arXiv subjects

Yu-Hao Huang

Publications and source records attributed to Yu-Hao Huang.

14 recordsLinked to original sources

arXiv2026

Controllable Financial Market Generation with Diffusion Guided Meta Agent

Generative modeling has transformed many fields, such as language and visual modeling, while its application in financial markets remains under-explored. As the minimal unit within a financial market is an order, order-flow modeling represents a fundamental generative financial task. However, current approaches often yield unsatisfactory fidelity in generating order flow, and their generation lacks controllability, thereby limiting their practical applications. In this paper, we formulate the challenge of controllable financial market generation, and propose a Diffusion Guided Meta Agent (DigMA) model to address it. Specifically, we employ a conditional diffusion model to capture the dynamics of the market state represented by time-evolving distribution parameters of the mid-price return rate and the order arrival rate, and we define a meta agent with financial economic priors to generate orders from the corresponding distributions. Extensive experimental results show that DigMA achieves superior controllability and generation fidelity. Moreover, we validate its effectiveness as a generative environment for downstream high-frequency trading tasks and its computational efficiency.

cs.CE↗

arXiv2025

MIRA: Medical Time Series Foundation Model for Real-World Health Data

A unified foundation model for medical time series -- pretrained on open access and ethics board-approved medical corpora -- offers the potential to reduce annotation burdens, minimize model customization, and enable robust transfer across clinical institutions, modalities, and tasks, particularly in data-scarce or privacy-constrained environments. However, existing generalist time series foundation models struggle to handle medical time series data due to their inherent challenges, including irregular intervals, heterogeneous sampling rates, and frequent missing values. To address these challenges, we introduce MIRA, a unified foundation model specifically designed for medical time series forecasting. MIRA incorporates a Continuous-Time Rotary Positional Encoding that enables fine-grained modeling of variable time intervals, a frequency-specific mixture-of-experts layer that routes computation across latent frequency regimes to further promote temporal specialization, and a Continuous Dynamics Extrapolation Block based on Neural ODE that models the continuous trajectory of latent states, enabling accurate forecasting at arbitrary target timestamps. Pretrained on a large-scale and diverse medical corpus comprising over 454 billion time points collect from publicly available datasets, MIRA achieves reductions in forecasting errors by an average of 10% and 7% in out-of-distribution and in-distribution scenarios, respectively, when compared to other zero-shot and fine-tuned baselines. We also introduce a comprehensive benchmark spanning multiple downstream clinical tasks, establishing a foundation for future research in medical time series modeling.

cs.LG↗

arXiv2025

BRIDGE: Bootstrapping Text to Control Time-Series Generation via Multi-Agent Iterative Optimization and Diffusion Modeling

Time-series Generation (TSG) is a prominent research area with broad applications in simulations, data augmentation, and counterfactual analysis. While existing methods have shown promise in unconditional single-domain TSG, real-world applications demand for cross-domain approaches capable of controlled generation tailored to domain-specific constraints and instance-level requirements. In this paper, we argue that text can provide semantic insights, domain information and instance-specific temporal patterns, to guide and improve TSG. We introduce ``Text-Controlled TSG'', a task focused on generating realistic time series by incorporating textual descriptions. To address data scarcity in this setting, we propose a novel LLM-based Multi-Agent framework that synthesizes diverse, realistic text-to-TS datasets. Furthermore, we introduce BRIDGE, a hybrid text-controlled TSG framework that integrates semantic prototypes with text description for supporting domain-level guidance. This approach achieves state-of-the-art generation fidelity on 11 of 12 datasets, and improves controllability by up to 12% on MSE and 6% MAE compared to no text input generation, highlighting its potential for generating tailored time-series data.

