arXiv subjects

Pengyu Wang

Publications and source records attributed to Pengyu Wang.

At least 91 records · Page 5Linked to original sources

arXiv2023

Attitude Takeover Control for Noncooperative Space Targets Based on Gaussian Processes with Online Model Learning

One major challenge for autonomous attitude takeover control for on-orbit servicing of spacecraft is that an accurate dynamic motion model of the combined vehicles is highly nonlinear, complex and often costly to identify online, which makes traditional model-based control impractical for this task. To address this issue, a recursive online sparse Gaussian Process (GP)-based learning strategy for attitude takeover control of noncooperative targets with maneuverability is proposed, where the unknown dynamics are online compensated based on the learnt GP model in a semi-feedforward manner. The method enables the continuous use of on-orbit data to successively improve the learnt model during online operation and has reduced computational load compared to standard GP regression. Next to the GP-based feedforward, a feedback controller is proposed that varies its gains based on the predicted model confidence, ensuring robustness of the overall scheme. Moreover, rigorous theoretical proofs of Lyapunov stability and boundedness guarantees of the proposed method-driven closed-loop system are provided in the probabilistic sense. A simulation study based on a high-fidelity simulator is used to show the effectiveness of the proposed strategy and demonstrate its high performance.

eess.SY↗

arXiv2023

RVAE-EM: Generative speech dereverberation based on recurrent variational auto-encoder and convolutive transfer function

In indoor scenes, reverberation is a crucial factor in degrading the perceived quality and intelligibility of speech. In this work, we propose a generative dereverberation method. Our approach is based on a probabilistic model utilizing a recurrent variational auto-encoder (RVAE) network and the convolutive transfer function (CTF) approximation. Different from most previous approaches, the output of our RVAE serves as the prior of the clean speech. And our target is the maximum a posteriori (MAP) estimation of clean speech, which is achieved iteratively through the expectation maximization (EM) algorithm. The proposed method integrates the capabilities of network-based speech prior modelling and CTF-based observation modelling. Experiments on single-channel speech dereverberation show that the proposed generative method noticeably outperforms the advanced discriminative networks.

eess.AS↗

arXiv2023

Watermarking LLMs with Weight Quantization

Abuse of large language models reveals high risks as large language models are being deployed at an astonishing speed. It is important to protect the model weights to avoid malicious usage that violates licenses of open-source large language models. This paper proposes a novel watermarking strategy that plants watermarks in the quantization process of large language models without pre-defined triggers during inference. The watermark works when the model is used in the fp32 mode and remains hidden when the model is quantized to int8, in this way, the users can only inference the model without further supervised fine-tuning of the model. We successfully plant the watermark into open-source large language model weights including GPT-Neo and LLaMA. We hope our proposed method can provide a potential direction for protecting model weights in the era of large language model applications.

cs.CL↗

arXiv2023

PerturbScore: Connecting Discrete and Continuous Perturbations in NLP

With the rapid development of neural network applications in NLP, model robustness problem is gaining more attention. Different from computer vision, the discrete nature of texts makes it more challenging to explore robustness in NLP. Therefore, in this paper, we aim to connect discrete perturbations with continuous perturbations, therefore we can use such connections as a bridge to help understand discrete perturbations in NLP models. Specifically, we first explore how to connect and measure the correlation between discrete perturbations and continuous perturbations. Then we design a regression task as a PerturbScore to learn the correlation automatically. Through experimental results, we find that we can build a connection between discrete and continuous perturbations and use the proposed PerturbScore to learn such correlation, surpassing previous methods used in discrete perturbation measuring. Further, the proposed PerturbScore can be well generalized to different datasets, perturbation methods, indicating that we can use it as a powerful tool to study model robustness in NLP.

cs.CL↗

arXiv2023

The Uncertainty-based Retrieval Framework for Ancient Chinese CWS and POS

Automatic analysis for modern Chinese has greatly improved the accuracy of text mining in related fields, but the study of ancient Chinese is still relatively rare. Ancient text division and lexical annotation are important parts of classical literature comprehension, and previous studies have tried to construct auxiliary dictionary and other fused knowledge to improve the performance. In this paper, we propose a framework for ancient Chinese Word Segmentation and Part-of-Speech Tagging that makes a twofold effort: on the one hand, we try to capture the wordhood semantics; on the other hand, we re-predict the uncertain samples of baseline model by introducing external knowledge. The performance of our architecture outperforms pre-trained BERT with CRF and existing tools such as Jiayan.

cs.CL↗

arXiv2023

Robust magnetism against pressure in non-superconducting samples prepared from lutetium foil and H2/N2 gas mixture

