arXiv subjects

Wei Xu

Publications and source records attributed to Wei Xu.

At least 451 records · Page 25Linked to original sources

arXiv2021

Human-AI interaction: An emerging interdisciplinary domain for enabling human-centered AI

The new characteristics of AI technology have brought new challenges to the research and development of AI systems. AI technology has benefited humans, but if improperly developed, it will harm humans. At present, there is no systematic interdisciplinary approach to effectively deal with these new challenges. This paper analyzes the new challenges faced by AI systems and further elaborates the "Human-Centered AI" (HCAI) approach we proposed in 2019. In order to enable the implementation of the HCAI approach, we systematically propose an emerging interdisciplinary domain of "Human-AI Interaction" (HAII), and define the objective, methodology, and scope. Based on literature review and analyses, this paper summarizes the main areas of the HAII research and application as well as puts forward the future research agenda for HAII. Finally, the paper provides strategic recommendations for future implementation of the HCAII approach and HAII work.

cs.HC↗

arXiv2021

Human factors engineering research on single pilot operations for large commercial aircraft: Status and prospect

The civil aviation community is actively exploring and developing the solutions of single pilot operations SPO for large commercial aircraft. Human factors engineering research for SPO has been launched, and the research mainly focuses on three research solutions: flight deck airborne equipment upgrade, flight support from ground stations, and the combined SPO solution of "flight deck airborne equipment upgrade, flight support from ground stations". This paper reviews and analyzez the progress of human factors engineering research on SPO. The preliminary research outcome tends to support the combined SPO solution. However, the current human factors engineering research is not comprehensive and cannot provide a complete human factors engineering solution for SPO. For future human factors engineering research, this paper analyzes the key human factors issues on SPO and points out the gaps in the current research and the areas for future work. Finally, this paper puts forward an overall strategy and recommendations for future human factors engineering research on SPO.

cs.HC↗

arXiv2021

TAAC: Temporally Abstract Actor-Critic for Continuous Control

We present temporally abstract actor-critic (TAAC), a simple but effective off-policy RL algorithm that incorporates closed-loop temporal abstraction into the actor-critic framework. TAAC adds a second-stage binary policy to choose between the previous action and a new action output by an actor. Crucially, its "act-or-repeat" decision hinges on the actually sampled action instead of the expected behavior of the actor. This post-acting switching scheme let the overall policy make more informed decisions. TAAC has two important features: a) persistent exploration, and b) a new compare-through Q operator for multi-step TD backup, specially tailored to the action repetition scenario. We demonstrate TAAC's advantages over several strong baselines across 14 continuous control tasks. Our surprising finding reveals that while achieving top performance, TAAC is able to "mine" a significant number of repeated actions with the trained policy even on continuous tasks whose problem structures on the surface seem to repel action repetition. This suggests that aside from encouraging persistent exploration, action repetition can find its place in a good policy behavior. Code is available at https://github.com/hnyu/taac.

cs.LG↗

arXiv2021

Natural Language for Human-Robot Collaboration: Problems Beyond Language Grounding

To enable robots to instruct humans in collaborations, we identify several aspects of language processing that are not commonly studied in this context. These include location, planning, and generation. We suggest evaluations for each task, offer baselines for simple methods, and close by discussing challenges and opportunities in studying language for collaboration.

cs.AI↗

arXiv2021

BiSECT: Learning to Split and Rephrase Sentences with Bitexts

An important task in NLP applications such as sentence simplification is the ability to take a long, complex sentence and split it into shorter sentences, rephrasing as necessary. We introduce a novel dataset and a new model for this `split and rephrase' task. Our BiSECT training data consists of 1 million long English sentences paired with shorter, meaning-equivalent English sentences. We obtain these by extracting 1-2 sentence alignments in bilingual parallel corpora and then using machine translation to convert both sides of the corpus into the same language. BiSECT contains higher quality training examples than previous Split and Rephrase corpora, with sentence splits that require more significant modifications. We categorize examples in our corpus, and use these categories in a novel model that allows us to target specific regions of the input sentence to be split and edited. Moreover, we show that models trained on BiSECT can perform a wider variety of split operations and improve upon previous state-of-the-art approaches in automatic and human evaluations.

cs.CL↗

arXiv2021

Neural CRF Model for Sentence Alignment in Text Simplification

The success of a text simplification system heavily depends on the quality and quantity of complex-simple sentence pairs in the training corpus, which are extracted by aligning sentences between parallel articles. To evaluate and improve sentence alignment quality, we create two manually annotated sentence-aligned datasets from two commonly used text simplification corpora, Newsela and Wikipedia. We propose a novel neural CRF alignment model which not only leverages the sequential nature of sentences in parallel documents but also utilizes a neural sentence pair model to capture semantic similarity. Experiments demonstrate that our proposed approach outperforms all the previous work on monolingual sentence alignment task by more than 5 points in F1. We apply our CRF aligner to construct two new text simplification datasets, Newsela-Auto and Wiki-Auto, which are much larger and of better quality compared to the existing datasets. A Transformer-based seq2seq model trained on our datasets establishes a new state-of-the-art for text simplification in both automatic and human evaluation.

