arXiv subjects

Zeyu Zhang

Publications and source records attributed to Zeyu Zhang.

At least 289 records · Page 16Linked to original sources

arXiv2022

Understanding Physical Effects for Effective Tool-use

We present a robot learning and planning framework that produces an effective tool-use strategy with the least joint efforts, capable of handling objects different from training. Leveraging a Finite Element Method (FEM)-based simulator that reproduces fine-grained, continuous visual and physical effects given observed tool-use events, the essential physical properties contributing to the effects are identified through the proposed Iterative Deepening Symbolic Regression (IDSR) algorithm. We further devise an optimal control-based motion planning scheme to integrate robot- and tool-specific kinematics and dynamics to produce an effective trajectory that enacts the learned properties. In simulation, we demonstrate that the proposed framework can produce more effective tool-use strategies, drastically different from the observed ones in two exemplar tasks.

cs.RO↗

arXiv2022

RecBole 2.0: Towards a More Up-to-Date Recommendation Library

In order to support the study of recent advances in recommender systems, this paper presents an extended recommendation library consisting of eight packages for up-to-date topics and architectures. First of all, from a data perspective, we consider three important topics related to data issues (i.e., sparsity, bias and distribution shift), and develop five packages accordingly: meta-learning, data augmentation, debiasing, fairness and cross-domain recommendation. Furthermore, from a model perspective, we develop two benchmarking packages for Transformer-based and graph neural network (GNN)-based models, respectively. All the packages (consisting of 65 new models) are developed based on a popular recommendation framework RecBole, ensuring that both the implementation and interface are unified. For each package, we provide complete implementations from data loading, experimental setup, evaluation and algorithm implementation. This library provides a valuable resource to facilitate the up-to-date research in recommender systems. The project is released at the link: https://github.com/RUCAIBox/RecBole2.0.

cs.IR↗

arXiv2022

Observation of Ultrafast Interfacial Exciton Formation and Recombination in Graphene/MoS2 Heterostructure

In this study,we combined time-resolved terahertz spectroscopy along with transient absorption spectroscopy to revisit the interlayer non-equilibrium carrier dynamics in largely lateral size Gr/MoS2 heterostructure fabricated with chemical vapor deposition method. Our experimental results reveal that, with photon-energy below the A-exciton of MoS2 monolayer, hot electrons transfer from graphene to MoS2 takes place in time scale of less than 0.5 ps, resulting in ultrafast formation of interfacial exciton in the heterostructure, subsequently, recombination relaxation of the interfacial exciton occurs in time scale of ~18 ps. A new model considering carrier heating and photogating effect in graphene is proposed to estimate the amount of carrier transfer in the heterostructure, which shows a good agreement with experimental result. Moreover, when the photon-energy is on-resonance with the A-exciton of MoS2, photogenerated holes in MoS2 are transferred to graphene layer within 0.5 ps, leading to the formation of interfacial exciton, the subsequent photoconductivity (PC) relaxation of graphene and bleaching recovery of A-exciton in MoS2 take place around ~10 ps time scale, ascribing to the interfacial exciton recombination. The faster recombination time of interfacial exciton with on-resonance excitation could come from the reduced interface barrier caused by bandgap renormalization effect. Our study provides deep insight into the understanding of interfacial charge transfer as well as the relaxation dynamics in graphene-based heterostructures, which are promising for the applications of graphene-based optoelectronic devices.

physics.optics↗

arXiv2022

Double Retrieval and Ranking for Accurate Question Answering

Recent work has shown that an answer verification step introduced in Transformer-based answer selection models can significantly improve the state of the art in Question Answering. This step is performed by aggregating the embeddings of top $k$ answer candidates to support the verification of a target answer. Although the approach is intuitive and sound still shows two limitations: (i) the supporting candidates are ranked only according to the relevancy with the question and not with the answer, and (ii) the support provided by the other answer candidates is suboptimal as these are retrieved independently of the target answer. In this paper, we address both drawbacks by proposing (i) a double reranking model, which, for each target answer, selects the best support; and (ii) a second neural retrieval stage designed to encode question and answer pair as the query, which finds more specific verification information. The results on three well-known datasets for AS2 show consistent and significant improvement of the state of the art.

