arXiv subjects

Huanyu Zhang

Publications and source records attributed to Huanyu Zhang.

At least 37 records · Page 2Linked to original sources

arXiv2025

Nonequilibrium hysteretic phase transitions in periodically light-driven superconductors

We find nonequilibrium phase transitions accompanied by multiple (nested) hysteresis behaviors in superconductors coupled to baths under a time-periodic light driving. The transitions are demonstrated with a full phase diagram in the domain of the driving amplitude and frequency by means of the Floquet many-body theory. In the weak driving regime with a frequency smaller than half of the superconducting gap, excited quasiparticles are accumulated at the far edges of the bands, realizing a distribution reminiscent of the Eliashberg effect, which suddenly becomes unstable in the strong driving regime due to multi-photon-assisted tunneling across the gap mediated by the in-gap Floquet sidebands. We also show that superconductivity is enhanced in the weak driving regime without effective cooling, which is attributed to the modulation of the spectrum due to Floquet sidebands.

cond-mat.supr-con↗

arXiv2025

MM-RLHF: The Next Step Forward in Multimodal LLM Alignment

Despite notable advancements in Multimodal Large Language Models (MLLMs), most state-of-the-art models have not undergone thorough alignment with human preferences. This gap exists because current alignment research has primarily achieved progress in specific areas (e.g., hallucination reduction), while the broader question of whether aligning models with human preferences can systematically enhance MLLM capability remains largely unexplored. To this end, we introduce MM-RLHF, a dataset containing $\mathbf{120k}$ fine-grained, human-annotated preference comparison pairs. This dataset represents a substantial advancement over existing resources, offering superior size, diversity, annotation granularity, and quality. Leveraging this dataset, we propose several key innovations to improve both the quality of reward models and the efficiency of alignment algorithms. Notably, we introduce a Critique-Based Reward Model, which generates critiques of model outputs before assigning scores, offering enhanced interpretability and more informative feedback compared to traditional scalar reward mechanisms. Additionally, we propose Dynamic Reward Scaling, a method that adjusts the loss weight of each sample according to the reward signal, thereby optimizing the use of high-quality comparison pairs. Our approach is rigorously evaluated across $\mathbf{10}$ distinct dimensions and $\mathbf{27}$ benchmarks, with results demonstrating significant and consistent improvements in model performance. Specifically, fine-tuning LLaVA-ov-7B with MM-RLHF and our alignment algorithm leads to a $\mathbf{19.5}$% increase in conversational abilities and a $\mathbf{60}$% improvement in safety. We have open-sourced the preference dataset, reward model, training and evaluation code, as well as reward modeling and safety benchmarks. For more details, please visit our project page: https://mm-rlhf.github.io.

cs.CL↗

arXiv2025

MME-RealWorld: Could Your Multimodal LLM Challenge High-Resolution Real-World Scenarios that are Difficult for Humans?

Comprehensive evaluation of Multimodal Large Language Models (MLLMs) has recently garnered widespread attention in the research community. However, we observe that existing benchmarks present several common barriers that make it difficult to measure the significant challenges that models face in the real world, including: 1) small data scale leads to a large performance variance; 2) reliance on model-based annotations results in restricted data quality; 3) insufficient task difficulty, especially caused by the limited image resolution. To tackle these issues, we introduce MME-RealWorld. Specifically, we collect more than $300$K images from public datasets and the Internet, filtering $13,366$ high-quality images for annotation. This involves the efforts of professional $25$ annotators and $7$ experts in MLLMs, contributing to $29,429$ question-answer pairs that cover $43$ subtasks across $5$ real-world scenarios, extremely challenging even for humans. As far as we know, MME-RealWorld is the largest manually annotated benchmark to date, featuring the highest resolution and a targeted focus on real-world applications. We further conduct a thorough evaluation involving $28$ prominent MLLMs, such as GPT-4o, Gemini 1.5 Pro, and Claude 3.5 Sonnet. Our results show that even the most advanced models struggle with our benchmarks, where none of them reach $60\%$ accuracy. The challenges of perceiving high-resolution images and understanding complex real-world scenarios remain urgent issues to be addressed. The data and evaluation code are released at https://mme-realworld.github.io/ .