cs.CL↗

arXiv2021

Feature Importance in a Deep Learning Climate Emulator

We present a study using a class of post-hoc local explanation methods i.e., feature importance methods for "understanding" a deep learning (DL) emulator of climate. Specifically, we consider a multiple-input-single-output emulator that uses a DenseNet encoder-decoder architecture and is trained to predict interannual variations of sea surface temperature (SST) at 1, 6, and 9 month lead times using the preceding 36 months of (appropriately filtered) SST data. First, feature importance methods are employed for individual predictions to spatio-temporally identify input features that are important for model prediction at chosen geographical regions and chosen prediction lead times. In a second step, we also examine the behavior of feature importance in a generalized sense by considering an aggregation of the importance heatmaps over training samples. We find that: 1) the climate emulator's prediction at any geographical location depends dominantly on a small neighborhood around it; 2) the longer the prediction lead time, the further back the "importance" extends; and 3) to leading order, the temporal decay of "importance" is independent of geographical location. An ablation experiment is adopted to verify the findings. From the perspective of climate dynamics, these findings suggest a dominant role for local processes and a negligible role for remote teleconnections at the spatial and temporal scales we consider. From the perspective of network architecture, the spatio-temporal relations between the inputs and outputs we find suggest potential model refinements. We discuss further extensions of our methods, some of which we are considering in ongoing work.

cs.LG↗

arXiv2021

Pre-training for Ad-hoc Retrieval: Hyperlink is Also You Need

Designing pre-training objectives that more closely resemble the downstream tasks for pre-trained language models can lead to better performance at the fine-tuning stage, especially in the ad-hoc retrieval area. Existing pre-training approaches tailored for IR tried to incorporate weak supervised signals, such as query-likelihood based sampling, to construct pseudo query-document pairs from the raw textual corpus. However, these signals rely heavily on the sampling method. For example, the query likelihood model may lead to much noise in the constructed pre-training data. \blfootnote{$\dagger$ This work was done during an internship at Huawei.} In this paper, we propose to leverage the large-scale hyperlinks and anchor texts to pre-train the language model for ad-hoc retrieval. Since the anchor texts are created by webmasters and can usually summarize the target document, it can help to build more accurate and reliable pre-training samples than a specific algorithm. Considering different views of the downstream ad-hoc retrieval, we devise four pre-training tasks based on the hyperlinks. We then pre-train the Transformer model to predict the pair-wise preference, jointly with the Masked Language Model objective. Experimental results on two large-scale ad-hoc retrieval datasets show the significant improvement of our model compared with the existing methods.

cs.IR↗

arXiv2021

Generative Particle Variational Inference via Estimation of Functional Gradients

Recently, particle-based variational inference (ParVI) methods have gained interest because they can avoid arbitrary parametric assumptions that are common in variational inference. However, many ParVI approaches do not allow arbitrary sampling from the posterior, and the few that do allow such sampling suffer from suboptimality. This work proposes a new method for learning to approximately sample from the posterior distribution. We construct a neural sampler that is trained with the functional gradient of the KL-divergence between the empirical sampling distribution and the target distribution, assuming the gradient resides within a reproducing kernel Hilbert space. Our generative ParVI (GPVI) approach maintains the asymptotic performance of ParVI methods while offering the flexibility of a generative sampler. Through carefully constructed experiments, we show that GPVI outperforms previous generative ParVI methods such as amortized SVGD, and is competitive with ParVI as well as gold-standard approaches like Hamiltonian Monte Carlo for fitting both exactly known and intractable target distributions.

cs.LG↗

arXiv2021

A Generalizable Model-and-Data Driven Approach for Open-Set RFF Authentication

Radio-frequency fingerprints~(RFFs) are promising solutions for realizing low-cost physical layer authentication. Machine learning-based methods have been proposed for RFF extraction and discrimination. However, most existing methods are designed for the closed-set scenario where the set of devices is remains unchanged. These methods can not be generalized to the RFF discrimination of unknown devices. To enable the discrimination of RFF from both known and unknown devices, we propose a new end-to-end deep learning framework for extracting RFFs from raw received signals. The proposed framework comprises a novel preprocessing module, called neural synchronization~(NS), which incorporates the data-driven learning with signal processing priors as an inductive bias from communication-model based processing. Compared to traditional carrier synchronization techniques, which are static, this module estimates offsets by two learnable deep neural networks jointly trained by the RFF extractor. Additionally, a hypersphere representation is proposed to further improve the discrimination of RFF. Theoretical analysis shows that such a data-and-model framework can better optimize the mutual information between device identity and the RFF, which naturally leads to better performance. Experimental results verify that the proposed RFF significantly outperforms purely data-driven DNN-design and existing handcrafted RFF methods in terms of both discrimination and network generalizability.

