arXiv subjects

Tianyi Wu

Publications and source records attributed to Tianyi Wu.

At least 37 records · Page 2Linked to original sources

arXiv2025

Anomalous terahertz nonlinearity in disordered s-wave superconductor close to the superconductor-insulator transition

Detection of the Higgs mode in superconductors using nonlinear terahertz spectroscopy is a key area of interest in condensed matter physics. We investigate the influence of disorder on the nonlinear terahertz response and the Higgs mode in NbN thin films with varying Ioffe-Regel parameters ($k_Fl$). In strongly disordered films near the superconductor-insulator transition (SIT), we observe an anomalous third-harmonic generation (THG) signal above $T_c$, which is absent in both cleaner superconducting and non-superconducting counterparts. The persistence of this normal-state THG signal in a high magnetic field excludes superconducting fluctuations as its origin. Below $T_c$, the THG intensity increases sharply, indicating a dominant contribution from the driven Higgs mode. The THG spectrum of the strongly disordered sample exhibits a broadened, multi-peak structure, which we attribute to quantum path interference between distinct channels involving unpaired electrons and Cooper pairs within emergent superconducting islands. Our findings not only demonstrate how disorder tunes the nonlinear terahertz response but also uncover a strong coupling between electrons responsible for normal-state THG and the superconducting Higgs mode below $T_c$ in strongly disordered samples.

cond-mat.supr-con↗

arXiv2025

Neural Diffeomorphic-Neural Operator for Residual Stress-Induced Deformation Prediction

Accurate prediction of machining deformation in structural components is essential for ensuring dimensional precision and reliability. Such deformation often originates from residual stress fields, whose distribution and influence vary significantly with geometric complexity. Conventional numerical methods for modeling the coupling between residual stresses and deformation are computationally expensive, particularly when diverse geometries are considered. Neural operators have recently emerged as a powerful paradigm for efficiently solving partial differential equations, offering notable advantages in accelerating residual stress-deformation analysis. However, their direct application across changing geometric domains faces theoretical and practical limitations. To address this challenge, a novel framework based on diffeomorphic embedding neural operators named neural diffeomorphic-neural operator (NDNO) is introduced. Complex three-dimensional geometries are explicitly mapped to a common reference domain through a diffeomorphic neural network constrained by smoothness and invertibility. The neural operator is then trained on this reference domain, enabling efficient learning of deformation fields induced by residual stresses. Once trained, both the diffeomorphic neural network and the neural operator demonstrate efficient prediction capabilities, allowing rapid adaptation to varying geometries. The proposed method thus provides an effective and computationally efficient solution for deformation prediction in structural components subject to varying geometries. The proposed method is validated to predict both main-direction and multi-direction deformation fields, achieving high accuracy and efficiency across parts with diverse geometries including component types, dimensions and features.

cs.LG↗

arXiv2025

Exploiting Scale-Variant Attention for Segmenting Small Medical Objects

Early detection and accurate diagnosis can predict the risk of malignant disease transformation, thereby increasing the probability of effective treatment. Identifying mild syndrome with small pathological regions serves as an ominous warning and is fundamental in the early diagnosis of diseases. While deep learning algorithms, particularly convolutional neural networks (CNNs), have shown promise in segmenting medical objects, analyzing small areas in medical images remains challenging. This difficulty arises due to information losses and compression defects from convolution and pooling operations in CNNs, which become more pronounced as the network deepens, especially for small medical objects. To address these challenges, we propose a novel scale-variant attention-based network (SvANet) for accurately segmenting small-scale objects in medical images. The SvANet consists of scale-variant attention, cross-scale guidance, Monte Carlo attention, and vision transformer, which incorporates cross-scale features and alleviates compression artifacts for enhancing the discrimination of small medical objects. Quantitative experimental results demonstrate the superior performance of SvANet, achieving 96.12%, 96.11%, 89.79%, 84.15%, 80.25%, 73.05%, and 72.58% in mean Dice coefficient for segmenting kidney tumors, skin lesions, hepatic tumors, polyps, surgical excision cells, retinal vasculatures, and sperms, which occupy less than 1% of the image areas in KiTS23, ISIC 2018, ATLAS, PolypGen, TissueNet, FIVES, and SpermHealth datasets, respectively.

