为了帮助现有的Telemental Mechanical服务，我们提出Deeptmh，这是一种通过提取对应于心理学文献经常使用的情感和认知特征的潜视和认知特征来模拟Telemental Mealth Session视频的新框架。我们的方法利用半监督学习的进步来解决Telemental Healts Sessience视频领域的数据稀缺，包括多模式半监督GaN，以检测Telemental卫生课程中的重要心理健康指标。我们展示了我们框架的有用性和与现有工作中的两项任务对比：参与回归和价值回归，这两者都对心理学家在眼药性健康会议期间对心理学家很重要。我们的框架报告了RMSE在参与回归中的RMSE方法的40％，并在价值唤醒回归中的SOTA方法中的50％改善。为了解决Telemental Health空间中公开的数据集的稀缺性，我们发布了一个新的数据集，Medica，用于心理健康患者参与检测。我们的数据集，Medica由1299个视频组成，每节3秒长。据我们所知，我们的方法是基于心理驱动的情感和认知功能来模拟Telemental Healts会话数据的第一种方法，这也通过利用半监督设置来解决数据稀疏性。

Language models have become increasingly popular in recent years for tasks like information retrieval. As use-cases become oriented toward specific domains, fine-tuning becomes default for standard performance. To fine-tune these models for specific tasks and datasets, it is necessary to carefully tune the model's hyperparameters and training techniques. In this paper, we present an in-depth analysis of the performance of four transformer-based language models on the task of biomedical information retrieval. The models we consider are DeepMind's RETRO (7B parameters), GPT-J (6B parameters), GPT-3 (175B parameters), and BLOOM (176B parameters). We compare their performance on the basis of relevance, accuracy, and interpretability, using a large corpus of 480000 research papers on protein structure/function prediction as our dataset. Our findings suggest that smaller models, with <10B parameters and fine-tuned on domain-specific datasets, tend to outperform larger language models on highly specific questions in terms of accuracy, relevancy, and interpretability by a significant margin (+50% on average). However, larger models do provide generally better results on broader prompts.

Text classifiers have promising applications in high-stake tasks such as resume screening and content moderation. These classifiers must be fair and avoid discriminatory decisions by being invariant to perturbations of sensitive attributes such as gender or ethnicity. However, there is a gap between human intuition about these perturbations and the formal similarity specifications capturing them. While existing research has started to address this gap, current methods are based on hardcoded word replacements, resulting in specifications with limited expressivity or ones that fail to fully align with human intuition (e.g., in cases of asymmetric counterfactuals). This work proposes novel methods for bridging this gap by discovering expressive and intuitive individual fairness specifications. We show how to leverage unsupervised style transfer and GPT-3's zero-shot capabilities to automatically generate expressive candidate pairs of semantically similar sentences that differ along sensitive attributes. We then validate the generated pairs via an extensive crowdsourcing study, which confirms that a lot of these pairs align with human intuition about fairness in the context of toxicity classification. Finally, we show how limited amounts of human feedback can be leveraged to learn a similarity specification that can be used to train downstream fairness-aware models.

We study the sample complexity of reducing reinforcement learning to a sequence of empirical risk minimization problems over the policy space. Such reductions-based algorithms exhibit local convergence in the function space, as opposed to the parameter space for policy gradient algorithms, and thus are unaffected by the possibly non-linear or discontinuous parameterization of the policy class. We propose a variance-reduced variant of Conservative Policy Iteration that improves the sample complexity of producing a $\varepsilon$-functional local optimum from $O(\varepsilon^{-4})$ to $O(\varepsilon^{-3})$. Under state-coverage and policy-completeness assumptions, the algorithm enjoys $\varepsilon$-global optimality after sampling $O(\varepsilon^{-2})$ times, improving upon the previously established $O(\varepsilon^{-3})$ sample requirement.

This work aims at showing that it is feasible and safe to use a swarm of Unmanned Aerial Vehicles (UAVs) indoors alongside humans. UAVs are increasingly being integrated under the Industry 4.0 framework. UAV swarms are primarily deployed outdoors in civil and military applications, but the opportunities for using them in manufacturing and supply chain management are immense. There is extensive research on UAV technology, e.g., localization, control, and computer vision, but less research on the practical application of UAVs in industry. UAV technology could improve data collection and monitoring, enhance decision-making in an Internet of Things framework and automate time-consuming and redundant tasks in the industry. However, there is a gap between the technological developments of UAVs and their integration into the supply chain. Therefore, this work focuses on automating the task of transporting packages utilizing a swarm of small UAVs operating alongside humans. MoCap system, ROS, and unity are used for localization, inter-process communication and visualization. Multiple experiments are performed with the UAVs in wander and swarm mode in a warehouse like environment.

