Many existing approaches to generalizing statistical inference amidst distribution shift operate under the covariate shift assumption, which posits that the conditional distribution of unobserved variables given observable ones is invariant across populations. However, recent empirical investigations have demonstrated that adjusting for shift in observed variables (covariate shift) is often insufficient for generalization. In other words, covariate shift does not typically ``explain away'' the distribution shift between settings. As such, addressing the unknown yet non-negligible shift in the unobserved variables given observed ones (conditional shift) is crucial for generalizable inference. In this paper, we present a series of empirical evidence from two large-scale multi-site replication studies to support a new role of covariate shift in ``predicting'' the strength of the unknown conditional shift. Analyzing 680 studies across 65 sites, we find that even though the conditional shift is non-negligible, its strength can often be bounded by that of the observable covariate shift. However, this pattern only emerges when the two sources of shifts are quantified by our proposed standardized, ``pivotal'' measures. We then interpret this phenomenon by connecting it to similar patterns that can be theoretically derived from a random distribution shift model. Finally, we demonstrate that exploiting the predictive role of covariate shift leads to reliable and efficient uncertainty quantification for target estimates in generalization tasks with partially observed data. Overall, our empirical and theoretical analyses suggest a new way to approach the problem of distributional shift, generalizability, and external validity.

-- This paper presents a unified algorithm for motion and force control for a six degree-of-freedom spatial manipulator . The motion-force contoller performs trajectory tracking, maneuvering the manipulator's end-effector through desired positions, orientations and rates. When contacting an obstacle or target object, the force module of the controller restricts the manipulator movements with a novel force exertion method, which prevents damage to the manipulator, end-effectors and objects during the contact or collision. The core strategy presented in this paper is to design the linear acceleration for the end-effector which ensures both trajectory tracking and restriction of any contact force at the end-effector . The design of the controller has been validated through numerical simulations and digital twin visualization. I. INTRODUCTION Robotic manipulators are used in various industries such as automotive and aerospace for a vast amount of applications. These common applications, such as material handling and assembly, require the end effector to follow the reference trajectories. In addition to trajectory tracking, a safe collaborative robot must control the force that the end-effector exerts upon contact with any obstacles during trajectory tracking. Specifically, the magnitude of the force that the robot exerts should be bounded by the maximum allowable force.

We present an open-source and extensible knowledge extraction toolkit DeepKE, supporting complicated low-resource, document-level and multimodal scenarios in the knowledge base population. DeepKE implements various information extraction tasks, including named entity recognition, relation extraction and attribute extraction. With a unified framework, DeepKE allows developers and researchers to customize datasets and models to extract information from unstructured data according to their requirements. Specifically, DeepKE not only provides various functional modules and model implementation for different tasks and scenarios but also organizes all components by consistent frameworks to maintain sufficient modularity and extensibility. We release the source code at GitHub in https://github.com/zjunlp/DeepKE with Google Colab tutorials and comprehensive documents for beginners. Besides, we present an online system in http://deepke.openkg.cn/EN/re_doc_show.html for real-time extraction of various tasks, and a demo video.

Flexible needle insertion procedures are common for minimally-invasive surgeries for diagnosing and treating prostate cancer. Bevel-tip needles provide physicians the capability to steer the needle during long insertions to avoid vital anatomical structures in the patient and reduce post-operative patient discomfort. To provide needle placement feedback to the physician, sensors are embedded into needles for determining the real-time 3D shape of the needle during operation without needing to visualize the needle intra-operatively. Through expansive research in fiber optics, a plethora of bio-compatible, MRI-compatible, optical shape-sensors have been developed to provide real-time shape feedback, such as single-core and multicore fiber Bragg gratings. In this paper, we directly compare single-core fiber-based and multicore fiber-based needle shape-sensing through identically constructed, four-active area sensorized bevel-tip needles inserted into phantom and \exvivo tissue on the same experimental platform. In this work, we found that for shape-sensing in phantom tissue, the two needles performed identically with a $p$-value of $0.164 > 0.05$, but in \exvivo real tissue, the single-core fiber sensorized needle significantly outperformed the multicore fiber configuration with a $p$-value of $0.0005 < 0.05$. This paper also presents the experimental platform and method for directly comparing these optical shape sensors for the needle shape-sensing task, as well as provides direction, insight and required considerations for future work in constructively optimizing sensorized needles.

Considering a collection of RDF triples, the RDF-to-text generation task aims to generate a text description. Most previous methods solve this task using a sequence-to-sequence model or using a graph-based model to encode RDF triples and to generate a text sequence. Nevertheless, these approaches fail to clearly model the local and global structural information between and within RDF triples. Moreover, the previous methods also face the non-negligible problem of low faithfulness of the generated text, which seriously affects the overall performance of these models. To solve these problems, we propose a model combining two new graph-augmented structural neural encoders to jointly learn both local and global structural information in the input RDF triples. To further improve text faithfulness, we innovatively introduce a reinforcement learning (RL) reward based on information extraction (IE). We first extract triples from the generated text using a pretrained IE model and regard the correct number of the extracted triples as the additional RL reward. Experimental results on two benchmark datasets demonstrate that our proposed model outperforms the state-of-the-art baselines, and the additional reinforcement learning reward does help to improve the faithfulness of the generated text.

Document-level relation extraction aims to extract relations among entities within a document. Different from sentence-level relation extraction, it requires reasoning over multiple sentences across a document. In this paper, we propose Graph Aggregation-and-Inference Network (GAIN) featuring double graphs. GAIN first constructs a heterogeneous mention-level graph (hMG) to model complex interaction among different mentions across the document. It also constructs an entity-level graph (EG), based on which we propose a novel path reasoning mechanism to infer relations between entities. Experiments on the public dataset, DocRED, show GAIN achieves a significant performance improvement (2.85 on F1) over the previous state-of-the-art. Our code is available at https://github.com/DreamInvoker/GAIN .

Robots are increasingly becoming key players in human-robot teams. To become effective teammates, robots must possess profound understanding of an environment, be able to reason about the desired commands and goals within a specific context, and be able to communicate with human teammates in a clear and natural way. To address these challenges, we have developed an intelligence architecture that combines cognitive components to carry out high-level cognitive tasks, semantic perception to label regions in the world, and a natural language component to reason about the command and its relationship to the objects in the world. This paper describes recent developments using this architecture on a fielded mobile robot platform operating in unknown urban environments. We report a summary of extensive outdoor experiments; the results suggest that a multidisciplinary approach to robotics has the potential to create competent human-robot teams.

We study logical principles connecting two relations: independence, which is known as nondeducibility in the study of information flow, and functional dependence. Two different epistemic interpretations for these relations are discussed: semantics of secrets and probabilistic semantics. A logical system sound and complete with respect to both of these semantics is introduced and is shown to be decidable.