Dynamic movement primitives are widely used for learning skills which can be demonstrated to a robot by a skilled human or controller. While their generalization capabilities and simple formulation make them very appealing to use, they possess no strong guarantees to satisfy operational safety constraints for a task. In this paper, we present constrained dynamic movement primitives (CDMP) which can allow for constraint satisfaction in the robot workspace. We present a formulation of a non-linear optimization to perturb the DMP forcing weights regressed by locally-weighted regression to admit a Zeroing Barrier Function (ZBF), which certifies workspace constraint satisfaction. We demonstrate the proposed CDMP under different constraints on the end-effector movement such as obstacle avoidance and workspace constraints on a physical robot. A video showing the implementation of the proposed algorithm using different manipulators in different environments could be found here https://youtu.be/hJegJJkJfys.

Advancement in large pretrained language models has significantly improved their performance for conditional language generation tasks including summarization albeit with hallucinations. To reduce hallucinations, conventional methods proposed improving beam search or using a fact checker as a postprocessing step. In this paper, we investigate the use of the Natural Language Inference (NLI) entailment metric to detect and prevent hallucinations in summary generation. We propose an NLI-assisted beam re-ranking mechanism by computing entailment probability scores between the input context and summarization model-generated beams during saliency-enhanced greedy decoding. Moreover, a diversity metric is introduced to compare its effectiveness against vanilla beam search. Our proposed algorithm significantly outperforms vanilla beam decoding on XSum and CNN/DM datasets.

Recent work in sim2real has successfully enabled robots to act in physical environments by training in simulation with a diverse ''population'' of environments (i.e. domain randomization). In this work, we focus on enabling generalization in assistive tasks: tasks in which the robot is acting to assist a user (e.g. helping someone with motor impairments with bathing or with scratching an itch). Such tasks are particularly interesting relative to prior sim2real successes because the environment now contains a human who is also acting. This complicates the problem because the diversity of human users (instead of merely physical environment parameters) is more difficult to capture in a population, thus increasing the likelihood of encountering out-of-distribution (OOD) human policies at test time. We advocate that generalization to such OOD policies benefits from (1) learning a good latent representation for human policies that test-time humans can accurately be mapped to, and (2) making that representation adaptable with test-time interaction data, instead of relying on it to perfectly capture the space of human policies based on the simulated population only. We study how to best learn such a representation by evaluating on purposefully constructed OOD test policies. We find that sim2real methods that encode environment (or population) parameters and work well in tasks that robots do in isolation, do not work well in assistance. In assistance, it seems crucial to train the representation based on the history of interaction directly, because that is what the robot will have access to at test time. Further, training these representations to then predict human actions not only gives them better structure, but also enables them to be fine-tuned at test-time, when the robot observes the partner act. https://adaptive-caregiver.github.io.

Finetuning image-text models such as CLIP achieves state-of-the-art accuracies on a variety of benchmarks. However, recent works like WiseFT (Wortsman et al., 2021) and LP-FT (Kumar et al., 2022) have shown that even subtle differences in the finetuning process can lead to surprisingly large differences in the final performance, both for in-distribution (ID) and out-of-distribution (OOD) data. In this work, we show that a natural and simple approach of mimicking contrastive pretraining consistently outperforms alternative finetuning approaches. Specifically, we cast downstream class labels as text prompts and continue optimizing the contrastive loss between image embeddings and class-descriptive prompt embeddings (contrastive finetuning). Our method consistently outperforms baselines across 7 distribution shifts, 6 transfer learning, and 3 few-shot learning benchmarks. On WILDS-iWILDCam, our proposed approach FLYP outperforms the top of the leaderboard by $2.3\%$ ID and $2.7\%$ OOD, giving the highest reported accuracy. Averaged across 7 OOD datasets (2 WILDS and 5 ImageNet associated shifts), FLYP gives gains of $4.2\%$ OOD over standard finetuning and outperforms the current state of the art (LP-FT) by more than $1\%$ both ID and OOD. Similarly, on 3 few-shot learning benchmarks, our approach gives gains up to $4.6\%$ over standard finetuning and $4.4\%$ over the state of the art. In total, these benchmarks establish contrastive finetuning as a simple, intuitive, and state-of-the-art approach for supervised finetuning of image-text models like CLIP. Code is available at https://github.com/locuslab/FLYP.

Generative Adversarial Networks (GANs) have received wide acclaim among the machine learning (ML) community for their ability to generate realistic 2D images. ML is being applied more often to complex problems beyond those of computer vision. However, current frameworks often serve as black boxes and lack physics embeddings, leading to poor ability in enforcing constraints and unreliable models. In this work, we develop physics embeddings that can be stringently imposed, referred to as hard constraints, in the neural network architecture. We demonstrate their capability for 3D turbulence by embedding them in GANs, particularly to enforce the mass conservation constraint in incompressible fluid turbulence. In doing so, we also explore and contrast the effects of other methods of imposing physics constraints within the GANs framework, especially penalty-based physics constraints popular in literature. By using physics-informed diagnostics and statistics, we evaluate the strengths and weaknesses of our approach and demonstrate its feasibility.