cs.LG↗

arXiv2025

TimeDP: Learning to Generate Multi-Domain Time Series with Domain Prompts

Time series generation models are crucial for applications like data augmentation and privacy preservation. Most existing time series generation models are typically designed to generate data from one specified domain. While leveraging data from other domain for better generalization is proved to work in other application areas, this approach remains challenging for time series modeling due to the large divergence in patterns among different real world time series categories. In this paper, we propose a multi-domain time series diffusion model with domain prompts, named TimeDP. In TimeDP, we utilize a time series semantic prototype module which defines time series prototypes to represent time series basis, each prototype vector serving as "word" representing some elementary time series feature. A prototype assignment module is applied to extract the extract domain specific prototype weights, for learning domain prompts as generation condition. During sampling, we extract "domain prompt" with few-shot samples from the target domain and use the domain prompts as condition to generate time series samples. Experiments demonstrate that our method outperforms baselines to provide the state-of-the-art in-domain generation quality and strong unseen domain generation capability.

cs.LG↗

arXiv2024

InvDiff: Invariant Guidance for Bias Mitigation in Diffusion Models

As one of the most successful generative models, diffusion models have demonstrated remarkable efficacy in synthesizing high-quality images. These models learn the underlying high-dimensional data distribution in an unsupervised manner. Despite their success, diffusion models are highly data-driven and prone to inheriting the imbalances and biases present in real-world data. Some studies have attempted to address these issues by designing text prompts for known biases or using bias labels to construct unbiased data. While these methods have shown improved results, real-world scenarios often contain various unknown biases, and obtaining bias labels is particularly challenging. In this paper, we emphasize the necessity of mitigating bias in pre-trained diffusion models without relying on auxiliary bias annotations. To tackle this problem, we propose a framework, InvDiff, which aims to learn invariant semantic information for diffusion guidance. Specifically, we propose identifying underlying biases in the training data and designing a novel debiasing training objective. Then, we employ a lightweight trainable module that automatically preserves invariant semantic information and uses it to guide the diffusion model's sampling process toward unbiased outcomes simultaneously. Notably, we only need to learn a small number of parameters in the lightweight learnable module without altering the pre-trained diffusion model. Furthermore, we provide a theoretical guarantee that the implementation of InvDiff is equivalent to reducing the error upper bound of generalization. Extensive experimental results on three publicly available benchmarks demonstrate that InvDiff effectively reduces biases while maintaining the quality of image generation. Our code is available at https://github.com/Hundredl/InvDiff.

cs.CV↗

arXiv2024

NumLLM: Numeric-Sensitive Large Language Model for Chinese Finance

Recently, many works have proposed various financial large language models (FinLLMs) by pre-training from scratch or fine-tuning open-sourced LLMs on financial corpora. However, existing FinLLMs exhibit unsatisfactory performance in understanding financial text when numeric variables are involved in questions. In this paper, we propose a novel LLM, called numeric-sensitive large language model (NumLLM), for Chinese finance. We first construct a financial corpus from financial textbooks which is essential for improving numeric capability of LLMs during fine-tuning. After that, we train two individual low-rank adaptation (LoRA) modules by fine-tuning on our constructed financial corpus. One module is for adapting general-purpose LLMs to financial domain, and the other module is for enhancing the ability of NumLLM to understand financial text with numeric variables. Lastly, we merge the two LoRA modules into the foundation model to obtain NumLLM for inference. Experiments on financial question-answering benchmark show that NumLLM can boost the performance of the foundation model and can achieve the best overall performance compared to all baselines, on both numeric and non-numeric questions.

cs.CE↗

arXiv2023

Tailoring Interlayer Chiral Exchange by Azimuthal Symmetry Engineering

Recent theoretical and experimental studies of the interlayer Dzyaloshinskii-Moriya interaction (DMI) has sparked great interest in its implementation into practical magnetic random-access memory (MRAM) devices, due to its capability to mediate long-range chiral spin textures. So far, experimental reports focused on the observation of interlayer DMI, leaving the development of strategies to control interlayer DMI's magnitude unaddressed. Here, we introduce an azimuthal symmetry engineering protocol capable of additive/subtractive tuning of interlayer DMI through the control of wedge deposition of separate layers, and demonstrate its capability to mediate field-free spin-orbit torque (SOT) magnetization switching in both orthogonally magnetized and synthetic antiferromagnetically coupled systems. Furthermore, we showcase the spatial inhomogeneity brought about by wedge depositon can be suppressed by specific azimuthal engineering design, ideal for practical implementation. Our findings provide guidelines for effective manipulations of interlayer DMI strength, beneficial for future design of SOT-MRAM or other spintronic devices utilizing interlayer DMI.

