arXiv subjects

Kai Yuan

Publications and source records attributed to Kai Yuan.

At least 37 records · Page 2Linked to original sources

arXiv2025

Generating Physically Realistic and Directable Human Motions from Multi-Modal Inputs

This work focuses on generating realistic, physically-based human behaviors from multi-modal inputs, which may only partially specify the desired motion. For example, the input may come from a VR controller providing arm motion and body velocity, partial key-point animation, computer vision applied to videos, or even higher-level motion goals. This requires a versatile low-level humanoid controller that can handle such sparse, under-specified guidance, seamlessly switch between skills, and recover from failures. Current approaches for learning humanoid controllers from demonstration data capture some of these characteristics, but none achieve them all. To this end, we introduce the Masked Humanoid Controller (MHC), a novel approach that applies multi-objective imitation learning on augmented and selectively masked motion demonstrations. The training methodology results in an MHC that exhibits the key capabilities of catch-up to out-of-sync input commands, combining elements from multiple motion sequences, and completing unspecified parts of motions from sparse multimodal input. We demonstrate these key capabilities for an MHC learned over a dataset of 87 diverse skills and showcase different multi-modal use cases, including integration with planning frameworks to highlight MHC's ability to solve new user-defined tasks without any finetuning.

cs.RO↗

arXiv2024

Robust multimode interference and conversion in topological unidirectional surface magnetoplasmons

We have theoretically investigated surface magnetoplasmons (SMPs) in a yttrium-iron-garnet (YIG) sandwiched waveguide. The dispersion demonstated that this waveguide can support topological unidirectional SMPs. Based on unidirectional SMPs, magnetically controllable multimode interference (MMI) is verified in both symmetric and asymmetric waveguides. Due to the coupling between the modes along two YIG-air interfaces, the asymmetric waveguide supports a unidirectional even mode within a single-mode frequency range. Moreover, these modes are topological protected when disorder is introduced. Utilizing robust unidirectional SMPs MMI (USMMI), tunable splitters have been achieved. It has been demonstrated that mode conversion between different modes can be realized. These results provide many degrees of freedom to manipulate topological waves.

physics.optics↗

arXiv2024

Can Large Language Models Logically Predict Myocardial Infarction? Evaluation based on UK Biobank Cohort

Background: Large language models (LLMs) have seen extraordinary advances with applications in clinical decision support. However, high-quality evidence is urgently needed on the potential and limitation of LLMs in providing accurate clinical decisions based on real-world medical data. Objective: To evaluate quantitatively whether universal state-of-the-art LLMs (ChatGPT and GPT-4) can predict the incidence risk of myocardial infarction (MI) with logical inference, and to further make comparison between various models to assess the performance of LLMs comprehensively. Methods: In this retrospective cohort study, 482,310 participants recruited from 2006 to 2010 were initially included in UK Biobank database and later on resampled into a final cohort of 690 participants. For each participant, tabular data of the risk factors of MI were transformed into standardized textual descriptions for ChatGPT recognition. Responses were generated by asking ChatGPT to select a score ranging from 0 to 10 representing the risk. Chain of Thought (CoT) questioning was used to evaluate whether LLMs make prediction logically. The predictive performance of ChatGPT was compared with published medical indices, traditional machine learning models and other large language models. Conclusions: Current LLMs are not ready to be applied in clinical medicine fields. Future medical LLMs are suggested to be expert in medical domain knowledge to understand both natural languages and quantified medical data, and further make logical inferences.

cs.AI↗

arXiv2024

Arrays of one-dimensional conducting channels in minimally twisted bilayer graphene

Minimally twisted bilayer graphene (TBG) with interlayer potential asymmetry host one-dimensional (1D) topological helical states (THSs) at domain walls between AB/BA stacking regions. However, the nature of THS propagation remains elusive. Although it is widely believed that they form a two-dimensional (2D) triangular network, a few argue that they self-organize into 1D topological zigzag modes (TZMs) that propagate independently. In this Letter, we propose a protocol based on a two-terminal TBG nanoflake transport device and resolve this issue. Through rigorous calculations on the differential conductance and the nonequilibrium local density of states, we show that, these THSs indeed self-construct the 1D distorted TZMs, each bypassing the AA-stacking spots and propagating independently. By considering a long TBG nanoflake, we obtain a nearly quantized conductance plateau with its value close to 1, 2, and 3 (in units of $2e^2/h$), which serves as a strong experimental sign for the existence of TZMs. Our work not only clarifies the propagation nature of the THSs, but also realizes an array of 1D conducting channels on a 2D platform. This work provides an unprecedented way to engineering topological states intrinsic in TBG.

