arXiv subjects

Yiwen Huang

Publications and source records attributed to Yiwen Huang.

At least 19 recordsLinked to original sources

arXiv2026

Dynamic Loss Balancing for Joint SOH and RUL Prediction of Lithium-Ion Batteries via a Rotary SOH-Injected Prior Battery Transformer

The deployment of reliable lithium-ion battery management systems is crucial for accelerating electrification, yet the joint prognosis of State of Health (SOH) and Remaining Useful Life (RUL) remains severely hindered by task heteroscedasticity. Conventional multi-task learning frameworks fail to balance the bounded, low-variance noise of SOH estimation with the unbounded, nonlinearly expanding uncertainty of long-term RUL predictions. Here, we present the Rotary SOH-Injected Prior Battery Transformer (RoSIP-Batt), a unified co-estimation framework that resolves these optimization conflicts. By formulating joint prediction as a Bayesian multi-task objective, RoSIP-Batt introduces a homoscedastic uncertainty weighting mechanism to dynamically scale task-specific gradients based on learned residual noise levels. The architecture leverages decoupled dual classification tokens and a per-dimension gated fusion mechanism, secured by a gradient-detachment operator to prevent high-variance RUL updates from corrupting the stable SOH representation space. To capture electrochemical degradation patterns without relying on absolute cycle steps, Rotary Position Embedding (RoPE) is incorporated into a shared Transformer backbone to model translation-invariant relative temporal profiles. Crucially, the intermediate SOH estimate is directly injected into the RUL regression head as a physical degradation prior. Evaluations across the NASA, MIT-Stanford, and HUST datasets show that RoSIP-Batt significantly outperforms state-of-the-art baselines, reducing SOH estimation error to 1.994% MAE on NASA and restricting RUL prediction error to 62.85 cycles on Stanford. These findings establish RoSIP-Batt as a highly generalizable, computationally efficient solution suitable for real-time embedded BMS deployment.

cs.LG↗

arXiv2026

A Compact Story of Positivity in de Sitter

Recent developments have yielded significant progress towards systematically understanding loop corrections to de Sitter (dS) correlators. In close analogy with physics in Anti-de Sitter (AdS), large logarithms can result from loops that can be interpreted as corrections to the dimensions of operators. In contrast with AdS, these dimensions are not manifestly real. This implies that the theoretical constraints on the associated correlators are less transparent, particularly in the presence of light scalars. In this paper, we revisit these issues by performing and comparing calculations using the spectral representation approach and the Soft de Sitter Effective Theory (SdSET). We review the general arguments that yield positivity constraints on dS correlators from both perspectives. Our particular focus will be on vertex operators for compact scalar fields, since this case introduces novel complications. We will explain how to resolve apparent disagreements between different techniques for calculating the anomalous dimensions for principal series fields coupled to these vertex operators. Along the way, we will offer new proofs of positivity of the anomalous dimensions, and explain why renormalization group flow associated with these anomalous dimensions in SdSET is the same as resumming bubble diagrams in the spectral representation.

hep-th↗

arXiv2026

Model-X Change-Point Detection of Conditional Distribution

The dynamic nature of many real-world systems can lead to temporal outcome model shifts, causing a deterioration in model accuracy and reliability over time. This requires change-point detection on the outcome models to guide model retraining and adjustments. However, inferring the change point of conditional models is more prone to loss of validity or power than classic detection problems for marginal distributions. This is due to both the temporal covariate shift and the complexity of the outcome model. Also, the existing method of conditional change points detection both have many limitations including linear assumption and low dimension prerequisite which sometimes is not suitable for real world application. To address these challenges, we propose a novel Model-X changE-point detectioN of conditional Distribution (MEND) method computationally enhanced with distillation function for simultaneous change-point detection and localization of the conditional outcome model. We extend and combine our model with neural network to accommodate complex nonlinear and high dimensional situation, which is proved to be valid in both simulation and real data. Theoretical validity of the proposed method is justified. Extensive simulation studies and two real-world examples demonstrate the statistical effectiveness and computational scalability of our method as well as its significant improvements over existing methods.

stat.ME↗

arXiv2025

SAT-BO: Verification Rule Learning and Optimization for FraudTransaction Detection