eess.IV↗

arXiv2025

Balancing Truthfulness and Informativeness with Uncertainty-Aware Instruction Fine-Tuning

Instruction fine-tuning (IFT) can increase the informativeness of large language models (LLMs), but may reduce their truthfulness. This trade-off arises because IFT steers LLMs to generate responses containing long-tail knowledge that was not well covered during pre-training. As a result, models become more informative but less accurate when generalizing to unseen tasks. In this paper, we empirically demonstrate how unfamiliar knowledge in IFT datasets can negatively affect the truthfulness of LLMs, and we introduce two new IFT paradigms, $UNIT_{cut}$ and $UNIT_{ref}$, to address this issue. $UNIT_{cut}$ identifies and removes unfamiliar knowledge from IFT datasets to mitigate its impact on model truthfulness, whereas $UNIT_{ref}$ trains LLMs to recognize their uncertainty and explicitly indicate it at the end of their responses. Our experiments show that $UNIT_{cut}$ substantially improves LLM truthfulness, while $UNIT_{ref}$ maintains high informativeness and reduces hallucinations by distinguishing between confident and uncertain statements.

cs.CL↗

arXiv2025

Value Residual Learning

While Transformer models have achieved remarkable success in various domains, the effectiveness of information propagation through deep networks remains a critical challenge. Standard hidden state residuals often fail to adequately preserve initial token-level information in deeper layers. This paper introduces ResFormer, a novel architecture that enhances information flow by incorporating value residual connections in addition to hidden state residuals. And a variant is SVFormer, where all layers share the first layer's value embedding. Comprehensive empirical evidence demonstrates ResFormer achieves equivalent validation loss with 16.11\% fewer model parameters and 20.3\% less training data compared to Transformer, while maintaining similar memory usage and computational cost. Besides, SVFormer reduces KV cache size by nearly half with only a small performance penalty and can be integrated with other KV-efficient methods, yielding further reductions in KV cache, with performance influenced by sequence length and cumulative learning rate.

cs.CL↗

arXiv2025

Criticality and Universality of Generalized Kuramoto Model

We explore synchronization transitions in even-$D$-dimensional generalized Kuramoto oscillators on both complete graphs and $d$-dimensional lattices. In the globally coupled system, analytical expansions of the self-consistency equations, incorporating finite-size corrections, reveal universal critical exponents $β= 1/2$ and $\barν = 5/2$ for all even $D$, indicating an unconventional upper critical dimension $d_u = 5$. Extensive numerical simulations across multiple $D$ confirm these theoretical predictions. For locally coupled systems, we develop a framework based on spin-wave theory and fluctuation-resolved functional network diagnostics, which captures criticality in entrainment transition. A modified Edwards-Anderson order parameter further validates the predicted exponents. This combined theoretical and numerical study uncovers a family of universality classes characterized by $D$-independent but $d$-dependent criticality, offering a unified perspective on symmetry and dimensionality in nonequilibrium synchronization phenomena.

cond-mat.stat-mech↗

arXiv2025

New Sphere Packings from the Antipode Construction

In this note, we construct non-lattice sphere packings in dimensions $19$, $20$, $21$, $23$, $44$, $45$, and $47$, demonstrating record densities that surpass all previously documented results in these dimensions. The construction involves applying the antipode method to suboptimal cross-sections of $Λ_{24}$ and $P_{48p}$ respectively in those dimensions.