The process of screening molecules for desirable properties is a key step in several applications, ranging from drug discovery to material design. During the process of drug discovery specifically, protein-ligand docking, or chemical docking, is a standard in-silico scoring technique that estimates the binding affinity of molecules with a specific protein target. Recently, however, as the number of virtual molecules available to test has rapidly grown, these classical docking algorithms have created a significant computational bottleneck. We address this problem by introducing Deep Surrogate Docking (DSD), a framework that applies deep learning-based surrogate modeling to accelerate the docking process substantially. DSD can be interpreted as a formalism of several earlier surrogate prefiltering techniques, adding novel metrics and practical training practices. Specifically, we show that graph neural networks (GNNs) can serve as fast and accurate estimators of classical docking algorithms. Additionally, we introduce FiLMv2, a novel GNN architecture which we show outperforms existing state-of-the-art GNN architectures, attaining more accurate and stable performance by allowing the model to filter out irrelevant information from data more efficiently. Through extensive experimentation and analysis, we show that the DSD workflow combined with the FiLMv2 architecture provides a 9.496x speedup in molecule screening with a <3% recall error rate on an example docking task. Our open-source code is available at https://github.com/ryienh/graph-dock.

Duckiebots是低成本的移动机器人，在研究和教育领域广泛使用。尽管Duckietown平台有现有的自动驾驶算法，但它们要么太复杂，要么表现太差，无法导航多车道轨道。此外，必须将内存和计算资源提供给Duckiebot，以便它可以执行其他任务，例如分布式输入检测。为了满足这些约束，我们构建了一种低成本的自主驾驶算法，能够在两车道轨道上驾驶。该算法使用传统的计算机视觉技术来识别轨道上的中央车道并获得相关的转向角度。然后，转向由PID控制器控制，该PID控制器使Duckiebot的运动平滑。将算法的性能与Neurips 2018 AI驾驶奥运会（AIDO）决赛入围者进行了比较，并且除了一名决赛选手以外，它的表现优于所有球员。我们算法的两个主要贡献是其低计算要求和非常快速的设置，并持续努力使其更加可靠。

仇恨言论以贬义的评论以多种形式针对社区，并使人类退后一步。 Hatexplain是最近出版的第一个数据集，用于以理由的形式使用带注释的跨度，以及语音分类类别和有针对性的社区，以使分类更具人性化，可解释，准确和偏见。我们调整BERT以理由和阶级预测的形式执行此任务，并比较我们对跨精度，解释性和偏见的不同指标的性能。我们的新颖性是三倍。首先，我们尝试具有不同重要性值的合并理由类损失。其次，我们对理由的地面真相注意值进行了广泛的实验。随着保守和宽大的关注，我们比较了hatexplain模型的性能并检验我们的假设。第三，为了改善模型中的意外偏见，我们使用目标社区单词的掩盖，并注意偏见和解释性指标的改善。总体而言，我们成功地实现了模型的解释性，偏差删除和对原始BERT实施的几个增量改进。

深度神经网络的过度参数性质导致在低端设备上的部署过程中有很大的障碍，并具有时间和空间限制。使用迭代修剪培训方案稀疏DNN的网络修剪策略通常在计算上很昂贵。结果，在训练之前，在初始化时修剪修剪的技术变得越来越流行。在这项工作中，我们提出了神经元到神经元的跳过连接，这些连接是稀疏的加权跳过连接，以增强修剪的DNN的整体连通性。遵循初步修剪步骤，在修剪网络的单个神经元/通道之间随机添加N2NSKIP连接，同时保持网络的整体稀疏性。我们证明，与没有N2NSKIP连接的修剪的网络相比，在修剪网络中引入N2NSKIP连接可以显着卓越的性能，尤其是在高稀疏度水平上。此外，我们提出了基于热扩散的连接分析，以定量确定修剪网络相对于参考网络的连通性。我们评估方法对两种不同初步修剪方法的疗效，这些方法在初始化时修剪，并通过利用N2NSKIP连接引起的增强连接性来始终获得卓越的性能。

独立组件分析是一种无监督的学习方法，用于从多元信号或数据矩阵计算独立组件（IC）。基于权重矩阵与多元数据矩阵的乘法进行评估。这项研究提出了一个新型的Memristor横杆阵列，用于实施ACY ICA和快速ICA，以用于盲源分离。数据输入以脉冲宽度调制电压的形式应用于横梁阵列，并且已实现的神经网络的重量存储在Memristor中。来自Memristor列的输出电荷用于计算重量更新，该重量更新是通过电压高于Memristor SET/RESET电压执行的。为了证明其潜在应用，采用了基于ICA架构的基于ICA架构的拟议的Memristor横杆阵列用于图像源分离问题。实验结果表明，所提出的方法非常有效地分离图像源，并且与常规ACY的基于软件的ACY实施相比，与结构相似性的百分比相比，结构相似性的百分比为67.27％，图像的对比度得到了改进。 ICA和快速ICA算法。