Electronic payment platforms are estimated to process billions oftransactions daily, with the cumulative value of these transactionspotentially reaching into the trillions. Even a minor error within thishigh-volume environment could precipitate substantial financiallosses. To mitigate this risk, manually constructed verification rules,developed by domain experts, are typically employed to identifyand scrutinize transactions in production environments. However,due to the absence of a systematic approach to ensure the robust-ness of these verification rules against vulnerabilities, they remainsusceptible to exploitation.To mitigate this risk, manually constructed verification rules, de-veloped by domain experts, are typically employed to identify andscrutinize transactions in production environments. However, dueto the absence of a systematic approach to ensure the robustness ofthese verification rules against vulnerabilities, they remain suscep-tible to exploitation. To ensure data security, database maintainersusually compose complex verification rules to check whether aquery/update request is valid. However, the rules written by ex-perts are usually imperfect, and malicious requests may bypassthese rules. As a result, the demand for identifying the defects ofthe rules systematically emerges.

cs.CR↗

arXiv2025

Impact of calibration uncertainties on Hubble constant measurements from gravitational-wave sources

Gravitational-wave (GW) detections of electromagnetically bright compact binary coalescences can provide an independent measurement of the Hubble constant $H_0$. In order to obtain a measurement that could help arbitrate the existing tension on $H_0$, one needs to fully understand any source of systematic biases for this approach. In this study, we aim to understand the impact of instrumental calibration errors (CEs) on the measurements of the luminosity distance, $D_L$, and the inferred $H_0$ value. We simulate binary neutron star mergers (BNSs), as detected by a network of Advanced LIGO and Advanced Virgo interferometers at their design sensitivity. We artificially add CEs equal to exceptionally large values experienced in LIGO-Virgo's third observing run (O3). We find that for individual BNSs at a network signal-to-noise ratio of 50, the systematic errors on $D_L$ - and hence $H_0$ - are still smaller than the statistical uncertainties. The biases become more significant when we combine multiple events to obtain a joint posterior on $H_0$. In the rather unrealistic case that the data around each detection is affected by the same CEs corresponding to the worst offender of O3, the true $H_0$ value would be excluded from the 90% credible interval after we combine $\sim$40 sources. If instead, 10% of the sources suffer from severe CEs, the true value of $H_0$ is included in the 90% credible interval even after 100 sources.

gr-qc↗

arXiv2025

The GAN is dead; long live the GAN! A Modern GAN Baseline

There is a widely-spread claim that GANs are difficult to train, and GAN architectures in the literature are littered with empirical tricks. We provide evidence against this claim and build a modern GAN baseline in a more principled manner. First, we derive a well-behaved regularized relativistic GAN loss that addresses issues of mode dropping and non-convergence that were previously tackled via a bag of ad-hoc tricks. We analyze our loss mathematically and prove that it admits local convergence guarantees, unlike most existing relativistic losses. Second, our new loss allows us to discard all ad-hoc tricks and replace outdated backbones used in common GANs with modern architectures. Using StyleGAN2 as an example, we present a roadmap of simplification and modernization that results in a new minimalist baseline -- R3GAN. Despite being simple, our approach surpasses StyleGAN2 on FFHQ, ImageNet, CIFAR, and Stacked MNIST datasets, and compares favorably against state-of-the-art GANs and diffusion models.

cs.LG↗

arXiv2024

Hierarchical Visual Categories Modeling: A Joint Representation Learning and Density Estimation Framework for Out-of-Distribution Detection

Detecting out-of-distribution inputs for visual recognition models has become critical in safe deep learning. This paper proposes a novel hierarchical visual category modeling scheme to separate out-of-distribution data from in-distribution data through joint representation learning and statistical modeling. We learn a mixture of Gaussian models for each in-distribution category. There are many Gaussian mixture models to model different visual categories. With these Gaussian models, we design an in-distribution score function by aggregating multiple Mahalanobis-based metrics. We don't use any auxiliary outlier data as training samples, which may hurt the generalization ability of out-of-distribution detection algorithms. We split the ImageNet-1k dataset into ten folds randomly. We use one fold as the in-distribution dataset and the others as out-of-distribution datasets to evaluate the proposed method. We also conduct experiments on seven popular benchmarks, including CIFAR, iNaturalist, SUN, Places, Textures, ImageNet-O, and OpenImage-O. Extensive experiments indicate that the proposed method outperforms state-of-the-art algorithms clearly. Meanwhile, we find that our visual representation has a competitive performance when compared with features learned by classical methods. These results demonstrate that the proposed method hasn't weakened the discriminative ability of visual recognition models and keeps high efficiency in detecting out-of-distribution samples.

