arXiv subjects

Yu Chen

Publications and source records attributed to Yu Chen.

At least 271 records · Page 15Linked to original sources

arXiv2024

Upper-Limb Rehabilitation with a Dual-Mode Individualized Exoskeleton Robot: A Generative-Model-Based Solution

Several upper-limb exoskeleton robots have been developed for stroke rehabilitation, but their rather low level of individualized assistance typically limits their effectiveness and practicability. Individualized assistance involves an upper-limb exoskeleton robot continuously assessing feedback from a stroke patient and then meticulously adjusting interaction forces to suit specific conditions and online changes. This paper describes the development of a new upper-limb exoskeleton robot with a novel online generative capability that allows it to provide individualized assistance to support the rehabilitation training of stroke patients. Specifically, the upper-limb exoskeleton robot exploits generative models to customize the fine and fit trajectory for the patient, as medical conditions, responses, and comfort feedback during training generally differ between patients. This generative capability is integrated into the two working modes of the upper-limb exoskeleton robot: an active mirroring mode for patients who retain motor abilities on one side of the body and a passive following mode for patients who lack motor ability on both sides of the body. The performance of the upper-limb exoskeleton robot was illustrated in experiments involving healthy subjects and stroke patients.

cs.RO↗

arXiv2024

Quantum error correction below the surface code threshold

Quantum error correction provides a path to reach practical quantum computing by combining multiple physical qubits into a logical qubit, where the logical error rate is suppressed exponentially as more qubits are added. However, this exponential suppression only occurs if the physical error rate is below a critical threshold. In this work, we present two surface code memories operating below this threshold: a distance-7 code and a distance-5 code integrated with a real-time decoder. The logical error rate of our larger quantum memory is suppressed by a factor of $Λ$ = 2.14 $\pm$ 0.02 when increasing the code distance by two, culminating in a 101-qubit distance-7 code with 0.143% $\pm$ 0.003% error per cycle of error correction. This logical memory is also beyond break-even, exceeding its best physical qubit's lifetime by a factor of 2.4 $\pm$ 0.3. We maintain below-threshold performance when decoding in real time, achieving an average decoder latency of 63 $μ$s at distance-5 up to a million cycles, with a cycle time of 1.1 $μ$s. To probe the limits of our error-correction performance, we run repetition codes up to distance-29 and find that logical performance is limited by rare correlated error events occurring approximately once every hour, or 3 $\times$ 10$^9$ cycles. Our results present device performance that, if scaled, could realize the operational requirements of large scale fault-tolerant quantum algorithms.

quant-ph↗

arXiv2024

Polyphone Disambiguation in Mandarin Chinese with Semi-Supervised Learning

The majority of Chinese characters are monophonic, while a special group of characters, called polyphonic characters, have multiple pronunciations. As a prerequisite of performing speech-related generative tasks, the correct pronunciation must be identified among several candidates. This process is called Polyphone Disambiguation. Although the problem has been well explored with both knowledge-based and learning-based approaches, it remains challenging due to the lack of publicly available labeled datasets and the irregular nature of polyphone in Mandarin Chinese. In this paper, we propose a novel semi-supervised learning (SSL) framework for Mandarin Chinese polyphone disambiguation that can potentially leverage unlimited unlabeled text data. We explore the effect of various proxy labeling strategies including entropy-thresholding and lexicon-based labeling. Qualitative and quantitative experiments demonstrate that our method achieves state-of-the-art performance. In addition, we publish a novel dataset specifically for the polyphone disambiguation task to promote further research.

cs.CL↗

arXiv2024

Enabling Regional Explainability by Automatic and Model-agnostic Rule Extraction

In Explainable AI, rule extraction translates model knowledge into logical rules, such as IF-THEN statements, crucial for understanding patterns learned by black-box models. This could significantly aid in fields like disease diagnosis, disease progression estimation, or drug discovery. However, such application domains often contain imbalanced data, with the class of interest underrepresented. Existing methods inevitably compromise the performance of rules for the minor class to maximise the overall performance. As the first attempt in this field, we propose a model-agnostic approach for extracting rules from specific subgroups of data, featuring automatic rule generation for numerical features. This method enhances the regional explainability of machine learning models and offers wider applicability compared to existing methods. We additionally introduce a new method for selecting features to compose rules, reducing computational costs in high-dimensional spaces. Experiments across various datasets and models demonstrate the effectiveness of our methods.