Recently, the claim of "near-ambient superconductivity" in a N-doped lutetium hydride attracted enormous following-up investigations in the community of condensed matter physics and material sciences. But quite soon, the experimental results from different groups indicate consistently that no evidence of near-ambient superconductivity is found in the samples synthesized by the same method as the reported one, or by the other alternative methods. From our extended high-pressure heat capacity and magnetic susceptibility measurements on the samples prepared with the lutetium foil and H2/N2 gas mixture, we report the finding of a magnetic transition at the temperature about 56 K. Our results show that this magnetic phase is robust against pressure up to 4.3 GPa, which covers the critical pressure of boosting the claimed near room temperature superconductivity.

cond-mat.supr-con↗

arXiv2023

SpeechGPT: Empowering Large Language Models with Intrinsic Cross-Modal Conversational Abilities

Multi-modal large language models are regarded as a crucial step towards Artificial General Intelligence (AGI) and have garnered significant interest with the emergence of ChatGPT. However, current speech-language models typically adopt the cascade paradigm, preventing inter-modal knowledge transfer. In this paper, we propose SpeechGPT, a large language model with intrinsic cross-modal conversational abilities, capable of perceiving and generating multi-model content. With discrete speech representations, we first construct SpeechInstruct, a large-scale cross-modal speech instruction dataset. Additionally, we employ a three-stage training strategy that includes modality-adaptation pre-training, cross-modal instruction fine-tuning, and chain-of-modality instruction fine-tuning. The experimental results demonstrate that SpeechGPT has an impressive capacity to follow multi-modal human instructions and highlight the potential of handling multiple modalities with one model. Demos are shown in https://0nutation.github.io/SpeechGPT.github.io/.

cs.CL↗

arXiv2023

Origin Tracing and Detecting of LLMs

The extraordinary performance of large language models (LLMs) heightens the importance of detecting whether the context is generated by an AI system. More importantly, while more and more companies and institutions release their LLMs, the origin can be hard to trace. Since LLMs are heading towards the time of AGI, similar to the origin tracing in anthropology, it is of great importance to trace the origin of LLMs. In this paper, we first raise the concern of the origin tracing of LLMs and propose an effective method to trace and detect AI-generated contexts. We introduce a novel algorithm that leverages the contrastive features between LLMs and extracts model-wise features to trace the text origins. Our proposed method works under both white-box and black-box settings therefore can be widely generalized to detect various LLMs.(e.g. can be generalized to detect GPT-3 models without the GPT-3 models). Also, our proposed method requires only limited data compared with the supervised learning methods and can be extended to trace new-coming model origins. We construct extensive experiments to examine whether we can trace the origins of given texts. We provide valuable observations based on the experimental results, such as the difficulty level of AI origin tracing, and the AI origin similarities, and call for ethical concerns of LLM providers. We are releasing all codes and data as a toolkit and benchmark for future AI origin tracing and detecting studies. \footnote{We are releasing all available resource at \url{https://github.com/OpenLMLab/}.}

cs.CL↗

arXiv2023

No evidence of superconductivity in the compressed sample prepared from the lutetium foil and H2/N2 gas mixture

A material described as lutetium-hydrogen-nitrogen (Lu-H-N in short) was recently claimed to have near-ambient superconductivity[Gammon et al, Nature 615, 244, 2023]. If the results could be reproduced by other teams, it would be a major scientific breakthrough. Here, we report our results of transport and structure measurements on a material prepared using the same method as that reported by Gammon et al. Our X-ray diffraction measurements indicated that the obtained sample contained three substances: the FCC-1 phase (Fm-3m) with a lattice parameter a=5.03 Å, the FCC-2 phase (Fm-3m) with a lattice parameter a= 4.755 Å and Lu metal. These two FCC phases are identical to the those reported in the so-called near-ambient superconductor. However, we found that the samples had no evidence of superconductivity, through our resistance measurements in the temperature range of 300 - 4 K and pressure range of 0.9 - 3.4 GPa, and our magnetic susceptibility measurements in the pressure range of 0.8-3.3 GPa and temperature down to 100 K. We also used a laser heating technique to heat the sample to 1800°C and found no superconductivity in the produced dark blue samples below 6.5 GPa. In addition, the color of the both samples remain dark blue in the pressure range investigated.

cond-mat.supr-con↗

arXiv2023

The breakdown of both strange metal and superconducting states at a pressure-induced quantum critical point in iron-pnictide superconductors