cond-mat.mes-hall↗

arXiv2024

Cooperative Multi-Agent Deep Reinforcement Learning in Content Ranking Optimization

In a typical e-commerce setting, Content Ranking Optimization (CRO) mechanisms are employed to surface content on the search page to fulfill customers' shopping missions. CRO commonly utilizes models such as contextual deep bandits model to independently rank content at different positions, e.g., one optimizer dedicated to organic search results and another to sponsored results. However, this regional optimization approach does not necessarily translate to whole page optimization, e.g., maximizing revenue at the top of the page may inadvertently diminish the revenue of lower positions. In this paper, we propose a reinforcement learning based method for whole page ranking to jointly optimize across all positions by: 1) shifting from position level optimization to whole page level optimization to achieve an overall optimized ranking; 2) applying reinforcement learning to optimize for the cumulative rewards instead of the instant reward. We formulate page level CRO as a cooperative Multi-agent Markov Decision Process , and address it with the novel Multi-Agent Deep Deterministic Policy Gradient (MADDPG) model. MADDPG supports a flexible and scalable joint optimization framework by adopting a "centralized training and decentralized execution" approach. Extensive experiments demonstrate that MADDPG scales to a 2.5 billion action space in the public Mujoco environment, and outperforms the deep bandits modeling by 25.7% on the offline CRO data set from a leading e-commerce company. We foresee that this novel multi-agent optimization is applicable to similar joint optimization problems in the field of information retrieval.

cs.LG↗

arXiv2024

Fault-tolerant Quantum Chemical Calculations with Improved Machine-Learning Models

Easy and effective usage of computational resources is crucial for scientific calculations. Following our recent work of machine-learning (ML) assisted scheduling optimization [Ref: J. Comput. Chem. 2023, 44, 1174], we further propose 1) the improve ML models for the better predictions of computational loads, and as such, more elaborate load-balancing calculations can be expected; 2) the idea of coded computation, i.e. the integration of gradient coding, in order to introduce fault tolerance during the distributed calculations; and 3) their applications together with re-normalized exciton model with time-dependent density functional theory (REM-TDDFT) for calculating the excited states. Illustrated benchmark calculations include P38 protein, and solvent model with one or several excitable centers. The results show that the improved ML-assisted coded calculations can further improve the load-balancing and cluster utilization, and owing primarily profit in fault tolerance that aiming at the automated quantum chemical calculations for both ground and excited states.

physics.chem-ph↗

arXiv2024

IENE: Identifying and Extrapolating the Node Environment for Out-of-Distribution Generalization on Graphs

Due to the performance degradation of graph neural networks (GNNs) under distribution shifts, the work on out-of-distribution (OOD) generalization on graphs has received widespread attention. A novel perspective involves distinguishing potential confounding biases from different environments through environmental identification, enabling the model to escape environmentally-sensitive correlations and maintain stable performance under distribution shifts. However, in graph data, confounding factors not only affect the generation process of node features but also influence the complex interaction between nodes. We observe that neglecting either aspect of them will lead to a decrease in performance. In this paper, we propose IENE, an OOD generalization method on graphs based on node-level environmental identification and extrapolation techniques. It strengthens the model's ability to extract invariance from two granularities simultaneously, leading to improved generalization. Specifically, to identify invariance in features, we utilize the disentangled information bottleneck framework to achieve mutual promotion between node-level environmental estimation and invariant feature learning. Furthermore, we extrapolate topological environments through graph augmentation techniques to identify structural invariance. We implement the conceptual method with specific algorithms and provide theoretical analysis and proofs for our approach. Extensive experimental evaluations on two synthetic and four real-world OOD datasets validate the superiority of IENE, which outperforms existing techniques and provides a flexible framework for enhancing the generalization of GNNs.