cs.CL↗

arXiv2022

In Situ Answer Sentence Selection at Web-scale

Current answer sentence selection (AS2) applied in open-domain question answering (ODQA) selects answers by ranking a large set of possible candidates, i.e., sentences, extracted from the retrieved text. In this paper, we present Passage-based Extracting Answer Sentence In-place (PEASI), a novel design for AS2 optimized for Web-scale setting, that, instead, computes such answer without processing each candidate individually. Specifically, we design a Transformer-based framework that jointly (i) reranks passages retrieved for a question and (ii) identifies a probable answer from the top passages in place. We train PEASI in a multi-task learning framework that encourages feature sharing between the components: passage reranker and passage-based answer sentence extractor. To facilitate our development, we construct a new Web-sourced large-scale QA dataset consisting of 800,000+ labeled passages/sentences for 60,000+ questions. The experiments show that our proposed design effectively outperforms the current state-of-the-art setting for AS2, i.e., a point-wise model for ranking sentences independently, by 6.51% in accuracy, from 48.86% to 55.37%. In addition, PEASI is exceptionally efficient in computing answer sentences, requiring only ~20% inferences compared to the standard setting, i.e., reranking all possible candidates. We believe the release of PEASI, both the dataset and our proposed design, can contribute to advancing the research and development in deploying question answering services at Web scale.

cs.CL↗

arXiv2021

A Comparative Study on Robust Graph Neural Networks to Structural Noises

Graph neural networks (GNNs) learn node representations by passing and aggregating messages between neighboring nodes. GNNs have been applied successfully in several application domains and achieved promising performance. However, GNNs could be vulnerable to structural noise because of the message passing mechanism where noise may be propagated through the entire graph. Although a series of robust GNNs have been proposed, they are evaluated with different structural noises, and it lacks a systematic comparison with consistent settings. In this work, we conduct a comprehensive and systematical comparative study on different types of robust GNNs under consistent structural noise settings. From the noise aspect, we design three different levels of structural noises, i.e., local, community, and global noises. From the model aspect, we select some representative models from sample-based, revision-based, and construction-based robust GNNs. Based on the empirical results, we provide some practical suggestions for robust GNNs selection.

cs.LG↗

arXiv2021

Extending the spectrum of fully integrated photonics

Integrated photonics has profoundly impacted a wide range of technologies underpinning modern society. The ability to fabricate a complete optical system on a chip offers unrivalled scalability, weight, cost and power efficiency. Over the last decade, the progression from pure III-V materials platforms to silicon photonics has significantly broadened the scope of integrated photonics by combining integrated lasers with the high-volume, advanced fabrication capabilities of the commercial electronics industry. Yet, despite remarkable manufacturing advantages, reliance on silicon-based waveguides currently limits the spectral window available to photonic integrated circuits (PICs). Here, we present a new generation of integrated photonics by directly uniting III-V materials with silicon nitride (SiN) waveguides on Si wafers. Using this technology, we present the first fully integrated PICs at wavelengths shorter than silicon's bandgap, demonstrating essential photonic building blocks including lasers, photodetectors, modulators and passives, all operating at sub-um wavelengths. Using this platform, we achieve unprecedented coherence and tunability in an integrated laser at short wavelength. Furthermore, by making use of this higher photon energy, we demonstrate superb high temperature performance and, for the first time, kHz-level fundamental linewidths at elevated temperatures. Given the many potential applications at short wavelengths, the success of this integration strategy unlocks a broad range of new integrated photonics applications.

physics.optics↗

arXiv2021

Partial Symbol Recovery for Interference Resilience in Low-Power Wide Area Networks

Recent years have witnessed the proliferation of Low-power Wide Area Networks (LPWANs) in the unlicensed band for various Internet-of-Things (IoT) applications. Due to the ultra-low transmission power and long transmission duration, LPWAN devices inevitably suffer from high power Cross Technology Interference (CTI), such as interference from Wi-Fi, coexisting in the same spectrum. To alleviate this issue, this paper introduces the Partial Symbol Recovery (PSR) scheme for improving the CTI resilience of LPWAN. We verify our idea on LoRa, a widely adopted LPWAN technique, as a proof of concept. At the PHY layer, although CTI has much higher power, its duration is relatively shorter compared with LoRa symbols, leaving part of a LoRa symbol uncorrupted. Moreover, due to its high redundancy, LoRa chips within a symbol are highly correlated. This opens the possibility of detecting a LoRa symbol with only part of the chips. By examining the unique frequency patterns in LoRa symbols with time-frequency analysis, our design effectively detects the clean LoRa chips that are free of CTI. This enables PSR to only rely on clean LoRa chips for successfully recovering from communication failures. We evaluate our PSR design with real-world testbeds, including SX1280 LoRa chips and USRP B210, under Wi-Fi interference in various scenarios. Extensive experiments demonstrate that our design offers reliable packet recovery performance, successfully boosting the LoRa packet reception ratio from 45.2% to 82.2% with a performance gain of 1.8 times.

