Searcharxiv⌕ Search

arXiv subjects

Yao Du

Publications and source records attributed to Yao Du.

At least 37 records · Page 2Linked to original sources
arXiv2025

Metamaterials that learn to change shape

Learning to change shape is a fundamental strategy of adaptation and evolution of living organisms, from bacteria and cells to tissues and animals. Human-made materials can also exhibit advanced shape morphing capabilities, but lack the ability to learn. Here, we build metamaterials that can learn complex shape-changing responses using a contrastive learning scheme. By being shown examples of the target shape changes, our metamaterials are able to learn those shape changes by progressively updating internal learning degrees of freedom -- the local stiffnesses. Unlike traditional materials that are designed once and for all, our metamaterials have the ability to forget and learn new shape changes in sequence, to learn multiple shape changes that break reciprocity, and to learn multistable shape changes, which in turn allows them to perform reflex gripping actions and locomotion. Our findings establish metamaterials as an exciting platform for physical learning, which in turn opens avenues for the use of physical learning to design adaptive materials and robots.

cond-mat.soft↗
arXiv2025

Can LLMs Grasp Implicit Cultural Values? Benchmarking LLMs' Cultural Intelligence with CQ-Bench

Cultural Intelligence (CQ) refers to the ability to understand unfamiliar cultural contexts, a crucial skill for large language models (LLMs) to effectively engage with globally diverse users. Existing studies often focus on explicitly stated cultural norms, but fail to capture the subtle, implicit values that are common in daily conversation. To address this gap, we introduce CQBench, a benchmark specifically designed to assess LLMs' capability to infer implicit cultural values from natural conversational contexts. CQBench consists of multi character conversation based stories using values from the World Value Survey and the GlobalOpinions, with topics including ethical, religious, social, etc. Our automatic dataset construction pipeline integrates rigorous validation procedures (incorporation, consistency, and implicitness checks), achieving a 94.5% human model agreement in the final validation. To leverage CQBench data, we design three tasks of increasing complexity: attitude detection, value selection, and value extraction. These tasks evaluate whether models can detect attitude and recognize values embedded within natural dialogues rather than relying on explicit cultural knowledge. We find that while frontier models like o1 reach human level performance in value selection (0.809 F1), they still fall short in nuanced attitude detection (0.622 F1). Notably, finetuning a smaller LLaMA-3.2-3B on only 500 culturally rich examples improves performance by over 10%, even outperforming o3-mini in some cases. Using CQ-Bench, we provide insights into the current challenges in LLMs' CQ research and suggest practical pathways for enhancing LLMs' cross-cultural reasoning abilities.

cs.CL↗
arXiv2025

CardiacCLIP: Video-based CLIP Adaptation for LVEF Prediction in a Few-shot Manner

Echocardiography is a vital non-invasive modality for cardiac assessment, with left ventricular ejection fraction (LVEF) serving as a key indicator of heart function. Existing LVEF estimation methods depend on large-scale annotated video datasets, which are costly and limit adaptability across various clinical settings. Recent vision-language models for echocardiography, such as EchoCLIP, apply image-to-text pretraining but fail to capture crucial temporal dynamics and localized cardiac structures essential for accurate diagnosis. To address these challenges, we propose CardiacCLIP, a video-based framework that enhances LVEF prediction through attention-based frame aggregation and multi-resolution input scaling. Specifically, we introduce MFL (Multi Frame Learning), a novel attention-based mechanism for selectively fusing informative frames, and EchoZoom, a multi-scale feature extraction strategy that refines spatial representations of cardiac structures. As a novel adaptation of CLIP models for few-shot echocardiogram video analysis, our approach significantly improves diagnostic accuracy, reducing MAE by 2.07 on the EchoNet-Dynamic dataset under 1-shot setting. The code is available at https://github.com/xmed-lab/CardiacCLIP.

cs.CV↗
arXiv2025

Ground state solutions for the asymptotically periodic Schrödinger-Poisson systems with $p$-Laplacian

In this paper we study the existence of ground state solutions for the asymptotically periodic Schrödinger-Poisson systems which are coupled by a Schrödinger equation of $p$-Laplacian and a Poisson equation of $q$-Laplacian. The method relies on a variational approach and the case of the nonlinearity exhibits a critical growth is also considered. Some results in the literature are extended.

math.AP↗
arXiv2025

The Role of Visual Modality in Multimodal Mathematical Reasoning: Challenges and Insights