The strange metal (SM) state, characterized by a linear-in-temperature resistivity, is often seen in the normal state of high temperature superconductors. It is believed that the SM state is one of the keys to understand the underlying mechanism of high-Tc superconductivity. Here we report the first observation of the concurrent breakdown of the SM normal state and superconductivity at a pressure-induced quantum critical point in an iron-pnictide superconductor, Ca10(Pt4As8)((Fe0.97Pt0.03)2As2)5. We find that, upon suppressing the superconducting state by applying pressure, the power exponent changes from 1 to 2, and the corresponding coefficient A, the slope of the temperature-linear resistivity per FeAs layer, gradually diminishes. At a critical pressure (12.5 GPa), A and Tc go to zero concurrently,where a quantum phase transition (QPT) from a superconducting state with a SM normal state to a non-superconducting Fermi liquid state takes place. Scaling analysis on the results obtained from the pressurized 1048 superconductor reveals that A and Tc have a positive relation, which exhibits a similarity with that is seen in other chemically-doped unconventional superconductors, regardless of the type of the tuning method (doping or pressurizing), the crystal structure, the bulk or film superconductors and the nature of dopant. These results suggest that there is a simple but powerful organizational principle of connecting the SM normal state with the high-Tc superconductivity.

cond-mat.supr-con↗

arXiv2023

Pressure-induced coevolution of transport properties and lattice stability in CaK(Fe1-xNix)4As4 (x= 0.04 and 0) superconductors with and without spin-vortex crystal state

Here we report the first investigation on correlation between the transport properties and the corresponding stability of the lattice structure for CaK(Fe1-xNix)4As4 (x=0.04 and 0), a new type of putative topological superconductors, with and without a spin-vortex crystal (SVC) state in a wide pressure range involving superconducting to non-superconducting transition and the half- to full-collapse of tetragonal (h-cT and f-cT) phases, by the complementary measurements of high-pressure resistance, Hall coefficient and synchrotron X-ray diffraction. We identify the three critical pressures, P1 that is the turn-on critical pressure of the h-cT phase transition and it coincides with the critical pressure for the sign change of Hall coefficient from positive to negative, a manifestation of the Fermi surface reconstruction, P2 that is the turn-off pressures of the h-cT phase transition, and P3 that is the critical pressure of the f-cT phase transition. By comparing the high-pressure results measured from the two kinds of samples, we find a distinct left-shift of the P1 for the doped sample, at the pressure of which its SVC state is fully suppressed, however the P2 and the P3 remain the same as that of the undoped one. Our results not only provide a consistent understanding on the results reported before, but also demonstrate the importance of the Fe-As bonding in stabilizing the superconductivity of the iron pnictide superconductors through the pressure window.

cond-mat.supr-con↗

arXiv2022

Learning For Predictive Control: A Dual Gaussian Process Approach

An important issue in model-based control design is that an accurate dynamic model of the system is generally nonlinear, complex, and costly to obtain. This limits achievable control performance in practice. Gaussian process (GP) based estimation of system models is an effective tool to learn unknown dynamics directly from input/output data. However, conventional GP-based control methods often ignore the computational cost associated with accumulating data during the operation of the system and how to handle forgetting in continuous adaption. In this paper, we present a novel Dual Gaussian Process (DGP) based model predictive control (MPC) strategy that enables efficient use of online learning based predictive control without the danger of catastrophic forgetting. The bio-inspired DGP structure is a combination of a long-term GP and a short-term GP, where the long-term GP is used to keep the learned knowledge in memory and the short-term GP is employed to rapidly compensate unknown dynamics during online operation. Furthermore, a novel recursive online update strategy for the short-term GP is proposed to successively improve the learnt model during online operation. Effectiveness of the proposed strategy is demonstrated via numerical simulations.

eess.SY↗

arXiv2022

Quadrotor Autonomous Landing on Moving Platform

This paper introduces a quadrotor's autonomous take-off and landing system on a moving platform. The designed system addresses three challenging problems: fast pose estimation, restricted external localization, and effective obstacle avoidance. Specifically, first, we design a landing recognition and positioning system based on the AruCo marker to help the quadrotor quickly calculate the relative pose; second, we leverage a gradient-based local motion planner to generate collision-free reference trajectories rapidly for the quadrotor; third, we build an autonomous state machine that enables the quadrotor to complete its take-off, tracking and landing tasks in full autonomy; finally, we conduct experiments in simulated, real-world indoor and outdoor environments to verify the system's effectiveness and demonstrate its potential.

cs.RO↗

arXiv2022

In-plane anisotropic response to the uniaxial pressure in the hidden order state of URu$_2$Si$_2$