cs.LG↗

arXiv2024

Fully-fused Multi-Layer Perceptrons on Intel Data Center GPUs

This paper presents a SYCL implementation of Multi-Layer Perceptrons (MLPs), which targets and is optimized for the Intel Data Center GPU Max 1550. To increase the performance, our implementation minimizes the slow global memory accesses by maximizing the data reuse within the general register file and the shared local memory by fusing the operations in each layer of the MLP. We show with a simple roofline model that this results in a significant increase in the arithmetic intensity, leading to improved performance, especially for inference. We compare our approach to a similar CUDA implementation for MLPs and show that our implementation on the Intel Data Center GPU outperforms the CUDA implementation on Nvidia's H100 GPU by a factor up to 2.84 in inference and 1.75 in training. The paper also showcases the efficiency of our SYCL implementation in three significant areas: Image Compression, Neural Radiance Fields, and Physics-Informed Machine Learning. In all cases, our implementation outperforms the off-the-shelf Intel Extension for PyTorch (IPEX) implementation on the same Intel GPU by up to a factor of 30 and the CUDA PyTorch version on Nvidia's H100 GPU by up to a factor 19. The code can be found at https://github.com/intel/tiny-dpcpp-nn.

cs.AI↗

arXiv2024

D$^2$-JSCC: Digital Deep Joint Source-channel Coding for Semantic Communications

Semantic communications (SemCom) have emerged as a new paradigm for supporting sixth-generation applications, where semantic features of data are transmitted using artificial intelligence algorithms to attain high communication efficiencies. Most existing SemCom techniques utilize deep neural networks (DNNs) to implement analog source-channel mappings, which are incompatible with existing digital communication architectures. To address this issue, this paper proposes a novel framework of digital deep joint source-channel coding (D$^2$-JSCC) targeting image transmission in SemCom. The framework features digital source and channel codings that are jointly optimized to reduce the end-to-end (E2E) distortion. First, deep source coding with an adaptive density model is designed to encode semantic features according to their distributions. Second, digital channel coding is employed to protect encoded features against channel distortion. To facilitate their joint design, the E2E distortion is characterized as a function of the source and channel rates via the analysis of the Bayesian model and Lipschitz assumption on the DNNs. Then to minimize the E2E distortion, a two-step algorithm is proposed to control the source-channel rates for a given channel signal-to-noise ratio. Simulation results reveal that the proposed framework outperforms classic deep JSCC and mitigates the cliff and leveling-off effects, which commonly exist for separation-based approaches.

cs.IT↗

arXiv2023

Coded Computing for Half-Duplex Wireless Distributed Computing Systems via Interference Alignment

Distributed computing frameworks such as MapReduce and Spark are often used to process large-scale data computing jobs. In wireless scenarios, exchanging data among distributed nodes would seriously suffer from the communication bottleneck due to limited communication resources such as bandwidth and power. To address this problem, we propose a coded parallel computing (CPC) scheme for distributed computing systems where distributed nodes exchange information over a half-duplex wireless interference network. The CPC scheme achieves the multicast gain by utilizing coded computing to multicast coded symbols {intended to} multiple receiver nodes and the cooperative transmission gain by allowing multiple {transmitter} nodes to jointly deliver messages via interference alignment. To measure communication performance, we apply the widely used latency-oriented metric: \emph{normalized delivery time (NDT)}. It is shown that CPC can significantly reduce the NDT by jointly exploiting the parallel transmission and coded multicasting opportunities. Surprisingly, when $K$ tends to infinity and the computation load is fixed, CPC approaches zero NDT while all state-of-the-art schemes achieve positive values of NDT. Finally, we establish an information-theoretic lower bound for the NDT-computation load trade-off over \emph{half-duplex} network, and prove our scheme achieves the minimum NDT within a multiplicative gap of $3$, i.e., our scheme is order optimal.