Recent research has increasingly focused on multimodal mathematical reasoning, particularly emphasizing the creation of relevant datasets and benchmarks. Despite this, the role of visual information in reasoning has been underexplored. Our findings show that existing multimodal mathematical models minimally leverage visual information, and model performance remains largely unaffected by changes to or removal of images in the dataset. We attribute this to the dominance of textual information and answer options that inadvertently guide the model to correct answers. To improve evaluation methods, we introduce the HC-M3D dataset, specifically designed to require image reliance for problem-solving and to challenge models with similar, yet distinct, images that change the correct answer. In testing leading models, their failure to detect these subtle visual differences suggests limitations in current visual perception capabilities. Additionally, we observe that the common approach of improving general VQA capabilities by combining various types of image encoders does not contribute to math reasoning performance. This finding also presents a challenge to enhancing visual reliance during math reasoning. Our benchmark and code would be available at \href{https://github.com/Yufang-Liu/visual_modality_role}{https://github.com/Yufang-Liu/visual\_modality\_role}.

cs.CV↗
arXiv2025

Versatile Reservoir Computing for Heterogeneous Complex Networks

A new machine learning scheme, termed versatile reservoir computing, is proposed for sustaining the dynamics of heterogeneous complex networks. We show that a single, small-scale reservoir computer trained on time series from a subset of elements is able to replicate the dynamics of any element in a large-scale complex network, though the elements are of different intrinsic parameters and connectivities. Furthermore, by substituting failed elements with the trained machine, we demonstrate that the collective dynamics of the network can be preserved accurately over a finite time horizon. The capability and effectiveness of the proposed scheme are validated on three representative network models: a homogeneous complex network of non-identical phase oscillators, a heterogeneous complex network of non-identical phase oscillators, and a heterogeneous complex network of non-identical chaotic oscillators.

nlin.CD↗
arXiv2025

Sustaining the dynamics of Kuramoto model by adaptable reservoir computer

A scenario frequently encountered in real-world complex systems is the temporary failure of a few components. For systems whose functionality hinges on the collective dynamics of the interacting components, a viable approach to dealing with the failures is replacing the malfunctioning components with their backups, so that the collective dynamics of the systems can be precisely maintained for a duration long enough to resolve the problem. Here, taking the paradigmatic Kuramoto model as an example and considering the scenario of oscillator failures, we propose substituting the failed oscillators with digital twins trained by the data measured from the system evolution. Specifically, leveraging the technique of adaptable reservoir computer (RC) in machine learning, we demonstrate that a single, small-size RC is able to substitute any oscillator in the Kuramoto model such that the time evolution of the synchronization order parameter of the repaired system is identical to that of the original system for a certain time period. The performance of adaptable RC is evaluated in various contexts, and it is found that the sustaining period is influenced by multiple factors, including the size of the training dataset, the overall coupling strength of the system, and the number of substituted oscillators. Additionally, though the synchronization order parameter diverges from the ground truth in the long-term running, the functional networks of the oscillators are still faithfully sustained by the machine substitutions.

nlin.CD↗
arXiv2025

Diffusion-based Virtual Staining from Polarimetric Mueller Matrix Imaging

Polarization, as a new optical imaging tool, has been explored to assist in the diagnosis of pathology. Moreover, converting the polarimetric Mueller Matrix (MM) to standardized stained images becomes a promising approach to help pathologists interpret the results. However, existing methods for polarization-based virtual staining are still in the early stage, and the diffusion-based model, which has shown great potential in enhancing the fidelity of the generated images, has not been studied yet. In this paper, a Regulated Bridge Diffusion Model (RBDM) for polarization-based virtual staining is proposed. RBDM utilizes the bidirectional bridge diffusion process to learn the mapping from polarization images to other modalities such as H\&E and fluorescence. And to demonstrate the effectiveness of our model, we conduct the experiment on our manually collected dataset, which consists of 18,000 paired polarization, fluorescence and H\&E images, due to the unavailability of the public dataset. The experiment results show that our model greatly outperforms other benchmark methods. Our dataset and code will be released upon acceptance.

eess.IV↗
arXiv2024

Ground states for the double weighted critical Kirchhoff equation on the unit ball in $\mathbb{R}^3$