cs.LG↗

arXiv2024

Dissipation Driven Coherent Dynamics Observed in Bose-Einstein Condensates

We report the first experimental observation of dissipation-driven coherent quantum many-body oscillation, and this oscillation is manifested as the coherent exchange of atoms between the thermal and the condensate components in a three-dimensional partially condensed Bose gas. Firstly, we observe that the dissipation leads to two different atom loss rates between the thermal and the condensate components, such that the thermal fraction increases as dissipation time increases. Therefore, this dissipation process serves as a tool to uniformly ramp up the system's temperature without introducing extra density excitation. Subsequently, a coherent pair exchange of atoms between the thermal and the condensate components occurs, resulting in coherent oscillation of atom numbers in both components. This oscillation, permanently embedded in the atom loss process, is revealed clearly when we inset a duration of dissipation-free evolution into the entire dynamics, manifested as an oscillation of total atom number at the end. Finally, we also present a theoretical calculation to support this physical mechanism, which simultaneously includes dissipation, interaction, finite temperature, and harmonic trap effects. Our work introduces a highly controllable dissipation as a new tool to control quantum many-body dynamics.

cond-mat.quant-gas↗

arXiv2024

FEEL: A Framework for Evaluating Emotional Support Capability with Large Language Models

Emotional Support Conversation (ESC) is a typical dialogue that can effectively assist the user in mitigating emotional pressures. However, owing to the inherent subjectivity involved in analyzing emotions, current non-artificial methodologies face challenges in effectively appraising the emotional support capability. These metrics exhibit a low correlation with human judgments. Concurrently, manual evaluation methods extremely will cause high costs. To solve these problems, we propose a novel model FEEL (Framework for Evaluating Emotional Support Capability with Large Lan-guage Models), employing Large Language Models (LLMs) as evaluators to assess emotional support capabilities. The model meticulously considers various evaluative aspects of ESC to apply a more comprehensive and accurate evaluation method for ESC. Additionally, it employs a probability distribution approach for a more stable result and integrates an ensemble learning strategy, leveraging multiple LLMs with assigned weights to enhance evaluation accuracy. To appraise the performance of FEEL, we conduct extensive experiments on existing ESC model dialogues. Experimental results demonstrate our model exhibits a substantial enhancement in alignment with human evaluations compared to the baselines. Our source code is available at https://github.com/Ansisy/FEEL.

cs.CL↗

arXiv2024

LM-Infinite: Zero-Shot Extreme Length Generalization for Large Language Models

Today's large language models (LLMs) typically train on short text segments (e.g., <4K tokens) due to the quadratic complexity of their Transformer architectures. As a result, their performance suffers drastically on inputs longer than those encountered during training, substantially limiting their applications in real-world tasks involving long contexts such as encoding scientific articles, code repositories, or long dialogues. Through theoretical analysis and empirical investigation, this work identifies three major factors contributing to this length generalization failure. Our theoretical analysis further reveals that commonly used techniques like truncating the attention window or relative positional encodings are inadequate to address them. Answering these challenges, we propose LM-Infinite, a simple and effective method for enhancing LLMs' capabilities of handling long contexts. LM-Infinite is highly flexible and can be used with most modern LLMs off-the-shelf. Without any parameter updates, it allows LLMs pre-trained with 2K or 4K-long segments to generalize to up to 200M length inputs while retaining perplexity. It also improves performance on downstream tasks such as Passkey Retrieval and Qasper in the zero-shot setting. LM-Infinite brings substantial efficiency improvements: it achieves 2.7x decoding speed up and 7.5x memory saving over the original model. Our codes are released at \url{https://github.com/Glaciohound/LM-Infinite}.

cs.CL↗

arXiv2024

Dirac-like fermions anomalous magneto-transport in a spin-polarized oxide two-dimensional electron system