cs.NI↗

arXiv2021

Consolidating Kinematic Models to Promote Coordinated Mobile Manipulations

We construct a Virtual Kinematic Chain (VKC) that readily consolidates the kinematics of the mobile base, the arm, and the object to be manipulated in mobile manipulations. Accordingly, a mobile manipulation task is represented by altering the state of the constructed VKC, which can be converted to a motion planning problem, formulated, and solved by trajectory optimization. This new VKC perspective of mobile manipulation allows a service robot to (i) produce well-coordinated motions, suitable for complex household environments, and (ii) perform intricate multi-step tasks while interacting with multiple objects without an explicit definition of intermediate goals. In simulated experiments, we validate these advantages by comparing the VKC-based approach with baselines that solely optimize individual components. The results manifest that VKC-based joint modeling and planning promote task success rates and produce more efficient trajectories.

cs.RO↗

arXiv2021

Efficient Task Planning for Mobile Manipulation: a Virtual Kinematic Chain Perspective

We present a Virtual Kinematic Chain (VKC) perspective, a simple yet effective method, to improve task planning efficacy for mobile manipulation. By consolidating the kinematics of the mobile base, the arm, and the object being manipulated collectively as a whole, this novel VKC perspective naturally defines abstract actions and eliminates unnecessary predicates in describing intermediate poses. As a result, these advantages simplify the design of the planning domain and significantly reduce the search space and branching factors in solving planning problems. In experiments, we implement a task planner using Planning Domain Definition Language (PDDL) with VKC. Compared with conventional domain definition, our VKC-based domain definition is more efficient in both planning time and memory. In addition, abstract actions perform better in producing feasible motion plans and trajectories. We further scale up the VKC-based task planner in complex mobile manipulation tasks. Taken together, these results demonstrate that task planning using VKC for mobile manipulation is not only natural and effective but also introduces new capabilities.

cs.RO↗

arXiv2021

Joint Models for Answer Verification in Question Answering Systems

This paper studies joint models for selecting correct answer sentences among the top $k$ provided by answer sentence selection (AS2) modules, which are core components of retrieval-based Question Answering (QA) systems. Our work shows that a critical step to effectively exploit an answer set regards modeling the interrelated information between pair of answers. For this purpose, we build a three-way multi-classifier, which decides if an answer supports, refutes, or is neutral with respect to another one. More specifically, our neural architecture integrates a state-of-the-art AS2 model with the multi-classifier, and a joint layer connecting all components. We tested our models on WikiQA, TREC-QA, and a real-world dataset. The results show that our models obtain the new state of the art in AS2.

cs.CL↗

arXiv2021

Disorder-assisted Robustness of Ultrafast Cooling in High Doped CVD-Graphene

Dirac Fermion, which is the low energy collective excitation near the Dirac cone in monolayer graphene, have gained great attention by low energy Terahertz probe. In the case of undoped graphene, it has been generally understood that the ultrafast terahertz thermal relaxation is mostly driven by the electron-phonon coupling (EOP), which can be prolonged to tens and hundreds of picoseconds. However, for the high doped graphene, which manifests the negative photoinduced terahertz conductivity, there is still no consensus on the dominant aspects of the cooling process on a time scale of a few picoseconds. Here, the competition between the disorders assisted defect scattering and the electron-phonon coupling process in the cooling process of the graphene terahertz dynamics is systematically studied and disentangled. We verify experimentally that the ultrafast disorder assisted lattice-phonon interaction, rather than the electron-phonon coupling process, would play the key role in the ultrafast thermal relaxation of the terahertz dynamics. Furthermore, the cooling process features robustness which is independent on the pump wavelength and external temperature. Our finding is expected to propose a considerable possible cooling channel in CVD-graphene and to increase the hot electron extracting efficiency for the design of graphene-based photoconversion devices.

cond-mat.mes-hall↗

arXiv2021

Reconstructing Interactive 3D Scenes by Panoptic Mapping and CAD Model Alignments

In this paper, we rethink the problem of scene reconstruction from an embodied agent's perspective: While the classic view focuses on the reconstruction accuracy, our new perspective emphasizes the underlying functions and constraints such that the reconstructed scenes provide \em{actionable} information for simulating \em{interactions} with agents. Here, we address this challenging problem by reconstructing an interactive scene using RGB-D data stream, which captures (i) the semantics and geometry of objects and layouts by a 3D volumetric panoptic mapping module, and (ii) object affordance and contextual relations by reasoning over physical common sense among objects, organized by a graph-based scene representation. Crucially, this reconstructed scene replaces the object meshes in the dense panoptic map with part-based articulated CAD models for finer-grained robot interactions. In the experiments, we demonstrate that (i) our panoptic mapping module outperforms previous state-of-the-art methods, (ii) a high-performant physical reasoning procedure that matches, aligns, and replaces objects' meshes with best-fitted CAD models, and (iii) reconstructed scenes are physically plausible and naturally afford actionable interactions; without any manual labeling, they are seamlessly imported to ROS-based simulators and virtual environments for complex robot task executions.