physics.app-ph↗

arXiv2023

Field-Free Switching in Symmetry Breaking Multilayers: The Critical Role of Interlayer Chiral Exchange

It is crucial to realize field-free, deterministic, current-induced switching in spin-orbit torque magnetic random-access memory (SOT-MRAM) with perpendicular magnetic anisotropy (PMA). A tentative solution has emerged recently, which employs the interlayer chiral exchange coupling or the interlayer Dzyaloshinskii-Moriya interaction (i-DMI) to achieve symmetry breaking. We hereby investigate the interlayer DMI in a Pt/Co multilayer system with orthogonally magnetized layers, using repeatedly stacked [Pt/Co]n structure with PMA, and a thick Co layer with in-plane magnetic anisotropy (IMA). We clarify the origin and the direction of such symmetry breaking with relation to the i-DMI effective field, and show a decreasing trend of the said effective field magnitude to the stacking number (n). By comparing the current-induced field-free switching behavior for both PMA and IMA layers, we confirm the dominating role of i-DMI in such field-free switching, excluding other possible mechanisms such as tilted-anisotropy and unconventional spin currents that may have arisen from the symmetry breaking.

cond-mat.mtrl-sci↗

arXiv2023

Automatic Emergency Dust-Free solution on-board International Space Station with Bi-GRU (AED-ISS)

With a rising attention for the issue of PM2.5 or PM0.3, particulate matters have become not only a potential threat to both the environment and human, but also a harming existence to instruments onboard International Space Station (ISS). Our team is aiming to relate various concentration of particulate matters to magnetic fields, humidity, acceleration, temperature, pressure and CO2 concentration. Our goal is to establish an early warning system (EWS), which is able to forecast the levels of particulate matters and provides ample reaction time for astronauts to protect their instruments in some experiments or increase the accuracy of the measurements; In addition, the constructed model can be further developed into a prototype of a remote-sensing smoke alarm for applications related to fires. In this article, we will implement the Bi-GRU (Bidirectional Gated Recurrent Unit) algorithms that collect data for past 90 minutes and predict the levels of particulates which over 2.5 micrometer per 0.1 liter for the next 1 minute, which is classified as an early warning

stat.AP↗

arXiv2022

Growth-dependent Interlayer Chiral Exchange and Field-free Switching

Interfacial Dzyaloshinskii-Moriya interaction (DMI) has long been observed in normal metal/ferromagnetic multilayers, enabling the formation of chiral domain walls, skyrmions and other 2D antisymmetric spin textures confined within a single ferromagnetic layer, while more recent works on interlayer DMI reveal new pathways in realizing novel chiral 3D spin textures between two separate layers.Here, we report on interlayer DMI between two orthogonally magnetized ferromagnetic layers (CoFeB/Co) mediated by a Pt layer, and confirm the chiral nature of the observed effective field of up to 37 Oe through asymmetric hysteresis loops under in-plane field.We highlight the importance of growth-induced in-plane symmetry breaking, resulting in a sizable interlayer DMI and a universal characteristic vector through wedge deposition of the samples.We further perform deterministic current-driven magnetization switching in the perpendicularly magnetized Co layer utilizing solely the effective field from the interlayer DMI.These results demonstrate the potential of interlayer DMI in facilitating deterministic field-free switching in spin memory applications.

cond-mat.mtrl-sci↗

arXiv2021

Bridging Unsupervised and Supervised Depth from Focus via All-in-Focus Supervision