This paper deals with the existence of ground states for degenerative ($a=0$) and non-degenerative ($a>0$) double weighted critical Kirchhoff equation \begin{eqnarray*} \left\{ \begin{array}{ll} \displaystyle-\left(a+b\int_B |\nabla u|^2dx\right)Δu=|x|^{α_1} |u|^{4+2α_1}u+μ|x|^{α_2} |u|^{4+2α_2}u+λh(|x|) f(u) &{\rm in}\ B,\\ u=0 &{\rm on}\ \partial B, \end{array} \right. \end{eqnarray*} where $B$ is a unit open ball in $\mathbb{R}^3$ with center $0$, $a\geq0, b>0, μ\in \mathbb{R}, λ>0, α_1>α_2>-2$, $4+2α_i=2^*(α_i)-2\ (i=1,2)$ with $2^*(α_i)=\frac{2(N+α_i)}{N-2} $ $(N=3)$ being Hardy-Sobolev ($-2<α_i<0$), Sobolev ($α_i=0$) or Hénon-Sobolev ($α_i>0$) critical exponent of the embedding $H_{0,r}^1(B)\hookrightarrow L^p(B;|x|^{α_i})$. Noting that the sign of $μ$ gives rise to a great effect on the existence of solutions. The methods rely on Nehari manifold and the mountain pass theorem.

math.AP↗
arXiv2024

Multi-functional reservoir computing

Whereas the power of reservoir computing (RC) in inferring chaotic systems has been well established in the literature, the studies are mostly restricted to mono-functional machines where the training and testing data are acquired from the same attractor. Here, using the strategies of attractor labeling and trajectory separation, we propose a new scheme of RC capable of learning multiple attractors generated by entirely different dynamics, namely multi-functional RC. Specifically, we demonstrate that by incorporating a label channel into the standard RC, a single machine is able to learn from data the dynamics of multiple chaotic attractors, while each attractor can be accurately retrieved by inputting just a scalar in the prediction phase. The dependence of the machine performance on the labeling and separation parameters is investigated, and it is found that the machine performance is optimized when the parameters take intermediate values. The working mechanism of multi-functional RC is analyzed by the method of functional networks in neuroscience, and it is revealed that each attractor is represented by a stable, unique functional network in the reservoir, and the optimal performance arises as a balance between the stability, complexity, and distinguishability of the functional networks.

nlin.CD↗
arXiv2024

Toward Efficient Visual Gyroscopes: Spherical Moments, Harmonics Filtering, and Masking Techniques for Spherical Camera Applications

Unlike a traditional gyroscope, a visual gyroscope estimates camera rotation through images. The integration of omnidirectional cameras, offering a larger field of view compared to traditional RGB cameras, has proven to yield more accurate and robust results. However, challenges arise in situations that lack features, have substantial noise causing significant errors, and where certain features in the images lack sufficient strength, leading to less precise prediction results. Here, we address these challenges by introducing a novel visual gyroscope, which combines an Efficient Multi-Mask-Filter Rotation Estimator(EMMFRE) and a Learning based optimization(LbTO) to provide a more efficient and accurate rotation estimation from spherical images. Experimental results demonstrate superior performance of the proposed approach in terms of accuracy. The paper emphasizes the advantages of integrating machine learning to optimize analytical solutions, discusses limitations, and suggests directions for future research.

cs.CV↗
arXiv2024

Teach CLIP to Develop a Number Sense for Ordinal Regression

Ordinal regression is a fundamental problem within the field of computer vision, with customised well-trained models on specific tasks. While pre-trained vision-language models (VLMs) have exhibited impressive performance on various vision tasks, their potential for ordinal regression has received less exploration. In this study, we first investigate CLIP's potential for ordinal regression, from which we expect the model could generalise to different ordinal regression tasks and scenarios. Unfortunately, vanilla CLIP fails on this task, since current VLMs have a well-documented limitation of encapsulating compositional concepts such as number sense. We propose a simple yet effective method called NumCLIP to improve the quantitative understanding of VLMs. We disassemble the exact image to number-specific text matching problem into coarse classification and fine prediction stages. We discretize and phrase each numerical bin with common language concept to better leverage the available pre-trained alignment in CLIP. To consider the inherent continuous property of ordinal regression, we propose a novel fine-grained cross-modal ranking-based regularisation loss specifically designed to keep both semantic and ordinal alignment in CLIP's feature space. Experimental results on three general ordinal regression tasks demonstrate the effectiveness of NumCLIP, with 10% and 3.83% accuracy improvement on historical image dating and image aesthetics assessment task, respectively. Code is publicly available at https://github.com/xmed-lab/NumCLIP.

cs.CV↗
arXiv2024

MIPI 2024 Challenge on Few-shot RAW Image Denoising: Methods and Results

The increasing demand for computational photography and imaging on mobile platforms has led to the widespread development and integration of advanced image sensors with novel algorithms in camera systems. However, the scarcity of high-quality data for research and the rare opportunity for in-depth exchange of views from industry and academia constrain the development of mobile intelligent photography and imaging (MIPI). Building on the achievements of the previous MIPI Workshops held at ECCV 2022 and CVPR 2023, we introduce our third MIPI challenge including three tracks focusing on novel image sensors and imaging algorithms. In this paper, we summarize and review the Few-shot RAW Image Denoising track on MIPI 2024. In total, 165 participants were successfully registered, and 7 teams submitted results in the final testing phase. The developed solutions in this challenge achieved state-of-the-art erformance on Few-shot RAW Image Denoising. More details of this challenge and the link to the dataset can be found at https://mipichallenge.org/MIPI2024.