cs.RO↗

arXiv2021

Laser soliton microcombs on silicon

Silicon photonics enables wafer-scale integration of optical functionalities on chip. A silicon-based laser frequency combs could significantly expand the applications of silicon photonics, by providing integrated sources of mutually coherent laser lines for terabit-per-second transceivers, parallel coherent LiDAR, or photonics-assisted signal processing. Here, we report on heterogeneously integrated laser soliton microcombs combining both InP/Si semiconductor lasers and ultralow-loss silicon nitride microresonators on monolithic silicon substrate. Thousands of devices are produced from a single wafer using standard CMOS techniques. Using on-chip electrical control of the microcomb-laser relative optical phase, these devices can output single-soliton microcombs with 100 GHz repetition rate. Our approach paves the way for large-volume, low-cost manufacturing of chip-based frequency combs for next-generation high-capacity transceivers, datacenters, space and mobile platforms.

physics.optics↗

arXiv2020

Human-Robot Interaction in a Shared Augmented Reality Workspace

We design and develop a new shared Augmented Reality (AR) workspace for Human-Robot Interaction (HRI), which establishes a bi-directional communication between human agents and robots. In a prototype system, the shared AR workspace enables a shared perception, so that a physical robot not only perceives the virtual elements in its own view but also infers the utility of the human agent--the cost needed to perceive and interact in AR--by sensing the human agent's gaze and pose. Such a new HRI design also affords a shared manipulation, wherein the physical robot can control and alter virtual objects in AR as an active agent; crucially, a robot can proactively interact with human agents, instead of purely passively executing received commands. In experiments, we design a resource collection game that qualitatively demonstrates how a robot perceives, processes, and manipulates in AR and quantitatively evaluates the efficacy of HRI using the shared AR workspace. We further discuss how the system can potentially benefit future HRI studies that are otherwise challenging.

cs.RO↗

arXiv2020

Unravelling Water Stability and Electrical Conductivity of 2D Layered Metal-Organic Frameworks in Aqueous Solutions

Molecular dynamics simulations combined with periodic electronic structure calculations are performed to decipher structural, thermodynamical and dynamical properties of the interfaced vs. confined water adsorbed in hexagonal 1D channels of the 2D layered electrically conductive Cu3(HHTP)2 and Cu3(HTTP)2 metal-organic frameworks (HHTP=2,3,6,7,10,11-hexahydroxytriphenylene and HTTP = 2,3,6,7,10,11-hexathiotriphenylene). Comparing water adsorption in bulk vs. slab models of the studied 2D MOFs shows that water is preferentially adsorbed on the framework walls via forming hydrogen bonds to the organic linkers rather than by coordinating to the coordinatively unsaturated open-Cu2+ sites. Theory predicts that in Cu3(HTTP)2 the van der Waals interactions are stronger which helps the MOF maintain its layered morphology with allowing very little water molecules to diffuse into the interlayer space. Data presented in this work are general and helpful in implementing new strategies for preserving the integrity as well as electrical conductivity of porous materials in aqueous solutions.

cond-mat.mtrl-sci↗

arXiv2020

Lineage Evolution Reinforcement Learning

We propose a general agent population learning system, and on this basis, we propose lineage evolution reinforcement learning algorithm. Lineage evolution reinforcement learning is a kind of derivative algorithm which accords with the general agent population learning system. We take the agents in DQN and its related variants as the basic agents in the population, and add the selection, mutation and crossover modules in the genetic algorithm to the reinforcement learning algorithm. In the process of agent evolution, we refer to the characteristics of natural genetic behavior, add lineage factor to ensure the retention of potential performance of agent, and comprehensively consider the current performance and lineage value when evaluating the performance of agent. Without changing the parameters of the original reinforcement learning algorithm, lineage evolution reinforcement learning can optimize different reinforcement learning algorithms. Our experiments show that the idea of evolution with lineage improves the performance of original reinforcement learning algorithm in some games in Atari 2600.

cs.NE↗

arXiv2020

Congestion-aware Evacuation Routing using Augmented Reality Devices

We present a congestion-aware routing solution for indoor evacuation, which produces real-time individual-customized evacuation routes among multiple destinations while keeping tracks of all evacuees' locations. A population density map, obtained on-the-fly by aggregating locations of evacuees from user-end Augmented Reality (AR) devices, is used to model the congestion distribution inside a building. To efficiently search the evacuation route among all destinations, a variant of A* algorithm is devised to obtain the optimal solution in a single pass. In a series of simulated studies, we show that the proposed algorithm is more computationally optimized compared to classic path planning algorithms; it generates a more time-efficient evacuation route for each individual that minimizes the overall congestion. A complete system using AR devices is implemented for a pilot study in real-world environments, demonstrating the efficacy of the proposed approach.

cs.HC↗