the overall best results.