arXiv subjects

Xing Li

Publications and source records attributed to Xing Li.

At least 73 records · Page 4Linked to original sources

arXiv2024

A Biologically Inspired Design Principle for Building Robust Robotic Systems

Robustness, the ability of a system to maintain performance under significant and unanticipated environmental changes, is a critical property for robotic systems. While biological systems naturally exhibit robustness, there is no comprehensive understanding of how to achieve similar robustness in robotic systems. In this work, we draw inspirations from biological systems and propose a design principle that advocates active interconnections among system components to enhance robustness to environmental variations. We evaluate this design principle in a challenging long-horizon manipulation task: solving lockboxes. Our extensive simulated and real-world experiments demonstrate that we could enhance robustness against environmental changes by establishing active interconnections among system components without substantial changes in individual components. Our findings suggest that a systematic investigation of design principles in system building is necessary. It also advocates for interdisciplinary collaborations to explore and evaluate additional principles of biological robustness to advance the development of intelligent and adaptable robotic systems.

cs.RO↗

arXiv2024

Logic Synthesis with Generative Deep Neural Networks

While deep learning has achieved significant success in various domains, its application to logic circuit design has been limited due to complex constraints and strict feasibility requirement. However, a recent generative deep neural model, "Circuit Transformer", has shown promise in this area by enabling equivalence-preserving circuit transformation on a small scale. In this paper, we introduce a logic synthesis rewriting operator based on the Circuit Transformer model, named "ctrw" (Circuit Transformer Rewriting), which incorporates the following techniques: (1) a two-stage training scheme for the Circuit Transformer tailored for logic synthesis, with iterative improvement of optimality through self-improvement training; (2) integration of the Circuit Transformer with state-of-the-art rewriting techniques to address scalability issues, allowing for guided DAG-aware rewriting. Experimental results on the IWLS 2023 contest benchmark demonstrate the effectiveness of our proposed rewriting methods.

cs.LO↗

arXiv2024

Real-time 3D human action recognition based on Hyperpoint sequence

Real-time 3D human action recognition has broad industrial applications, such as surveillance, human-computer interaction, and healthcare monitoring. By relying on complex spatio-temporal local encoding, most existing point cloud sequence networks capture spatio-temporal local structures to recognize 3D human actions. To simplify the point cloud sequence modeling task, we propose a lightweight and effective point cloud sequence network referred to as SequentialPointNet for real-time 3D action recognition. Instead of capturing spatio-temporal local structures, SequentialPointNet encodes the temporal evolution of static appearances to recognize human actions. Firstly, we define a novel type of point data, Hyperpoint, to better describe the temporally changing human appearances. A theoretical foundation is provided to clarify the information equivalence property for converting point cloud sequences into Hyperpoint sequences. Secondly, the point cloud sequence modeling task is decomposed into a Hyperpoint embedding task and a Hyperpoint sequence modeling task. Specifically, for Hyperpoint embedding, the static point cloud technology is employed to convert point cloud sequences into Hyperpoint sequences, which introduces inherent frame-level parallelism; for Hyperpoint sequence modeling, a Hyperpoint-Mixer module is designed as the basic building block to learning the spatio-temporal features of human actions. Extensive experiments on three widely-used 3D action recognition datasets demonstrate that the proposed SequentialPointNet achieves competitive classification performance with up to 10X faster than existing approaches.

cs.CV↗

arXiv2024

Red-shift effect on the zero field splitting for negatively charged nitrogen-vacancy centers in diamond

The zero field splitting (ZFS) quantifies the energy difference for the ground electron spin-triplet of a nitrogen-vacancy center in the absence of external fields. The values of the ZFS play a key role in determining the Larmor precession of the Bloch sphere and the Rabi oscillation of a spin system. The ZFS is generally detected using coherent spin manipulation by sweeping microwaves (MWs) at frequencies close to resonance with the ZFS. In this letter, we report our experimental observations of the red-shift effect on the ZFS as a function of the MW power for two different thermal environments of a sample. We find an asymptotic property of the red shifts of the ZFS. Given the identical initial thermal equilibrium states of the sample, the differences in the raw values of the ZFS between the two cases randomly vary from 47 kHz to 1505 kHz over the entire experimental range. According to the asymptotic approximation, the differences are reduced to 29-166 kHz with a standard deviation of 49 kHz, suggesting a significant elimination of the red-shift effect. To the best of our knowledge, no other study has addressed the quantification and elimination of the red shift-effect of the MW field dependence using the asymptotic approximation.