math.MG↗

arXiv2025

Geneshift: Impact of different scenario shift on Jailbreaking LLM

Jailbreak attacks, which aim to cause LLMs to perform unrestricted behaviors, have become a critical and challenging direction in AI safety. Despite achieving the promising attack success rate using dictionary-based evaluation, existing jailbreak attack methods fail to output detailed contents to satisfy the harmful request, leading to poor performance on GPT-based evaluation. To this end, we propose a black-box jailbreak attack termed GeneShift, by using a genetic algorithm to optimize the scenario shifts. Firstly, we observe that the malicious queries perform optimally under different scenario shifts. Based on it, we develop a genetic algorithm to evolve and select the hybrid of scenario shifts. It guides our method to elicit detailed and actionable harmful responses while keeping the seemingly benign facade, improving stealthiness. Extensive experiments demonstrate the superiority of GeneShift. Notably, GeneShift increases the jailbreak success rate from 0% to 60% when direct prompting alone would fail.

cs.CR↗

arXiv2025

RWKV-7 "Goose" with Expressive Dynamic State Evolution

We present RWKV-7 "Goose", a new sequence modeling architecture with constant memory usage and constant inference time per token. Despite being trained on dramatically fewer tokens than other top models, our 2.9 billion parameter language model achieves a new 3B SoTA on multilingual tasks and matches the current 3B SoTA on English language downstream performance. RWKV-7 introduces a newly generalized formulation of the delta rule with vector-valued gating and in-context learning rates, as well as a relaxed value replacement rule. We show that RWKV-7 can perform state tracking and recognize all regular languages, while retaining parallelizability of training. This exceeds the capabilities of Transformers under standard complexity conjectures, which are limited to $\mathsf{TC}^0$. To demonstrate RWKV-7's language modeling capability, we also present an extended open source 3.1 trillion token multilingual corpus, and train four RWKV-7 models ranging from 0.19 billion to 2.9 billion parameters on this dataset. To foster openness, reproduction, and adoption, we release our models and dataset component listing at https://huggingface.co/RWKV, and our training and inference code at https://github.com/RWKV/RWKV-LM all under the Apache 2.0 License.

cs.CL↗

arXiv2025

IGN : Implicit Generative Networks

In this work, we build recent advances in distributional reinforcement learning to give a state-of-art distributional variant of the model based on the IQN. We achieve this by using the GAN model's generator and discriminator function with the quantile regression to approximate the full quantile value for the state-action return distribution. We demonstrate improved performance on our baseline dataset - 57 Atari 2600 games in the ALE. Also, we use our algorithm to show the state-of-art training performance of risk-sensitive policies in Atari games with the policy optimization and evaluation.

cs.LG↗

arXiv2025

Gödel Incompleteness Theorem for PAC Learnable Theory from the view of complexity measurement

Different from the view that information is objective reality, this paper adopts the idea that all information needs to be compiled by the interpreter before it can be observed. From the traditional complexity definition, this paper defines the complexity under "the interpreter", which means that heuristically finding the best interpreter is equivalent to using PAC to find the most suitable interpreter. Then we generalize the observation process to the formal system with functors, in which we give concrete proof of the generalized Gödel incompleteness theorem which indicates that there are some objects that are PAC-learnable, but the best interpreter is not found among the alternative interpreters. A strong enough machine algorithm cannot be interpretable in the face of any object. There are always objects that make a strong enough machine learning algorithm uninterpretable, which puts an upper bound on the generalization ability of strong AI.

cs.LO↗

arXiv2024

Selective excitation of collective modes in multiband superconductor MgB2

Recent developments in nonequilibrium and nonlinear terahertz (THz) spectroscopies have significantly advanced our understanding of collective excitations in superconductors. However, there is still debate surrounding the identification of Higgs or Leggett modes, as well as BCS charge fluctuations, in the well-known two-band superconductor MgB$_2$. Here, we utilized both multi-cycle and single-cycle THz pump-broadband THz probe techniques to investigate the THz nonlinear response of MgB$_2$. Through multicycle THz pump-THz probe experiments on MgB$_2$, we observed distinct nonlinear signals at both the fundamental frequency ($ω$) and the second harmonic frequency (2$ω$) of the pump pulses, which exhibited resonant enhancement at temperatures where their frequencies respectively match 2$Δ_π(T)$. They are mainly attributed to the $π$-band Higgs mode. By adjusting the THz pump pulse to a single-cycle waveform that satisfies non-adiabatic excitation criteria, we observed an over-damped oscillation corresponding to the Leggett mode. Our findings contribute to solving the ongoing debates and demonstrate the selective excitation of collective modes in multiband superconductors, offering new insights into the interaction between Higgs and Leggett modes.