cs.IT↗

arXiv2023

Hierarchical generative modelling for autonomous robots

Humans can produce complex whole-body motions when interacting with their surroundings, by planning, executing and combining individual limb movements. We investigated this fundamental aspect of motor control in the setting of autonomous robotic operations. We approach this problem by hierarchical generative modelling equipped with multi-level planning-for autonomous task completion-that mimics the deep temporal architecture of human motor control. Here, temporal depth refers to the nested time scales at which successive levels of a forward or generative model unfold, for example, delivering an object requires a global plan to contextualise the fast coordination of multiple local movements of limbs. This separation of temporal scales also motivates robotics and control. Specifically, to achieve versatile sensorimotor control, it is advantageous to hierarchically structure the planning and low-level motor control of individual limbs. We use numerical and physical simulation to conduct experiments and to establish the efficacy of this formulation. Using a hierarchical generative model, we show how a humanoid robot can autonomously complete a complex task that necessitates a holistic use of locomotion, manipulation, and grasping. Specifically, we demonstrate the ability of a humanoid robot that can retrieve and transport a box, open and walk through a door to reach the destination, approach and kick a football, while showing robust performance in presence of body damage and ground irregularities. Our findings demonstrated the effectiveness of using human-inspired motor control algorithms, and our method provides a viable hierarchical architecture for the autonomous completion of challenging goal-directed tasks.

cs.RO↗

arXiv2022

A Novel Autonomous Robotics System for Aquaculture Environment Monitoring

Implementing fully automatic unmanned surface vehicles (USVs) monitoring water quality is challenging since effectively collecting environmental data while keeping the platform stable and environmental-friendly is hard to approach. To address this problem, we construct a USV that can automatically navigate an efficient path to sample water quality parameters in order to monitor the aquatic environment. The detection device needs to be stable enough to resist a hostile environment or climates while enormous volumes will disturb the aquaculture environment. Meanwhile, planning an efficient path for information collecting needs to deal with the contradiction between the restriction of energy and the amount of information in the coverage region. To tackle with mentioned challenges, we provide a USV platform that can perfectly balance mobility, stability, and portability attributed to its special round-shape structure and redundancy motion design. For informative planning, we combined the TSP and CPP algorithms to construct an optimistic plan for collecting more data within a certain range and limiting energy restrictions.We designed a fish existence prediction scenario to verify the novel system in both simulation experiments and field experiments. The novel aquaculture environment monitoring system significantly reduces the burden of manual operation in the fishery inspection field. Additionally, the simplicity of the sensor setup and the minimal cost of the platform enables its other possible applications in aquatic exploration and commercial utilization.

cs.RO↗

arXiv2022

Multi-Contact Motion Retargeting using Whole-body Optimization of Full Kinematics and Sequential Force Equilibrium

This paper presents a multi-contact motion adaptation framework that enables teleoperation of high degree-of-freedom (DoF) robots, such as quadrupeds and humanoids, for loco-manipulation tasks in multi-contact settings. Our proposed algorithms optimize whole-body configurations and formulate the retargeting of multi-contact motions as sequential quadratic programming, which is robust and stable near the edges of feasibility constraints. Our framework allows real-time operation of the robot and reduces cognitive load for the operator because infeasible commands are automatically adapted into physically stable and viable motions on the robot. The results in simulations with full dynamics demonstrated the effectiveness of teleoperating different legged robots interactively and generating rich multi-contact movements. We evaluated the computational efficiency of the proposed algorithms, and further validated and analyzed multi-contact loco-manipulation tasks on humanoid and quadruped robots by reaching, active pushing and various traversal on uneven terrains.

cs.RO↗

arXiv2022

Learning Perceptual Locomotion on Uneven Terrains using Sparse Visual Observations

To proactively navigate and traverse various terrains, active use of visual perception becomes indispensable. We aim to investigate the feasibility and performance of using sparse visual observations to achieve perceptual locomotion over a range of common terrains (steps, ramps, gaps, and stairs) in human-centered environments. We formulate a selection of sparse visual inputs suitable for locomotion over the terrains of interest, and propose a learning framework to integrate exteroceptive and proprioceptive states. We specifically design the state observations and a training curriculum to learn feedback control policies effectively over a range of different terrains. We extensively validate and benchmark the learned policy in various tasks: omnidirectional walking on flat ground, and forward locomotion over various obstacles, showing high success rate of traversability. Furthermore, we study exteroceptive ablations and evaluate policy generalization by adding various levels of noise and testing on new unseen terrains. We demonstrate the capabilities of autonomous perceptual locomotion that can be achieved by only using sparse visual observations from direct depth measurements, which are easily available from a Lidar or RGB-D sensor, showing robust ascent and descent over high stairs of 20 cm height, i.e., 50% leg length, and robustness against noise and unseen terrains.