cs.CV↗

arXiv2025

Imagine while Reasoning in Space: Multimodal Visualization-of-Thought

Chain-of-Thought (CoT) prompting has proven highly effective for enhancing complex reasoning in Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs). Yet, it struggles in complex spatial reasoning tasks. Nonetheless, human cognition extends beyond language alone, enabling the remarkable capability to think in both words and images. Inspired by this mechanism, we propose a new reasoning paradigm, Multimodal Visualization-of-Thought (MVoT). It enables visual thinking in MLLMs by generating image visualizations of their reasoning traces. To ensure high-quality visualization, we introduce token discrepancy loss into autoregressive MLLMs. This innovation significantly improves both visual coherence and fidelity. We validate this approach through several dynamic spatial reasoning tasks. Experimental results reveal that MVoT demonstrates competitive performance across tasks. Moreover, it exhibits robust and reliable improvements in the most challenging scenarios where CoT fails. Ultimately, MVoT establishes new possibilities for complex reasoning tasks where visual thinking can effectively complement verbal reasoning.

cs.CL↗

arXiv2025

A self-learning magnetic Hopfield neural network with intrinsic gradient descent adaption

Physical neural networks using physical materials and devices to mimic synapses and neurons offer an energy-efficient way to implement artificial neural networks. Yet, training physical neural networks are difficult and heavily relies on external computing resources. An emerging concept to solve this issue is called physical self-learning that uses intrinsic physical parameters as trainable weights. Under external inputs (i.e. training data), training is achieved by the natural evolution of physical parameters that intrinsically adapt modern learning rules via autonomous physical process, eliminating the requirements on external computation resources.Here, we demonstrate a real spintronic system that mimics Hopfield neural networks (HNN) and unsupervised learning is intrinsically performed via the evolution of physical process. Using magnetic texture defined conductance matrix as trainable weights, we illustrate that under external voltage inputs, the conductance matrix naturally evolves and adapts Oja's learning algorithm in a gradient descent manner. The self-learning HNN is scalable and can achieve associative memories on patterns with high similarities. The fast spin dynamics and reconfigurability of magnetic textures offer an advantageous platform towards efficient autonomous training directly in materials.

cond-mat.dis-nn↗

arXiv2024

TimeRAF: Retrieval-Augmented Foundation model for Zero-shot Time Series Forecasting

Time series forecasting plays a crucial role in data mining, driving rapid advancements across numerous industries. With the emergence of large models, time series foundation models (TSFMs) have exhibited remarkable generalization capabilities, such as zero-shot learning, through large-scale pre-training. Meanwhile, Retrieval-Augmented Generation (RAG) methods have been widely employed to enhance the performance of foundation models on unseen data, allowing models to access to external knowledge. In this paper, we introduce TimeRAF, a Retrieval-Augmented Forecasting model that enhance zero-shot time series forecasting through retrieval-augmented techniques. We develop customized time series knowledge bases that are tailored to the specific forecasting tasks. TimeRAF employs an end-to-end learnable retriever to extract valuable information from the knowledge base. Additionally, we propose Channel Prompting for knowledge integration, which effectively extracts relevant information from the retrieved knowledge along the channel dimension. Extensive experiments demonstrate the effectiveness of our model, showing significant improvement across various domains and datasets.

cs.LG↗

arXiv2024

Probing disorder-induced time-reversal symmetry breaking in Josephson junctions

The relation between superconductivity and time-reversal symmetry (TRS) is one of the most fascinating problems in condensed matter physics. Although most superconductors inherently possess TRS, nonmagnetic disorder can induce states that demonstrate the breaking of this symmetry. Yet, the identification of experimental signatures of superconductivity with broken TRS remains a challenge. Here, we fabricate vertical Josephson junctions using metallic superconductor (Al) and ion bombarded Sr2RuO4 to study disorder-driven TRS breaking effects. We observe persistent magnetoresistive hysteresis behavior dependent on the disorder deposition time that provides evidence of TRS breaking below the superconducting transition temperature. Field and temperature dependent measurements suggest that the observed effects arise from disorder-induced anomalous flux in Sr2RuO4 which can be sensitively detected by superconducting Al. Our experimental results can be accounted within a physical framework of disorder-induced reconstruction of the superconducting order parameter as described within a multiband Ginzburg-Landau approach.