In two-dimensional electron systems (2DES) the breaking of the inversion, time-reversal and bulk crystal-field symmetries is interlaced with the effects of spin-orbit coupling (SOC) triggering exotic quantum phenomena. Here, we used epitaxial engineering to design and realize a 2DES characterized simultaneously by ferromagnetic order, large Rashba SOC and hexagonal band warping at the (111) interfaces between LaAlO$_{3}$, EuTiO$_{3}$ and SrTiO$_{3}$ insulators. The 2DES displays anomalous quantum corrections to the magneto-conductance driven by the time-reversal-symmetry breaking occurring below the magnetic transition temperature. The results are explained by the emergence of a non-trivial Berry phase and competing weak anti-localization / weak localization back-scattering of Dirac-like fermions, mimicking the phenomenology of gapped topological insulators. These findings open perspectives for the engineering of novel spin-polarized functional 2DES holding promises in spin-orbitronics and topological electronics.

cond-mat.mes-hall↗

arXiv2024

Propagative Distance Optimization for Constrained Inverse Kinematics

This paper investigates a constrained inverse kinematic (IK) problem that seeks a feasible configuration of an articulated robot under various constraints such as joint limits and obstacle collision avoidance. Due to the high-dimensionality and complex constraints, this problem is often solved numerically via iterative local optimization. Classic local optimization methods take joint angles as the decision variable, which suffers from non-linearity caused by the trigonometric constraints. Recently, distance-based IK methods have been developed as an alternative approach that formulates IK as an optimization over the distances among points attached to the robot and the obstacles. Although distance-based methods have demonstrated unique advantages, they still suffer from low computational efficiency, since these approaches usually ignore the chain structure in the kinematics of serial robots. This paper proposes a new method called propagative distance optimization for constrained inverse kinematics (PDO-IK), which captures and leverages the chain structure in the distance-based formulation and expedites the optimization by computing forward kinematics and the Jacobian propagatively along the kinematic chain. Test results show that PDO-IK runs up to two orders of magnitude faster than the existing distance-based methods under joint limits constraints and obstacle avoidance constraints. It also achieves up to three times higher success rates than the conventional joint-angle-based optimization methods for IK problems. The high runtime efficiency of PDO-IK allows the real-time computation (10$-$1500 Hz) and enables a simulated humanoid robot with 19 degrees of freedom (DoFs) to avoid moving obstacles, which is otherwise hard to achieve with the baselines.

cs.RO↗

arXiv2024

FFB: A Fair Fairness Benchmark for In-Processing Group Fairness Methods

This paper introduces the Fair Fairness Benchmark (\textsf{FFB}), a benchmarking framework for in-processing group fairness methods. Ensuring fairness in machine learning is important for ethical compliance. However, there exist challenges in comparing and developing fairness methods due to inconsistencies in experimental settings, lack of accessible algorithmic implementations, and limited extensibility of current fairness packages and tools. To address these issues, we introduce an open-source standardized benchmark for evaluating in-processing group fairness methods and provide a comprehensive analysis of state-of-the-art methods to ensure different notions of group fairness. This work offers the following key contributions: the provision of flexible, extensible, minimalistic, and research-oriented open-source code; the establishment of unified fairness method benchmarking pipelines; and extensive benchmarking, which yields key insights from $\mathbf{45,079}$ experiments, $\mathbf{14,428}$ GPU hours. We believe that our work will significantly facilitate the growth and development of the fairness research community.

cs.LG↗

arXiv2024

Magnetic ground state and strain-mediated chiral-like atomic distortions behavior in two-dimensional rectangular spin lattice

Due to the large perpendicular magnetic anisotropy originating from spin-orbit coupling, magnetoelastic coupling is generally reported in easy-plane magnets with rectangular lattice where the easy magnetization is coupled with the lattice direction, while the acquisition of a novel coupling, beyond the easy-plane ferromagnets, in two-dimensional (2D) materials remains unknown. Here, by employing the density functional theory calculations, we demonstrate this feasibility with the discovery of long-range ferromagnetic ordering and elastic strain-mediated chiral-like atomic distortions behavior in a newly tetragonal As-Fe-As trilayer (t-FeAs monolayer), which shows large perpendicular magnetic anisotropy, robust ferromagnetic ordering, and in-plane ferroelasticity. We firstly point out that obvious limits exist when using the four magnetic configurations to determine the magnetic ground state for a rectangular spin lattice even if more exchange interaction parameters are included. A four-state mapping analysis is carefully examined for t-FeAs, where the calculated Curie temperature, Tc, is 435 K, which is higher than most reported 2D magnets, and can be further tuned by appropriate strains. Intriguingly, the chiral-like atomic distortion behavior of the Fe sub-layer is scanning tunneling microscopy characterizable, which can switch the magnetization axis between the out-of-plane and in-plane direction. This unusual finding of ferroelastic manipulation of both the atomic displacement and spin properties makes t-FeAs a promising candidate for future spintronics and also provides the possibility for exploring unprecedented coupling physics.