We studied the uniaxial-pressure dependence of the resistivity for URu$_{2-x}$Fe$_x$Si$_2$ samples with $x$ = 0 and 0.2, which host a hidden order (HO) and a large-moment antiferromagnetic (LMAFM) phase, respectively. For both samples, the elastoresistivity $ζ$ shows a seemingly divergent behavior above the transition temperature $T_0$ and a quick decrease below it. We found that the temperature dependence of $ζ$ for both samples can be well described by assuming the uniaxial pressure effect on the gap or certain energy scale except for $ζ_{(110)}$ of the $x$ = 0 sample, which exhibits a non-zero residual value at 0 K. We show that this provides a qualitative difference between the HO and LMAFM phases. Our results suggest that there is an in-plane anisotropic response to the uniaxial pressure that only exists in the hidden order state without necessarily breaking the rotational lattice symmetry.

cond-mat.str-el↗

arXiv2021

EventHPE: Event-based 3D Human Pose and Shape Estimation

Event camera is an emerging imaging sensor for capturing dynamics of moving objects as events, which motivates our work in estimating 3D human pose and shape from the event signals. Events, on the other hand, have their unique challenges: rather than capturing static body postures, the event signals are best at capturing local motions. This leads us to propose a two-stage deep learning approach, called EventHPE. The first-stage, FlowNet, is trained by unsupervised learning to infer optical flow from events. Both events and optical flow are closely related to human body dynamics, which are fed as input to the ShapeNet in the second stage, to estimate 3D human shapes. To mitigate the discrepancy between image-based flow (optical flow) and shape-based flow (vertices movement of human body shape), a novel flow coherence loss is introduced by exploiting the fact that both flows are originated from the identical human motion. An in-house event-based 3D human dataset is curated that comes with 3D pose and shape annotations, which is by far the largest one to our knowledge. Empirical evaluations on DHP19 dataset and our in-house dataset demonstrate the effectiveness of our approach.

cs.CV↗

arXiv2019

A New Automatic Tool for CME Detection and Tracking with Machine Learning Techniques

With the accumulation of big data of CME observations by coronagraphs, automatic detection and tracking of CMEs has proven to be crucial. The excellent performance of convolutional neural network in image classification, object detection and other computer vision tasks motivates us to apply it to CME detection and tracking as well. We have developed a new tool for CME Automatic detection and tracking with MachinE Learning (CAMEL) techniques. The system is a three-module pipeline. It is first a supervised image classification problem. We solve it by training a neural network LeNet with training labels obtained from an existing CME catalog. Those images containing CME structures are flagged as CME images. Next, to identify the CME region in each CME-flagged image, we use deep descriptor transforming to localize the common object in an image set. A following step is to apply the graph cut technique to finely tune the detected CME region. To track the CME in an image sequence, the binary images with detected CME pixels are converted from cartesian to polar coordinate. A CME event is labeled if it can move in at least two frames and reach the edge of coronagraph field of view. For each event, a few fundamental parameters are derived. The results of four representative CMEs with various characteristics are presented and compared with those from four existing automatic and manual catalogs. We find that CAMEL can detect more complete and weaker structures, and has better performance to catch a CME as early as possible.

astro-ph.SR↗

arXiv2018

3D Shape Segmentation via Shape Fully Convolutional Networks

We desgin a novel fully convolutional network architecture for shapes, denoted by Shape Fully Convolutional Networks (SFCN). 3D shapes are represented as graph structures in the SFCN architecture, based on novel graph convolution and pooling operations, which are similar to convolution and pooling operations used on images. Meanwhile, to build our SFCN architecture in the original image segmentation fully convolutional network (FCN) architecture, we also design and implement a generating operation} with bridging function. This ensures that the convolution and pooling operation we have designed can be successfully applied in the original FCN architecture. In this paper, we also present a new shape segmentation approach based on SFCN. Furthermore, we allow more general and challenging input, such as mixed datasets of different categories of shapes} which can prove the ability of our generalisation. In our approach, SFCNs are trained triangles-to-triangles by using three low-level geometric features as input. Finally, the feature voting-based multi-label graph cuts is adopted to optimise the segmentation results obtained by SFCN prediction. The experiment results show that our method can effectively learn and predict mixed shape datasets of either similar or different characteristics, and achieve excellent segmentation results.

cs.CV↗

arXiv2017

Large-Scale 3D Shape Reconstruction and Segmentation from ShapeNet Core55

We introduce a large-scale 3D shape understanding benchmark using data and annotation from ShapeNet 3D object database. The benchmark consists of two tasks: part-level segmentation of 3D shapes and 3D reconstruction from single view images. Ten teams have participated in the challenge and the best performing teams have outperformed state-of-the-art approaches on both tasks. A few novel deep learning architectures have been proposed on various 3D representations on both tasks. We report the techniques used by each team and the corresponding performances. In addition, we summarize the major discoveries from the reported results and possible trends for the future work in the field.

cs.CV↗