cs.RO↗

arXiv2022

Ultra-efficient magnetism modulation in a Weyl ferromagnet by current-assisted domain wall motion

Flexible and efficient manipulation of magnetic configurations can be challenging. In the design of practical devices, achieving a high effective magnetic field with a low working current is under tight demand. Here, we report a unique method for efficient magnetism modulation by direct current injection in magnetic Weyl semimetal Co3Sn2S2. We demonstrate that the modulation process stems from current-assisted domain wall motion. Through two independent methods, we reveal that the spin-transfer torque efficiency of Co3Sn2S2 reaches as high as 2.4-5.6 kOe MA^(-1) cm^2, and the threshold current density for driving the magnetic domain walls is as low as <5.1*10^5 A/cm^2 without an external field, and <1.5*10^5 A/cm^2 with a moderate external field. Our findings manifest a new and powerful approach for sub-micron magnetism manipulation, and also open the door towards a new paradigm of spintronics that combines magnetism, topology, and metallicity for low-energy consumption memory and computing.

cond-mat.mtrl-sci↗

arXiv2021

Deep Pairwise Learning To Rank For Search Autocomplete

Autocomplete (a.k.a "Query Auto-Completion", "AC") suggests full queries based on a prefix typed by customer. Autocomplete has been a core feature of commercial search engine. In this paper, we propose a novel context-aware neural network based pairwise ranker (DeepPLTR) to improve AC ranking, DeepPLTR leverages contextual and behavioral features to rank queries by minimizing a pairwise loss, based on a fully-connected neural network structure. Compared to LambdaMART ranker, DeepPLTR shows +3.90% MeanReciprocalRank (MRR) lift in offline evaluation, and yielded +0.06% (p < 0.1) Gross Merchandise Value (GMV) lift in an Amazon's online A/B experiment.

cs.IR↗

arXiv2021

Broadband energy squeezing and tunneling based on unidirectional modes

Energy squeezing attracts many attentions for its potential applications in electromagnetic (EM) energy harvesting and optical communication. However, due to the Fabry-Perot resonance, only the EM waves with discrete frequencies can be squeezed and, as far as we know, in the previous energy-squeezing devices, stringent requirements of the materials or the geometrical shape are needed. We note that the structures filled with epsilon-near-zero (ENZ) mediums as reported in some works can squeeze and tunnel EM waves at frequencies (e.g. plasma frequency). However, the group velocity is usually near zero which means few EM information travel through the structures. In this paper, low-loss energy squeezing and tunneling (EST) based on unidirectional modes were demonstrated in YIG-based one-way waveguides at microwave frequencies. According to our theoretical analysis and the simulations using finite element method, broadband EST was achieved and the EM EST was observed even for extremely bended structures. Besides, similar EM EST was achieved in a realistic three-dimensional remanence-based one-way waveguide as well. The unidirectional modes-based EST paving the way to ultra-subwavelength EM focusing, enhanced nonlinear optics, and designing numerous functional devices in integrated optical circuits such as phase modulator.

physics.app-ph↗

arXiv2021

Force-guided High-precision Grasping Control of Fragile and Deformable Objects using sEMG-based Force Prediction

Regulating contact forces with high precision is crucial for grasping and manipulating fragile or deformable objects. We aim to utilize the dexterity of human hands to regulate the contact forces for robotic hands and exploit human sensory-motor synergies in a wearable and non-invasive way. We extracted force information from the electric activities of skeletal muscles during their voluntary contractions through surface electromyography (sEMG). We built a regression model based on a Neural Network to predict the gripping force from the preprocessed sEMG signals and achieved high accuracy (R2 = 0.982). Based on the force command predicted from human muscles, we developed a force-guided control framework, where force control was realized via an admittance controller that tracked the predicted gripping force reference to grasp delicate and deformable objects. We demonstrated the effectiveness of the proposed method on a set of representative fragile and deformable objects from daily life, all of which were successfully grasped without any damage or deformation.

cs.RO↗