cond-mat.supr-con↗

arXiv2024

LogoRA: Local-Global Representation Alignment for Robust Time Series Classification

Unsupervised domain adaptation (UDA) of time series aims to teach models to identify consistent patterns across various temporal scenarios, disregarding domain-specific differences, which can maintain their predictive accuracy and effectively adapt to new domains. However, existing UDA methods struggle to adequately extract and align both global and local features in time series data. To address this issue, we propose the Local-Global Representation Alignment framework (LogoRA), which employs a two-branch encoder, comprising a multi-scale convolutional branch and a patching transformer branch. The encoder enables the extraction of both local and global representations from time series. A fusion module is then introduced to integrate these representations, enhancing domain-invariant feature alignment from multi-scale perspectives. To achieve effective alignment, LogoRA employs strategies like invariant feature learning on the source domain, utilizing triplet loss for fine alignment and dynamic time warping-based feature alignment. Additionally, it reduces source-target domain gaps through adversarial training and per-class prototype alignment. Our evaluations on four time-series datasets demonstrate that LogoRA outperforms strong baselines by up to $12.52\%$, showcasing its superiority in time series UDA tasks.

cs.LG↗

arXiv2024

Statler: State-Maintaining Language Models for Embodied Reasoning

There has been a significant research interest in employing large language models to empower intelligent robots with complex reasoning. Existing work focuses on harnessing their abilities to reason about the histories of their actions and observations. In this paper, we explore a new dimension in which large language models may benefit robotics planning. In particular, we propose Statler, a framework in which large language models are prompted to maintain an estimate of the world state, which are often unobservable, and track its transition as new actions are taken. Our framework then conditions each action on the estimate of the current world state. Despite being conceptually simple, our Statler framework significantly outperforms strong competing methods (e.g., Code-as-Policies) on several robot planning tasks. Additionally, it has the potential advantage of scaling up to more challenging long-horizon planning tasks.

cs.RO↗

arXiv2024

Contraction of Locally Differentially Private Mechanisms

We investigate the contraction properties of locally differentially private mechanisms. More specifically, we derive tight upper bounds on the divergence between $PK$ and $QK$ output distributions of an $ε$-LDP mechanism $K$ in terms of a divergence between the corresponding input distributions $P$ and $Q$, respectively. Our first main technical result presents a sharp upper bound on the $χ^2$-divergence $χ^2(PK}\|QK)$ in terms of $χ^2(P\|Q)$ and $\varepsilon$. We also show that the same result holds for a large family of divergences, including KL-divergence and squared Hellinger distance. The second main technical result gives an upper bound on $χ^2(PK\|QK)$ in terms of total variation distance $\mathsf{TV}(P, Q)$ and $ε$. We then utilize these bounds to establish locally private versions of the van Trees inequality, Le Cam's, Assouad's, and the mutual information methods, which are powerful tools for bounding minimax estimation risks. These results are shown to lead to better privacy analyses than the state-of-the-arts in several statistical problems such as entropy and discrete distribution estimation, non-parametric density estimation, and hypothesis testing.

cs.IT↗

arXiv2024

Advancing Differential Privacy: Where We Are Now and Future Directions for Real-World Deployment

In this article, we present a detailed review of current practices and state-of-the-art methodologies in the field of differential privacy (DP), with a focus of advancing DP's deployment in real-world applications. Key points and high-level contents of the article were originated from the discussions from "Differential Privacy (DP): Challenges Towards the Next Frontier," a workshop held in July 2022 with experts from industry, academia, and the public sector seeking answers to broad questions pertaining to privacy and its implications in the design of industry-grade systems. This article aims to provide a reference point for the algorithmic and design decisions within the realm of privacy, highlighting important challenges and potential research directions. Covering a wide spectrum of topics, this article delves into the infrastructure needs for designing private systems, methods for achieving better privacy/utility trade-offs, performing privacy attacks and auditing, as well as communicating privacy with broader audiences and stakeholders.