cs.LG↗

arXiv2021

The solution space structure of planted constraint satisfaction problems with growing domains

Planting a solution into the random RB model, which is a prototype of random constraint satisfaction problem (CSP) with growing domains, can generate very hard satisfiable CSP benchmarks. We study the solution space structure of the planted RB model. With constraint density growing, we find that this model goes through four phase transitions. In the replica symmetric phase, what we call the independent phase transition occurs, after which the planted cluster (cluster containing the planted solution) is separated from the giant cluster. Then the solutions except that in the planted cluster go through the same clustering phase transition and the same satisfiability phase transition as the random RB model. The planted cluster goes through the isolated phase transition, after which the planted cluster contains only one solution. This phase diagram provides strong evidence that this model can generate very hard satisfiable CSP benchmarks. For over constraint instances (where the constraint density is very large), we find that the configuration space has only a single energy valley, which makes the instances tractable. Experiments using Belief Propagation confirm the locations of the clustering, satisfiability (by configurations outside the planted cluster), and isolated phase transition points.

cond-mat.dis-nn↗

arXiv2021

Cooperative Reflection Design with Timing Offsets in Distributed Multi-RIS Communications

This letter investigates a wireless communication system deploying distributed reconfigurable intelligent surfaces (RISs). Existing works have assumed that perfect timing synchronization is available among all the cooperative RISs. For practical considerations, we first study cooperative reflection design for multi-RIS-aided communication systems taking into account timing synchronization errors. We aim to minimize the mean-squared error of the recovered data in the presence of timing offsets subject to the unit modulus constraints imposed on the phase shifts of the RISs. In order to handle this sophisticated nonconvex problem, we develop a computationally-efficient algorithm based on the majorization-minimization framework where the RIS phase shift matrices and the timing offset equalizer are respectively developed in a semi-closed form and a closed form. Numerical examples validate the improved performance of our proposed design compared with various schemes.

cs.IT↗

arXiv2021

VisDrone-CC2020: The Vision Meets Drone Crowd Counting Challenge Results

Crowd counting on the drone platform is an interesting topic in computer vision, which brings new challenges such as small object inference, background clutter and wide viewpoint. However, there are few algorithms focusing on crowd counting on the drone-captured data due to the lack of comprehensive datasets. To this end, we collect a large-scale dataset and organize the Vision Meets Drone Crowd Counting Challenge (VisDrone-CC2020) in conjunction with the 16th European Conference on Computer Vision (ECCV 2020) to promote the developments in the related fields. The collected dataset is formed by $3,360$ images, including $2,460$ images for training, and $900$ images for testing. Specifically, we manually annotate persons with points in each video frame. There are $14$ algorithms from $15$ institutes submitted to the VisDrone-CC2020 Challenge. We provide a detailed analysis of the evaluation results and conclude the challenge. More information can be found at the website: \url{http://www.aiskyeye.com/}.

cs.CV↗

arXiv2021

FAST-LIO2: Fast Direct LiDAR-inertial Odometry

This paper presents FAST-LIO2: a fast, robust, and versatile LiDAR-inertial odometry framework. Building on a highly efficient tightly-coupled iterated Kalman filter, FAST-LIO2 has two key novelties that allow fast, robust, and accurate LiDAR navigation (and mapping). The first one is directly registering raw points to the map (and subsequently update the map, i.e., mapping) without extracting features. This enables the exploitation of subtle features in the environment and hence increases the accuracy. The elimination of a hand-engineered feature extraction module also makes it naturally adaptable to emerging LiDARs of different scanning patterns; The second main novelty is maintaining a map by an incremental k-d tree data structure, ikd-Tree, that enables incremental updates (i.e., point insertion, delete) and dynamic re-balancing. Compared with existing dynamic data structures (octree, R*-tree, nanoflann k-d tree), ikd-Tree achieves superior overall performance while naturally supports downsampling on the tree. We conduct an exhaustive benchmark comparison in 19 sequences from a variety of open LiDAR datasets. FAST-LIO2 achieves consistently higher accuracy at a much lower computation load than other state-of-the-art LiDAR-inertial navigation systems. Various real-world experiments on solid-state LiDARs with small FoV are also conducted. Overall, FAST-LIO2 is computationally-efficient (e.g., up to 100 Hz odometry and mapping in large outdoor environments), robust (e.g., reliable pose estimation in cluttered indoor environments with rotation up to 1000 deg/s), versatile (i.e., applicable to both multi-line spinning and solid-state LiDARs, UAV and handheld platforms, and Intel and ARM-based processors), while still achieving higher accuracy than existing methods. Our implementation of the system FAST-LIO2, and the data structure ikd-Tree are both open-sourced on Github.