Human Activity Recognition (HAR) using on-body devices identifies specific human actions in unconstrained environments. HAR is challenging due to the inter and intra-variance of human movements; moreover, annotated datasets from on-body devices are scarce. This problem is mainly due to the difficulty of data creation, i.e., recording, expensive annotation, and lack of standard definitions of human activities. Previous works demonstrated that transfer learning is a good strategy for addressing scenarios with scarce data. However, the scarcity of annotated on-body device datasets remains. This paper proposes using datasets intended for human-pose estimation as a source for transfer learning; specifically, it deploys sequences of annotated pixel coordinates of human joints from video datasets for HAR and human pose estimation. We pre-train a deep architecture on four benchmark video-based source datasets. Finally, an evaluation is carried out on three on-body device datasets improving HAR performance.

A real-world application or setting involves interaction between different modalities (e.g., video, speech, text). In order to process the multimodal information automatically and use it for an end application, Multimodal Representation Learning (MRL) has emerged as an active area of research in recent times. MRL involves learning reliable and robust representations of information from heterogeneous sources and fusing them. However, in practice, the data acquired from different sources are typically noisy. In some extreme cases, a noise of large magnitude can completely alter the semantics of the data leading to inconsistencies in the parallel multimodal data. In this paper, we propose a novel method for multimodal representation learning in a noisy environment via the generalized product of experts technique. In the proposed method, we train a separate network for each modality to assess the credibility of information coming from that modality, and subsequently, the contribution from each modality is dynamically varied while estimating the joint distribution. We evaluate our method on two challenging benchmarks from two diverse domains: multimodal 3D hand-pose estimation and multimodal surgical video segmentation. We attain state-of-the-art performance on both benchmarks. Our extensive quantitative and qualitative evaluations show the advantages of our method compared to previous approaches.

This paper addresses the problem of reliably and efficiently solving broad classes of long-horizon stochastic path planning problems. Starting with a vanilla RL formulation with a stochastic dynamics simulator and an occupancy matrix of the environment, our approach computes useful options with policies as well as high-level paths that compose the discovered options. Our main contributions are (1) data-driven methods for creating abstract states that serve as endpoints for helpful options, (2) methods for computing option policies using auto-generated option guides in the form of dense pseudo-reward functions, and (3) an overarching algorithm for composing the computed options. We show that this approach yields strong guarantees of executability and solvability: under fairly general conditions, the computed option guides lead to composable option policies and consequently ensure downward refinability. Empirical evaluation on a range of robots, environments, and tasks shows that this approach effectively transfers knowledge across related tasks and that it outperforms existing approaches by a significant margin.

深尾学习旨在培训有用的深层网络，以实用现实世界中的不平衡分布，其中大多数尾巴类别的标签都与一些样本相关联。有大量的工作来训练判别模型，以进行长尾分布的视觉识别。相比之下，我们旨在训练有条件的生成对抗网络，这是一类长尾分布的图像生成模型。我们发现，类似于识别图像产生的最新方法类似，也遭受了尾部类别的性能降解。性能降解主要是由于尾部类别的类别模式塌陷，我们观察到与调节参数矩阵的光谱爆炸相关。我们提出了一种新型的组光谱正规剂（GSR），以防止光谱爆炸减轻模式崩溃，从而导致尾巴类别的形象产生多样化和合理的图像产生。我们发现GSR有效地与现有的增强和正则化技术结合在一起，从而导致长尾数据上的最新图像生成性能。广泛的实验证明了我们的常规器在不同程度不平衡的长尾数据集上的功效。

我们提出了Blenderbot 3，这是一个175B参数对话模型，能够通过访问Internet和长期内存进行开放域对话，并接受了大量用户定义的任务的培训。我们同时发布了模型权重和代码，还将模型部署在公共网页上，以与有机用户进行交互。该技术报告描述了该模型的构建方式（建筑，模型和培训计划）以及其部署的细节，包括安全机制。人类评估表明，它优于现有的开放域对话代理，包括其前身（Roller等，2021； Komeili等，2022）。最后，我们使用部署收集的数据详细介绍了持续学习的计划，该数据也将公开发布。因此，该研究计划的目标是使社区能够研究通过互动学习的不断改进的负责任的代理商。