cs.CR↗

arXiv2024

Correlation between magnetic domain structures and quantum anomalous Hall effect in epitaxial MnBi2Te4 thin films

We use magnetic force microscopy (MFM) to study spatial uniformity of magnetization of epitaxially grown MnBi2Te4 thin films. Compared to films which exhibit no quantum anomalous Hall effect (QAH), films with QAH are observed to have more spatial uniformity of magnetization with larger domain size. The domain evolution upon magnetic field sweeping indicates that the magnetic domains or the spatial nonuniformity of magnetization originates from the strong pinning of the inherent sample inhomogeneity. A direct correlation between the Hall resistivity and the domain size has been established by analyzing a series of thin films with and without QAH. Our observation shows that one has to suppress the spatial nonuniformity of magnetization to allow the Hall resistivity to be quantized. The fact that a sizable longitudinal resistivity remains even for the QAH sample suggests a quantized Hall insulator scenario. Our work provides important insights to the understanding of the quantization mechanism and the dissipation of the QAH state in MnBi2Te4 system.

cond-mat.mes-hall↗

arXiv2023

DP-HyPO: An Adaptive Private Hyperparameter Optimization Framework

Hyperparameter optimization, also known as hyperparameter tuning, is a widely recognized technique for improving model performance. Regrettably, when training private ML models, many practitioners often overlook the privacy risks associated with hyperparameter optimization, which could potentially expose sensitive information about the underlying dataset. Currently, the sole existing approach to allow privacy-preserving hyperparameter optimization is to uniformly and randomly select hyperparameters for a number of runs, subsequently reporting the best-performing hyperparameter. In contrast, in non-private settings, practitioners commonly utilize ``adaptive'' hyperparameter optimization methods such as Gaussian process-based optimization, which select the next candidate based on information gathered from previous outputs. This substantial contrast between private and non-private hyperparameter optimization underscores a critical concern. In our paper, we introduce DP-HyPO, a pioneering framework for ``adaptive'' private hyperparameter optimization, aiming to bridge the gap between private and non-private hyperparameter optimization. To accomplish this, we provide a comprehensive differential privacy analysis of our framework. Furthermore, we empirically demonstrate the effectiveness of DP-HyPO on a diverse set of real-world datasets.

cs.LG↗

arXiv2023

Federated Linear Contextual Bandits with User-level Differential Privacy

This paper studies federated linear contextual bandits under the notion of user-level differential privacy (DP). We first introduce a unified federated bandits framework that can accommodate various definitions of DP in the sequential decision-making setting. We then formally introduce user-level central DP (CDP) and local DP (LDP) in the federated bandits framework, and investigate the fundamental trade-offs between the learning regrets and the corresponding DP guarantees in a federated linear contextual bandits model. For CDP, we propose a federated algorithm termed as $\texttt{ROBIN}$ and show that it is near-optimal in terms of the number of clients $M$ and the privacy budget $\varepsilon$ by deriving nearly-matching upper and lower regret bounds when user-level DP is satisfied. For LDP, we obtain several lower bounds, indicating that learning under user-level $(\varepsilon,δ)$-LDP must suffer a regret blow-up factor at least $\min\{1/\varepsilon,M\}$ or $\min\{1/\sqrt{\varepsilon},\sqrt{M}\}$ under different conditions.

cs.LG↗

arXiv2022

Direct visualization of edge state in even-layer MnBi2Te4 at zero magnetic field

Being the first intrinsic antiferromagnetic(AFM) topological insulator(TI), MnBi2Te4 is argued to be a topological axion state in its even-layer form due to the antiparallel magnetization between the top and bottom layers. Here we combine both transport and scanning microwave impedance microscopy(sMIM) to investigate such axion state in atomically thin MnBi2Te4 with even-layer thickness at zero magnetic field. While transport measurements show a zero Hall plateau signaturing the axion state, sMIM uncovers an unexpected edge state raising questions regarding the nature of the 'axion state'. Based on our model calculation, we propose that the edge state of even-layer MnBi2Te4 at zero field is derived from gapped helical edge states of the quantum spin Hall effect with time-reversal-symmetry breaking, when a crossover from a three-dimensional TI MnBi2Te4 to a two-dimensional TI occurs. Our finding thus signifies the richness of topological phases in MnB2Te4 that has yet to be fully explored.