Depth estimation is a long-lasting yet important task in computer vision. Most of the previous works try to estimate depth from input images and assume images are all-in-focus (AiF), which is less common in real-world applications. On the other hand, a few works take defocus blur into account and consider it as another cue for depth estimation. In this paper, we propose a method to estimate not only a depth map but an AiF image from a set of images with different focus positions (known as a focal stack). We design a shared architecture to exploit the relationship between depth and AiF estimation. As a result, the proposed method can be trained either supervisedly with ground truth depth, or \emph{unsupervisedly} with AiF images as supervisory signals. We show in various experiments that our method outperforms the state-of-the-art methods both quantitatively and qualitatively, and also has higher efficiency in inference time.

cs.CV↗

arXiv2021

Anatomy of Type-X Spin-Orbit Torque Switching

Using type-x spin-orbit torque (SOT) switching scheme, in which the easy axis (EA) of the ferromagnetic (FM) layer and the charge current flow direction are collinear, is possible to realize a lower-power-consumption, higher-density, and better-performance SOT magnetoresistive random access memory (SOT-MRAM) as compared to the conventional type-y design. Here, we systematically investigate type-x SOT switching properties by both macrospin and micromagnetic simulations. The out-of-plane external field and anisotropy field dependence of the switching current density ($J_{sw}$) is first examined in the ideal type-x configuration. Next, we study the FM layer canting angle ($ϕ_{EA}$) dependence of $J_{sw}$ through macrospin simulations and experiments, which show a transformation of switching dynamics from type-x to type-y with increasing $ϕ_{EA}$. By further integrating field-like torque (FLT) into the simulated system, we find that a positive FLT can assist type-x SOT switching while a negative one brings about complex dynamics. More crucially, with the existence of a sizable FLT, type-x switching mode results in a lower critical switching current than type-y at current pulse width less than ~ 10 ns, indicating the advantage of employing type-x design for ultrafast switching using materials systems with FLT. Our work provides a thorough examination of type-x SOT scheme with various device/materials parameters, which can be informative for designing next-generation SOT-MRAM.

cond-mat.mes-hall↗

arXiv2021

Large Unidirectional Magnetoresistance in Metallic Heterostructures in the Spin Transfer Torque Regime

A large unidirectional magnetoresistance (UMR) ratio of UMR/$R_{xx}\sim$ $0.36\%$ is found in W/CoFeB metallic bilayer heterostructures at room temperature. Three different regimes in terms of the current dependence of UMR ratio are identified: A spin-dependent-scattering mechanism regime at small current densities $J \sim$ $10$$^{9}$A/m$^{2}$ (UMR ratio $\propto$ $J$), a spin-magnon-interaction mechanism regime at intermediate $J \sim$ $10$$^{10}$A/m$^{2}$ (UMR ratio $\propto$ $J$$^{3}$), and a spin-transfer torque (STT) regime at $J \sim$ $10$$^{11}$A/m$^{2}$ (UMR ratio independent of $J$). We verify the direct correlation between this large UMR and the transfer of spin angular momentum from the W layer to the CoFeB layer by both field-dependent and current-dependent UMR characterizations. Numerical simulations further confirm that the large STT-UMR stems from the tilting of the magnetization affected by the spin Hall effect-induced spin-transfer torques. An alternative approach to estimate damping-like spin-torque efficiencies from magnetic heterostructures is also proposed.

cond-mat.mes-hall↗

arXiv2021

CLCC: Contrastive Learning for Color Constancy

In this paper, we present CLCC, a novel contrastive learning framework for color constancy. Contrastive learning has been applied for learning high-quality visual representations for image classification. One key aspect to yield useful representations for image classification is to design illuminant invariant augmentations. However, the illuminant invariant assumption conflicts with the nature of the color constancy task, which aims to estimate the illuminant given a raw image. Therefore, we construct effective contrastive pairs for learning better illuminant-dependent features via a novel raw-domain color augmentation. On the NUS-8 dataset, our method provides $17.5\%$ relative improvements over a strong baseline, reaching state-of-the-art performance without increasing model complexity. Furthermore, our method achieves competitive performance on the Gehler dataset with $3\times$ fewer parameters compared to top-ranking deep learning methods. More importantly, we show that our model is more robust to different scenes under close proximity of illuminants, significantly reducing $28.7\%$ worst-case error in data-sparse regions.

cs.CV↗