cs.RO↗

arXiv2021

Asymptotic Results for Rough Continuous-state Branching Processes

In this paper we provide explicit representations of Laplace transforms of extinction time and total progeny of rough continuous-state branching processes introduced in [7]. Also, we show that their tail distributions are much fatter than those of Feller branching diffusions.

math.PR↗

arXiv2021

Hawking-Page transition with reentrance and triple point in Gauss-Bonnet gravity

In this paper, a new family of Hawking-Page (HP) transition, the HP transition with reentrance and triple point is introduced for the first time, by investigating HP transition of hyperbolic AdS black hole in extended thermodynamics of general dimensional Gauss-Bonnet gravity. The Reentrant HP transition is composed of two HP transitions with a large and a small HP temperature, and the triple point corresponds to small black holes/massless black holes/large black holes (SBHs/MBHs/LBHs) phases all coexisting. We present the two branches of HP transition temperatures, which both depend on the pressure (i.e. the cosmological constant) and the Gauss-Bonnet constant. Besides, the pressure and the Gauss-Bonnet constant both enlarge the large HP temperature and diminish the small HP temperature. We also show the coexistence lines in the $P-T$ phase diagrams. The triple point and an up critical point in phase diagrams for arbitrary dimensional Gauss-Bonnet AdS black hole systems are given, together with some interesting universal relations which only depend on the dimensions of spacetime. We can explain the reentrant HP transition and triple point of SBHs/MBHs/LBHs as the phase transition and triple point of Hadronic matter/Quark-Gluon/Plasma/Quarkyonic matter in the QCD phase diagram. These results may improve the comprehension of the black hole thermodynamics in the quantum gravity framework and shed some light on the AdS/CFT correspondence beyond the classical gravity limit.

gr-qc↗

arXiv2021

Model Predictive Control for Trajectory Tracking on Differentiable Manifolds

We consider the problem of bridging the gap between geometric tracking control theory and implementation of model predictive control (MPC) for robotic systems operating on manifolds. We propose a generic on-manifold MPC formulation based on a canonical representation of the system evolving on manifolds. Then, we present a method that solves the on-manifold MPC formulation by linearizing the system along the trajectory under tracking. There are two main advantages of the proposed scheme. The first is that the linearized system leads to an equivalent error system represented by a set of minimal parameters without any singularity. Secondly, the process of system modeling, error-system derivation, linearization and control has the manifold constraints completely decoupled from the system descriptions, enabling the development of a symbolic MPC framework that naturally encapsulates the manifold constraints. In this framework, users need only to supply system-specific descriptions without dealing with the manifold constraints. We implement this framework and test it on a quadrotor unmanned aerial vehicle (UAV) operating on $SO(3) \times \mathbb{R}^n$ and an unmanned ground vehicle (UGV) moving on a curved surface. Real-world experiments show that the proposed framework and implementation achieve high tracking performance and computational efficiency even in highly aggressive aerobatic quadrotor maneuvers.

cs.RO↗

arXiv2021

Kalman Filters on Differentiable Manifolds

Kalman filter is presumably one of the most important and extensively used filtering techniques in modern control systems. Yet, nearly all current variants of Kalman filters are formulated in the Euclidean space $\mathbb{R}^n$, while many real-world systems (e.g., robotic systems) are really evolving on manifolds. In this paper, we propose a method to develop Kalman filters for such on-manifold systems. Utilizing $\boxplus$, $\boxminus$ operations and further defining an oplus operation on the respective manifold, we propose a canonical representation of the on-manifold system. Such a canonical form enables us to separate the manifold constraints from the system behaviors in each step of the Kalman filter, ultimately leading to a generic and symbolic Kalman filter framework that are naturally evolving on the manifold. Furthermore, the on-manifold Kalman filter is implemented as a toolkit in $C$++ packages which enables users to implement an on-manifold Kalman filter just like the normal one in $\mathbb{R}^n$: the user needs only to provide the system-specific descriptions, and then call the respective filter steps (e.g., predict, update) without dealing with any of the manifold constraints. The existing implementation supports full iterated Kalman filtering for systems on any manifold composed of $\mathbb{R}^n$, $SO(3)$ and $\mathbb{S}^2$, and is extendable to other types of manifold when necessary. The proposed symbolic Kalman filter and the developed toolkit are verified by implementing a tightly-coupled lidar-inertial navigation system. Results show that the developed toolkit leads to superior filtering performances and computation efficiency comparable to hand-engineered counterparts. Finally, the toolkit is opened sourced at https://github.com/hku-mars/IKFoM to assist practitioners to quickly deploy an on-manifold Kalman filter.

cs.RO↗