physics.app-ph↗

arXiv2024

StreamVC: Real-Time Low-Latency Voice Conversion

We present StreamVC, a streaming voice conversion solution that preserves the content and prosody of any source speech while matching the voice timbre from any target speech. Unlike previous approaches, StreamVC produces the resulting waveform at low latency from the input signal even on a mobile platform, making it applicable to real-time communication scenarios like calls and video conferencing, and addressing use cases such as voice anonymization in these scenarios. Our design leverages the architecture and training strategy of the SoundStream neural audio codec for lightweight high-quality speech synthesis. We demonstrate the feasibility of learning soft speech units causally, as well as the effectiveness of supplying whitened fundamental frequency information to improve pitch stability without leaking the source timbre information.

eess.AS↗

arXiv2023

Multiscale Motion-Aware and Spatial-Temporal-Channel Contextual Coding Network for Learned Video Compression

Recently, learned video compression has achieved exciting performance. Following the traditional hybrid prediction coding framework, most learned methods generally adopt the motion estimation motion compensation (MEMC) method to remove inter-frame redundancy. However, inaccurate motion vector (MV) usually lead to the distortion of reconstructed frame. In addition, most approaches ignore the spatial and channel redundancy. To solve above problems, we propose a motion-aware and spatial-temporal-channel contextual coding based video compression network (MASTC-VC), which learns the latent representation and uses variational autoencoders (VAEs) to capture the characteristics of intra-frame pixels and inter-frame motion. Specifically, we design a multiscale motion-aware module (MS-MAM) to estimate spatial-temporal-channel consistent motion vector by utilizing the multiscale motion prediction information in a coarse-to-fine way. On the top of it, we further propose a spatial-temporal-channel contextual module (STCCM), which explores the correlation of latent representation to reduce the bit consumption from spatial, temporal and channel aspects respectively. Comprehensive experiments show that our proposed MASTC-VC is surprior to previous state-of-the-art (SOTA) methods on three public benchmark datasets. More specifically, our method brings average 10.15\% BD-rate savings against H.265/HEVC (HM-16.20) in PSNR metric and average 23.93\% BD-rate savings against H.266/VVC (VTM-13.2) in MS-SSIM metric.

eess.IV↗

arXiv2023

SGDP: A Stream-Graph Neural Network Based Data Prefetcher

Data prefetching is important for storage system optimization and access performance improvement. Traditional prefetchers work well for mining access patterns of sequential logical block address (LBA) but cannot handle complex non-sequential patterns that commonly exist in real-world applications. The state-of-the-art (SOTA) learning-based prefetchers cover more LBA accesses. However, they do not adequately consider the spatial interdependencies between LBA deltas, which leads to limited performance and robustness. This paper proposes a novel Stream-Graph neural network-based Data Prefetcher (SGDP). Specifically, SGDP models LBA delta streams using a weighted directed graph structure to represent interactive relations among LBA deltas and further extracts hybrid features by graph neural networks for data prefetching. We conduct extensive experiments on eight real-world datasets. Empirical results verify that SGDP outperforms the SOTA methods in terms of the hit ratio by 6.21%, the effective prefetching ratio by 7.00%, and speeds up inference time by 3.13X on average. Besides, we generalize SGDP to different variants by different stream constructions, further expanding its application scenarios and demonstrating its robustness. SGDP offers a novel data prefetching solution and has been verified in commercial hybrid storage systems in the experimental phase. Our codes and appendix are available at https://github.com/yyysjz1997/SGDP/.

cs.OS↗

arXiv2023

A Circuit Domain Generalization Framework for Efficient Logic Synthesis in Chip Design

Logic Synthesis (LS) plays a vital role in chip design -- a cornerstone of the semiconductor industry. A key task in LS is to transform circuits -- modeled by directed acyclic graphs (DAGs) -- into simplified circuits with equivalent functionalities. To tackle this task, many LS operators apply transformations to subgraphs -- rooted at each node on an input DAG -- sequentially. However, we found that a large number of transformations are ineffective, which makes applying these operators highly time-consuming. In particular, we notice that the runtime of the Resub and Mfs2 operators often dominates the overall runtime of LS optimization processes. To address this challenge, we propose a novel data-driven LS operator paradigm, namely PruneX, to reduce ineffective transformations. The major challenge of developing PruneX is to learn models that well generalize to unseen circuits, i.e., the out-of-distribution (OOD) generalization problem. Thus, the major technical contribution of PruneX is the novel circuit domain generalization framework, which learns domain-invariant representations based on the transformation-invariant domain-knowledge. To the best of our knowledge, PruneX is the first approach to tackle the OOD problem in LS operators. We integrate PruneX with the aforementioned Resub and Mfs2 operators. Experiments demonstrate that PruneX significantly improves their efficiency while keeping comparable optimization performance on industrial and very large-scale circuits, achieving up to $3.1\times$ faster runtime.