cond-mat.supr-con↗

arXiv2024

Dual-Optimized Adaptive Graph Reconstruction for Multi-View Graph Clustering

Multi-view clustering is an important machine learning task for multi-media data, encompassing various domains such as images, videos, and texts. Moreover, with the growing abundance of graph data, the significance of multi-view graph clustering (MVGC) has become evident. Most existing methods focus on graph neural networks (GNNs) to extract information from both graph structure and feature data to learn distinguishable node representations. However, traditional GNNs are designed with the assumption of homophilous graphs, making them unsuitable for widely prevalent heterophilous graphs. Several techniques have been introduced to enhance GNNs for heterophilous graphs. While these methods partially mitigate the heterophilous graph issue, they often neglect the advantages of traditional GNNs, such as their simplicity, interpretability, and efficiency. In this paper, we propose a novel multi-view graph clustering method based on dual-optimized adaptive graph reconstruction, named DOAGC. It mainly aims to reconstruct the graph structure adapted to traditional GNNs to deal with heterophilous graph issues while maintaining the advantages of traditional GNNs. Specifically, we first develop an adaptive graph reconstruction mechanism that accounts for node correlation and original structural information. To further optimize the reconstruction graph, we design a dual optimization strategy and demonstrate the feasibility of our optimization strategy through mutual information theory. Numerous experiments demonstrate that DOAGC effectively mitigates the heterophilous graph problem.

cs.LG↗

arXiv2024

Room-temperature non-volatile optical manipulation of polar order in a charge density wave

Utilizing ultrafast light-matter interaction to manipulate electronic states of quantum materials is an emerging area of research in condensed matter physics. It has significant implications for the development of future ultrafast electronic devices. However, the ability to induce long-lasting metastable electronic states in a fully reversible manner is a long-standing challenge.Here, by using ultrafast laser excitations, we demonstrate the capability to manipulate the electronic polar states in the charge-density-wavematerial EuTe4 in a non-volatile manner. The process is completely reversible and is achieved at room temperature with an all-optical approach. Each induced non-volatile state brings about modifications to the electrical resistance and second harmonic generation intensity. The results point to layer-specific phase inversion dynamics by which photoexcitation mediates the stacking polar order of the system. Our findings extend the scope of non-volatile all-optical control of electronic states to ambient conditions, and highlight a distinct role of layerdependent phase manipulation in quasi-two-dimensional systems with inherent sublayer stacking orders.

cond-mat.str-el↗

arXiv2024

SiMilarity-Enhanced Homophily for Multi-View Heterophilous Graph Clustering

With the increasing prevalence of graph-structured data, multi-view graph clustering has been widely used in various downstream applications. Existing approaches primarily rely on a unified message passing mechanism, which significantly enhances clustering performance. Nevertheless, this mechanism limits its applicability to heterophilous situations, as it is fundamentally predicated on the assumption of homophily, i.e., the connected nodes often belong to the same class. In reality, this assumption does not always hold; a moderately or even mildly homophilous graph is more common than a fully homophilous one due to inevitable heterophilous information in the graph. To address this issue, in this paper, we propose a novel SiMilarity-enhanced Homophily for Multi-view Heterophilous Graph Clustering (SMHGC) approach. By analyzing the relationship between similarity and graph homophily, we propose to enhance the homophily by introducing three similarity terms, i.e., neighbor pattern similarity, node feature similarity, and multi-view global similarity, in a label-free manner. Then, a consensus-based inter- and intra-view fusion paradigm is proposed to fuse the improved homophilous graph from different views and utilize them for clustering. The state-of-the-art experimental results on both multi-view heterophilous and homophilous datasets collectively demonstrate the strong capacity of similarity for unsupervised multi-view heterophilous graph learning. Additionally, the consistent performance across semi-synthetic datasets with varying levels of homophily serves as further evidence of SMHGC's resilience to heterophily.