cond-mat.mtrl-sci↗

arXiv2024

VQPy: An Object-Oriented Approach to Modern Video Analytics

Video analytics is widely used in contemporary systems and services. At the forefront of video analytics are video queries that users develop to find objects of particular interest. Building upon the insight that video objects (e.g., human, animals, cars, etc.), the center of video analytics, are similar in spirit to objects modeled by traditional object-oriented languages, we propose to develop an object-oriented approach to video analytics. This approach, named VQPy, consists of a frontend$\unicode{x2015}$a Python variant with constructs that make it easy for users to express video objects and their interactions$\unicode{x2015}$as well as an extensible backend that can automatically construct and optimize pipelines based on video objects. We have implemented and open-sourced VQPy, which has been productized in Cisco as part of its DeepVision framework.

cs.CV↗

arXiv2024

Multi-Scale 3D Gaussian Splatting for Anti-Aliased Rendering

3D Gaussians have recently emerged as a highly efficient representation for 3D reconstruction and rendering. Despite its high rendering quality and speed at high resolutions, they both deteriorate drastically when rendered at lower resolutions or from far away camera position. During low resolution or far away rendering, the pixel size of the image can fall below the Nyquist frequency compared to the screen size of each splatted 3D Gaussian and leads to aliasing effect. The rendering is also drastically slowed down by the sequential alpha blending of more splatted Gaussians per pixel. To address these issues, we propose a multi-scale 3D Gaussian splatting algorithm, which maintains Gaussians at different scales to represent the same scene. Higher-resolution images are rendered with more small Gaussians, and lower-resolution images are rendered with fewer larger Gaussians. With similar training time, our algorithm can achieve 13\%-66\% PSNR and 160\%-2400\% rendering speed improvement at 4$\times$-128$\times$ scale rendering on Mip-NeRF360 dataset compared to the single scale 3D Gaussian splitting. Our code and more results are available on our project website https://jokeryan.github.io/projects/ms-gs/

cs.CV↗

arXiv2024

On the Streaming Complexity of Expander Decomposition

In this paper we study the problem of finding $(ε, ϕ)$-expander decompositions of a graph in the streaming model, in particular for dynamic streams of edge insertions and deletions. The goal is to partition the vertex set so that every component induces a $ϕ$-expander, while the number of inter-cluster edges is only an $ε$ fraction of the total volume. It was recently shown that there exists a simple algorithm to construct a $(O(ϕ\log n), ϕ)$-expander decomposition of an $n$-vertex graph using $\widetilde{O}(n/ϕ^2)$ bits of space [Filtser, Kapralov, Makarov, ITCS'23]. This result calls for understanding the extent to which a dependence in space on the sparsity parameter $ϕ$ is inherent. We move towards answering this question on two fronts. We prove that a $(O(ϕ\log n), ϕ)$-expander decomposition can be found using $\widetilde{O}(n)$ space, for every $ϕ$. At the core of our result is the first streaming algorithm for computing boundary-linked expander decompositions, a recently introduced strengthening of the classical notion [Goranci et al., SODA'21]. The key advantage is that a classical sparsifier [Fung et al., STOC'11], with size independent of $ϕ$, preserves the cuts inside the clusters of a boundary-linked expander decomposition within a multiplicative error. Notable algorithmic applications use sequences of expander decompositions, in particular one often repeatedly computes a decomposition of the subgraph induced by the inter-cluster edges (e.g., the seminal work of Spielman and Teng on spectral sparsifiers [Spielman, Teng, SIAM Journal of Computing 40(4)], or the recent maximum flow breakthrough [Chen et al., FOCS'22], among others). We prove that any streaming algorithm that computes a sequence of $(O(ϕ\log n), ϕ)$-expander decompositions requires ${\widetildeΩ}(n/ϕ)$ bits of space, even in insertion only streams.