cs.AR↗

arXiv2023

The Lamé functions and elliptic soliton solutions: Bilinear approach

The Lamé function can be used to construct plane wave factors and solutions to the Korteweg-de Vries (KdV) and Kadomtsev-Petviashvili (KP) hierarchy. The solutions are usually called elliptic solitons. In this chapter, first, we review recent development in the Hirota bilinear method on elliptic solitons of the KdV equation and KP equation, including bilinear calculations involved with the Lamé type plane wave factors, expressions of $τ$ functions and the generating vertex operators. Then, for the discrete potential KdV and KP equations, we give their bilinear forms, derive $τ$ functions of elliptic solitons, and show that they share the same vertex operators with the KdV hierarchy and the KP hierarchy, respectively.

nlin.SI↗

arXiv2023

Superconductivity in graphite intercalation compounds with sodium

The discovery of superconductivity in CaC6 with a critical temperature (Tc) of 11.5 K reignites much interest in exploring high-temperature superconductivity in graphite intercalation compounds (GICs). Here we identify a GIC NaC4, discovered by ab initio evolutionary structure search, as a superconductor with a computed Tc of 41.2 K at 5 GPa. This value is eight times higher than that of the synthesized GIC NaC2 and possesses the highest Tc among available GICs. The remarkable superconductivity of GIC NaC4 mainly arises from the coupling of π electrons in graphene with the low-frequency vibrations involving both Na and C atoms. These findings suggest that Na-GICs may hold great promise as high-Tc superconductors.

cond-mat.supr-con↗

arXiv2023

GAT-COBO: Cost-Sensitive Graph Neural Network for Telecom Fraud Detection

Along with the rapid evolution of mobile communication technologies, such as 5G, there has been a drastically increase in telecom fraud, which significantly dissipates individual fortune and social wealth. In recent years, graph mining techniques are gradually becoming a mainstream solution for detecting telecom fraud. However, the graph imbalance problem, caused by the Pareto principle, brings severe challenges to graph data mining. This is a new and challenging problem, but little previous work has been noticed. In this paper, we propose a Graph ATtention network with COst-sensitive BOosting (GAT-COBO) for the graph imbalance problem. First, we design a GAT-based base classifier to learn the embeddings of all nodes in the graph. Then, we feed the embeddings into a well-designed cost-sensitive learner for imbalanced learning. Next, we update the weights according to the misclassification cost to make the model focus more on the minority class. Finally, we sum the node embeddings obtained by multiple cost-sensitive learners to obtain a comprehensive node representation, which is used for the downstream anomaly detection task. Extensive experiments on two real-world telecom fraud detection datasets demonstrate that our proposed method is effective for the graph imbalance problem, outperforming the state-of-the-art GNNs and GNN-based fraud detectors. In addition, our model is also helpful for solving the widespread over-smoothing problem in GNNs. The GAT-COBO code and datasets are available at https://github.com/xxhu94/GAT-COBO.

cs.LG↗

arXiv2023

Cost Sensitive GNN-based Imbalanced Learning for Mobile Social Network Fraud Detection

With the rapid development of mobile networks, the people's social contacts have been considerably facilitated. However, the rise of mobile social network fraud upon those networks, has caused a great deal of distress, in case of depleting personal and social wealth, then potentially doing significant economic harm. To detect fraudulent users, call detail record (CDR) data, which portrays the social behavior of users in mobile networks, has been widely utilized. But the imbalance problem in the aforementioned data, which could severely hinder the effectiveness of fraud detectors based on graph neural networks(GNN), has hardly been addressed in previous work. In this paper, we are going to present a novel Cost-Sensitive Graph Neural Network (CSGNN) by creatively combining cost-sensitive learning and graph neural networks. We conduct extensive experiments on two open-source realworld mobile network fraud datasets. The results show that CSGNN can effectively solve the graph imbalance problem and then achieve better detection performance than the state-of-the-art algorithms. We believe that our research can be applied to solve the graph imbalance problems in other fields. The CSGNN code and datasets are publicly available at https://github.com/xxhu94/CSGNN.

cs.SI↗

arXiv2023

Anonymous Pattern Molecular Fingerprint and its Applications on Property Identification

Molecular fingerprints are significant cheminformatics tools to map molecules into vectorial space according to their characteristics in diverse functional groups, atom sequences, and other topological structures. In this paper, we set out to investigate a novel molecular fingerprint \emph{Anonymous-FP} that possesses abundant perception about the underlying interactions shaped in small, medium, and large molecular scale links. In detail, the possible inherent atom chains are sampled from each molecule and are extended in a certain anonymous pattern. After that, the molecular fingerprint \emph{Anonymous-FP} is encoded in virtue of the Natural Language Processing technique \emph{PV-DBOW}. \emph{Anonymous-FP} is studied on molecular property identification and has shown valuable advantages such as rich information content, high experimental performance, and full structural significance. During the experimental verification, the scale of the atom chain or its anonymous manner matters significantly to the overall representation ability of \emph{Anonymous-FP}. Generally, the typical scale $r = 8$ enhances the performance on a series of real-world molecules, and specifically, the accuracy could level up to above $93\%$ on all NCI datasets.