cs.AI↗

arXiv2024

MedTsLLM: Leveraging LLMs for Multimodal Medical Time Series Analysis

The complexity and heterogeneity of data in many real-world applications pose significant challenges for traditional machine learning and signal processing techniques. For instance, in medicine, effective analysis of diverse physiological signals is crucial for patient monitoring and clinical decision-making and yet highly challenging. We introduce MedTsLLM, a general multimodal large language model (LLM) framework that effectively integrates time series data and rich contextual information in the form of text to analyze physiological signals, performing three tasks with clinical relevance: semantic segmentation, boundary detection, and anomaly detection in time series. These critical tasks enable deeper analysis of physiological signals and can provide actionable insights for clinicians. We utilize a reprogramming layer to align embeddings of time series patches with a pretrained LLM's embedding space and make effective use of raw time series, in conjunction with textual context. Given the multivariate nature of medical datasets, we develop methods to handle multiple covariates. We additionally tailor the text prompt to include patient-specific information. Our model outperforms state-of-the-art baselines, including deep learning models, other LLMs, and clinical methods across multiple medical domains, specifically electrocardiograms and respiratory waveforms. MedTsLLM presents a promising step towards harnessing the power of LLMs for medical time series analysis that can elevate data-driven tools for clinicians and improve patient outcomes.

cs.LG↗

arXiv2024

Temporal bistability in the dissipative Dicke-Bose-Hubbard system

We consider a driven-dissipative system consisting of an atomic Bose-Einstein condensates loaded into a two-dimensional Hubbard lattice and coupled to a single mode of an optical cavity. Due to the interplay between strong, repulsive atomic interaction and the atom-cavity coupling, the system exhibits several phases of atoms and photons including the atomic superfluid (SF) and supersolid (SS). We investigate the dynamical behaviour of the system, where we include dissipation by means of Lindblad master equation formalism. Due to the discontinuous nature of the Dicke transition for strong atomic repulsion, we find extended co-existence region of different phases. We investigate the resulting switching dynamics, particularly between the coexisting SF and SS phases, which eventually becomes damped by the dissipation.

cond-mat.quant-gas↗

arXiv2024

Homophily-Related: Adaptive Hybrid Graph Filter for Multi-View Graph Clustering

Recently there is a growing focus on graph data, and multi-view graph clustering has become a popular area of research interest. Most of the existing methods are only applicable to homophilous graphs, yet the extensive real-world graph data can hardly fulfill the homophily assumption, where the connected nodes tend to belong to the same class. Several studies have pointed out that the poor performance on heterophilous graphs is actually due to the fact that conventional graph neural networks (GNNs), which are essentially low-pass filters, discard information other than the low-frequency information on the graph. Nevertheless, on certain graphs, particularly heterophilous ones, neglecting high-frequency information and focusing solely on low-frequency information impedes the learning of node representations. To break this limitation, our motivation is to perform graph filtering that is closely related to the homophily degree of the given graph, with the aim of fully leveraging both low-frequency and high-frequency signals to learn distinguishable node embedding. In this work, we propose Adaptive Hybrid Graph Filter for Multi-View Graph Clustering (AHGFC). Specifically, a graph joint process and graph joint aggregation matrix are first designed by using the intrinsic node features and adjacency relationship, which makes the low and high-frequency signals on the graph more distinguishable. Then we design an adaptive hybrid graph filter that is related to the homophily degree, which learns the node embedding based on the graph joint aggregation matrix. After that, the node embedding of each view is weighted and fused into a consensus embedding for the downstream task. Experimental results show that our proposed model performs well on six datasets containing homophilous and heterophilous graphs.

cs.LG↗