cs.DS↗

arXiv2024

ViViD: Video Virtual Try-on using Diffusion Models

Video virtual try-on aims to transfer a clothing item onto the video of a target person. Directly applying the technique of image-based try-on to the video domain in a frame-wise manner will cause temporal-inconsistent outcomes while previous video-based try-on solutions can only generate low visual quality and blurring results. In this work, we present ViViD, a novel framework employing powerful diffusion models to tackle the task of video virtual try-on. Specifically, we design the Garment Encoder to extract fine-grained clothing semantic features, guiding the model to capture garment details and inject them into the target video through the proposed attention feature fusion mechanism. To ensure spatial-temporal consistency, we introduce a lightweight Pose Encoder to encode pose signals, enabling the model to learn the interactions between clothing and human posture and insert hierarchical Temporal Modules into the text-to-image stable diffusion model for more coherent and lifelike video synthesis. Furthermore, we collect a new dataset, which is the largest, with the most diverse types of garments and the highest resolution for the task of video virtual try-on to date. Extensive experiments demonstrate that our approach is able to yield satisfactory video try-on results. The dataset, codes, and weights will be publicly available. Project page: https://becauseimbatman0.github.io/ViViD.

cs.CV↗

arXiv2024

Towards robust prediction of material properties for nuclear reactor design under scarce data -- a study in creep rupture property

Advances in Deep Learning bring further investigation into credibility and robustness, especially for safety-critical engineering applications such as the nuclear industry. The key challenges include the availability of data set (often scarce and sparse) and insufficient consideration of the uncertainty in the data, model, and prediction. This paper therefore presents a meta-learning based approach that is both uncertainty- and prior knowledge-informed, aiming at trustful predictions of material properties for the nuclear reactor design. It is suited for robust learning under limited data. Uncertainty has been accounted for where a distribution of predictor functions are produced for extrapolation. Results suggest it achieves superior performance than existing empirical methods in rupture life prediction, a case which is typically under a small data regime. While demonstrated herein with rupture properties, this learning approach is transferable to solve similar problems of data scarcity across the nuclear industry. It is of great importance to boosting the AI analytics in the nuclear industry by proving the applicability and robustness while providing tools that can be trusted.

cs.LG↗

arXiv2024

Cross Domain LifeLong Sequential Modeling for Online Click-Through Rate Prediction

Deep neural networks (DNNs) that incorporated lifelong sequential modeling (LSM) have brought great success to recommendation systems in various social media platforms. While continuous improvements have been made in domain-specific LSM, limited work has been done in cross-domain LSM, which considers modeling of lifelong sequences of both target domain and source domain. In this paper, we propose Lifelong Cross Network (LCN) to incorporate cross-domain LSM to improve the click-through rate (CTR) prediction in the target domain. The proposed LCN contains a LifeLong Attention Pyramid (LAP) module that comprises of three levels of cascaded attentions to effectively extract interest representations with respect to the candidate item from lifelong sequences. We also propose Cross Representation Production (CRP) module to enforce additional supervision on the learning and alignment of cross-domain representations so that they can be better reused on learning of the CTR prediction in the target domain. We conducted extensive experiments on WeChat Channels industrial dataset as well as on benchmark dataset. Results have revealed that the proposed LCN outperforms existing work in terms of both prediction accuracy and online performance.

cs.IR↗

arXiv2024

Cognitive Effort Measures Driven by Fixation Induced Retinal Flow in Visual Scanning Behavior during Virtual Driving

In this paper, we consider the problem of visual scanning mechanism underpinning sensorimotor tasks, such as walking and driving, in dynamic environments. We exploit eye tracking data for offering two new cognitive effort measures in visual scanning behavior of virtual driving. By utilizing the retinal flow induced by fixation, two novel measures of cognitive effort are proposed through the importance of grids in the viewing plane and the concept of information quantity, respectively. Psychophysical studies are conducted to reveal the effectiveness of the two proposed measures. Both these two cognitive effort measures have shown their significant correlation with pupil size change. Our results suggest that the quantitative exploitation of eye tracking data provides an effective approach for the evaluation of sensorimotor activities.

cs.HC↗