stat.AP↗

arXiv2022

Pixel2ISDF: Implicit Signed Distance Fields based Human Body Model from Multi-view and Multi-pose Images

In this report, we focus on reconstructing clothed humans in the canonical space given multiple views and poses of a human as the input. To achieve this, we utilize the geometric prior of the SMPLX model in the canonical space to learn the implicit representation for geometry reconstruction. Based on the observation that the topology between the posed mesh and the mesh in the canonical space are consistent, we propose to learn latent codes on the posed mesh by leveraging multiple input images and then assign the latent codes to the mesh in the canonical space. Specifically, we first leverage normal and geometry networks to extract the feature vector for each vertex on the SMPLX mesh. Normal maps are adopted for better generalization to unseen images compared to 2D images. Then, features for each vertex on the posed mesh from multiple images are integrated by MLPs. The integrated features acting as the latent code are anchored to the SMPLX mesh in the canonical space. Finally, latent code for each 3D point is extracted and utilized to calculate the SDF. Our work for reconstructing the human shape on canonical pose achieves 3rd performance on WCPA MVP-Human Body Challenge.

cs.CV↗

arXiv2022

Augmentation for Learning From Demonstration with Environmental Constraints

We introduce a Learning from Demonstration (LfD) approach for contact-rich manipulation tasks with articulated mechanisms. The extracted policy from a single human demonstration generalizes to different mechanisms of the same type and is robust against environmental variations. The key to achieving such generalization and robustness from a single human demonstration is to autonomously augment the initial demonstration to gather additional information through purposefully interacting with the environment. Our real-world experiments on complex mechanisms with multi-DOF demonstrate that our approach can reliably accomplish the task in a changing environment. Videos are available at the: https://sites.google.com/view/rbosalfdec/home

cs.RO↗

arXiv2022

Parameter Convex Neural Networks

Deep learning utilizing deep neural networks (DNNs) has achieved a lot of success recently in many important areas such as computer vision, natural language processing, and recommendation systems. The lack of convexity for DNNs has been seen as a major disadvantage of many optimization methods, such as stochastic gradient descent, which greatly reduces the genelization of neural network applications. We realize that the convexity make sense in the neural network and propose the exponential multilayer neural network (EMLP), a class of parameter convex neural network (PCNN) which is convex with regard to the parameters of the neural network under some conditions that can be realized. Besides, we propose the convexity metric for the two-layer EGCN and test the accuracy when the convexity metric changes. For late experiments, we use the same architecture to make the exponential graph convolutional network (EGCN) and do the experiment on the graph classificaion dataset in which our model EGCN performs better than the graph convolutional network (GCN) and the graph attention network (GAT).

cs.LG↗

arXiv2022

Solving the Quispel-Roberts-Thompson maps using Kajiwara-Noumi-Yamada's representation of elliptic curves

It is well known that the dynamical system determined by a Quispel-Roberts-Thompson map (a QRT map) preserves a pencil of biquadratic polynomial curves on ${\mathbb{CP}}^1 \times {\mathbb{CP}}^1$. In most cases this pencil is elliptic, i.e. its generic member is a smooth algebraic curve of genus one, and the system can be solved as a translation on the elliptic fiber to which the initial point belongs. However, this procedure is rather complicated to handle, especially in the normalization process. In this paper, for a given initial point on an invariant elliptic curve, we present a method to construct the solution directly in terms of the Weierstrass sigma function, using Kajiwara-Noumi-Yamada's parametric representation of elliptic curves.

math.DS↗

arXiv2022

Elliptic soliton solutions: $τ$ functions, vertex operators and bilinear identities

We establish a bilinear framework for elliptic soliton solutions which are composed by the Lamé-type plane wave factors. $τ$ functions in Hirota's form are derived and vertex operators that generate such $τ$ functions are presented. Bilinear identities are constructed and an algorithm to calculate residues and bilinear equations is formulated. These are investigated in detail for the KdV equation and sketched for the KP hierarchy. Degenerations by the periods of elliptic functions are investigated, giving rise to the bilinear framework associated with trigonometric/hyperbolic and rational functions. Reductions by dispersion relation are considered by employing the so-called elliptic $N$-th roots of the unity. $τ$ functions, vertex operators and bilinear equations of the KdV hierarchy and Boussinesq equation are obtained from those of the KP. We also formulate two ways to calculate bilinear derivatives involved with the Lamé-type plane wave factors, which shows that such type of plane wave factors result in quasi-gauge property of bilinear equations.

nlin.SI↗