cond-mat.mes-hall↗

arXiv2022

Improved Rates for Differentially Private Stochastic Convex Optimization with Heavy-Tailed Data

We study stochastic convex optimization with heavy-tailed data under the constraint of differential privacy (DP). Most prior work on this problem is restricted to the case where the loss function is Lipschitz. Instead, as introduced by Wang, Xiao, Devadas, and Xu \cite{WangXDX20}, we study general convex loss functions with the assumption that the distribution of gradients has bounded $k$-th moments. We provide improved upper bounds on the excess population risk under concentrated DP for convex and strongly convex loss functions. Along the way, we derive new algorithms for private mean estimation of heavy-tailed distributions, under both pure and concentrated DP. Finally, we prove nearly-matching lower bounds for private stochastic convex optimization with strongly convex losses and mean estimation, showing new separations between pure and concentrated DP.

cs.LG↗

arXiv2022

Estimating Smooth GLM in Non-interactive Local Differential Privacy Model with Public Unlabeled Data

In this paper, we study the problem of estimating smooth Generalized Linear Models (GLMs) in the Non-interactive Local Differential Privacy (NLDP) model. Different from its classical setting, our model allows the server to access some additional public but unlabeled data. In the first part of the paper we focus on GLMs. Specifically, we first consider the case where each data record is i.i.d. sampled from a zero-mean multivariate Gaussian distribution. Motivated by the Stein's lemma, we present an $(ε, δ)$-NLDP algorithm for GLMs. Moreover, the sample complexity of public and private data for the algorithm to achieve an $\ell_2$-norm estimation error of $α$ (with high probability) is ${O}(p α^{-2})$ and $\tilde{O}(p^3α^{-2}ε^{-2})$ respectively, where $p$ is the dimension of the feature vector. This is a significant improvement over the previously known exponential or quasi-polynomial in $α^{-1}$, or exponential in $p$ sample complexities of GLMs with no public data. Then we consider a more general setting where each data record is i.i.d. sampled from some sub-Gaussian distribution with bounded $\ell_1$-norm. Based on a variant of Stein's lemma, we propose an $(ε, δ)$-NLDP algorithm for GLMs whose sample complexity of public and private data to achieve an $\ell_\infty$-norm estimation error of $α$ is ${O}(p^2α^{-2})$ and $\tilde{O}(p^2α^{-2}ε^{-2})$ respectively, under some mild assumptions and if $α$ is not too small ({\em i.e.,} $α\geq Ω(\frac{1}{\sqrt{p}})$). In the second part of the paper, we extend our idea to the problem of estimating non-linear regressions and show similar results as in GLMs for both multivariate Gaussian and sub-Gaussian cases. Finally, we demonstrate the effectiveness of our algorithms through experiments on both synthetic and real-world datasets.

cs.LG↗

arXiv2022

Direct visualization of percolating metal-insulator transition in V2O3 using scanning microwave impedance microscopy

Using the extensively studied V2O3 as a prototype system, we investigate the role of percolation in metal-insulator transition (MIT). We apply scanning microwave impedance microscopy to directly determine the metallic phase fraction p and relate it to the macroscopic conductance G, which shows a sudden jump when p reaches the percolation threshold. Interestingly, the conductance G exhibits a hysteretic behavior against p, suggesting two different percolating processes upon cooling and warming. Based on our image analysis and model simulation, we ascribe such hysteretic behavior to different domain nucleation and growth processes between cooling and warming, which is likely caused by the decoupled structural and electronic transitions in V2O3 during MIT. Our work provides a microscopic view of how the interplay of structural and electronic degrees of freedom affects MIT in strongly correlated systems.

cond-mat.str-el↗