cs.CV↗
arXiv2024

Scalable synchronization cluster in networked chaotic oscillators

Cluster synchronization in synthetic networks of coupled chaotic oscillators is investigated. It is found that despite the asymmetric nature of the network structure, a subset of the oscillators can be synchronized as a cluster while the other oscillators remain desynchronized. Interestingly, with the increase of the coupling strength, the cluster is expanding gradually by recruiting the desynchronized oscillators one by one. This new synchronization phenomenon, which is named ``scalable synchronization cluster", is explored theoretically by the method of eigenvector-based analysis, and it is revealed that the scalability of the cluster is attributed to the unique feature of the eigenvectors of the network coupling matrix. The transient dynamics of the cluster in response to random perturbations are also studied, and it is shown that in restoring to the synchronization state, oscillators inside the cluster are stabilized in sequence, illustrating again the hierarchy of the oscillators. The findings shed new light on the collective behaviors of networked chaotic oscillators, and are helpful for the design of real-world networks where scalable synchronization clusters are concerned.

nlin.AO↗
arXiv2023

Sign Language Production with Latent Motion Transformer

Sign Language Production (SLP) is the tough task of turning sign language into sign videos. The main goal of SLP is to create these videos using a sign gloss. In this research, we've developed a new method to make high-quality sign videos without using human poses as a middle step. Our model works in two main parts: first, it learns from a generator and the video's hidden features, and next, it uses another model to understand the order of these hidden features. To make this method even better for sign videos, we make several significant improvements. (i) In the first stage, we take an improved 3D VQ-GAN to learn downsampled latent representations. (ii) In the second stage, we introduce sequence-to-sequence attention to better leverage conditional information. (iii) The separated two-stage training discards the realistic visual semantic of the latent codes in the second stage. To endow the latent sequences semantic information, we extend the token-level autoregressive latent codes learning with perceptual loss and reconstruction loss for the prior model with visual perception. Compared with previous state-of-the-art approaches, our model performs consistently better on two word-level sign language datasets, i.e., WLASL and NMFs-CSL.

cs.CV↗
arXiv2023

G2P-DDM: Generating Sign Pose Sequence from Gloss Sequence with Discrete Diffusion Model

The Sign Language Production (SLP) project aims to automatically translate spoken languages into sign sequences. Our approach focuses on the transformation of sign gloss sequences into their corresponding sign pose sequences (G2P). In this paper, we present a novel solution for this task by converting the continuous pose space generation problem into a discrete sequence generation problem. We introduce the Pose-VQVAE framework, which combines Variational Autoencoders (VAEs) with vector quantization to produce a discrete latent representation for continuous pose sequences. Additionally, we propose the G2P-DDM model, a discrete denoising diffusion architecture for length-varied discrete sequence data, to model the latent prior. To further enhance the quality of pose sequence generation in the discrete space, we present the CodeUnet model to leverage spatial-temporal information. Lastly, we develop a heuristic sequential clustering method to predict variable lengths of pose sequences for corresponding gloss sequences. Our results show that our model outperforms state-of-the-art G2P models on the public SLP evaluation benchmark. For more generated results, please visit our project page: \textcolor{blue}{\url{https://slpdiffusier.github.io/g2p-ddm}}

cs.CV↗
arXiv2023

Reconstructing bifurcation diagrams of chaotic circuits with reservoir computing

Model-free reconstruction of the bifurcation diagrams of Chua's circuits by the technique of parameter-aware reservoir computing is investigated. We demonstrate that: (1) reservoir computer can be utilized as a noise filter to recover the system trajectory from noisy signals; (2) for a single Chua circuit, the machine trained by the noisy time series measured at several sampling states is capable of reconstructing the whole bifurcation diagram of the circuit with a high precision; (3) for two coupled chaotic Chua circuits of mismatched parameters, the machine trained by the noisy time series measured at several coupling strengths is able to anticipate the variation of the synchronization degree of the coupled circuits with respect to the coupling strength over a wide range. The studies verify the capability of the technique of parameter-aware reservoir computing in learning the dynamics of chaotic circuits from noisy signals, signifying the potential application of this technique in reconstructing the bifurcation diagram of real-world chaotic systems.

cond-mat.dis-nn↗