cs.CV↗

arXiv2024

Operator Origin of Anomalous Dimensions in de Sitter Space

The late time limit of the power spectrum for heavy (principal series) fields in de Sitter space yields a series of polynomial terms with complex scaling dimensions. Such scaling behavior is expected to result from an associated operator with a complex dimension. In a free theory, these complex dimensions are known to match the constraints imposed by unitarity on the space of states. Yet, perturbative corrections to the scaling behavior of operators are naively inconsistent with unitary evolution of the quantum fields in dS. This paper demonstrates how to compute one-loop corrections to the scaling dimensions that appear in the two point function from the field theory description in terms of local operators. We first show how to evaluate these anomalous dimensions using Mellin space, which has the feature that it naturally accommodates a scaleless regulator. We then explore the consequences for the Soft de Sitter Effective Theory (SdSET) description that emerges in the long wavelength limit. Carefully matching between the UV and SdSET descriptions requires the introduction of novel non-dynamical "operators" in the effective theory. This is not only necessary to reproduce results extracted from the Källén-Lehmann representation (that use the space of unitary states directly), but it is also required by general arguments that invoke positivity.

hep-th↗

arXiv2024

Covariate Shift Corrected Conditional Randomization Test

Conditional independence tests are crucial across various disciplines in determining the independence of an outcome variable $Y$ from a treatment variable $X$, conditioning on a set of confounders $Z$. The Conditional Randomization Test (CRT) offers a powerful framework for such testing by assuming known distributions of $X \mid Z$; it controls the Type-I error exactly, allowing for the use of flexible, black-box test statistics. In practice, testing for conditional independence often involves using data from a source population to draw conclusions about a target population. This can be challenging due to covariate shift -- differences in the distribution of $X$, $Z$, and surrogate variables, which can affect the conditional distribution of $Y \mid X, Z$ -- rendering traditional CRT approaches invalid. To address this issue, we propose a novel Covariate Shift Corrected Pearson Chi-squared Conditional Randomization (csPCR) test. This test adapts to covariate shifts by integrating importance weights and employing the control variates method to reduce variance in the test statistics and thus enhance power. Theoretically, we establish that the csPCR test controls the Type-I error asymptotically. Empirically, through simulation studies, we demonstrate that our method not only maintains control over Type-I errors but also exhibits superior power, confirming its efficacy and practical utility in real-world scenarios where covariate shifts are prevalent. Finally, we apply our methodology to a real-world dataset to assess the impact of a COVID-19 treatment on the 90-day mortality rate among patients.

stat.ME↗

arXiv2024

A Goldstone Boson Equivalence for Inflation

The effective field theory of single-field inflation characterizes the inflationary epoch in terms of a pattern of symmetry breaking. An operator acquires a time-dependent vacuum expectation value, defining a preferred spatial slicing. In the absence of dynamical gravity, the fluctuations around the time-dependent background are described by the Goldstone boson associated with this symmetry breaking process. With gravity, the Goldstone is eaten by the metric, becoming the scalar metric fluctuation. In this paper, we will show that in general single-field inflation, the statistics of scalar metric fluctuations are given by the statistics of this Goldstone boson decoupled from gravity up to corrections that are controlled as an expansion in slow-roll parameters. This even holds in the presence of additional parameters, like the speed of sound, that naively enhance the impact of the gravitational terms. In the process, we derive expressions for leading and sub-leading gravitational corrections to all-orders in the Goldstone boson.

hep-th↗

arXiv2024

FormalGeo: An Extensible Formalized Framework for Olympiad Geometric Problem Solving

This is the first paper in a series of work we have accomplished over the past three years. In this paper, we have constructed a consistent formal plane geometry system. This will serve as a crucial bridge between IMO-level plane geometry challenges and readable AI automated reasoning. Within this formal framework, we have been able to seamlessly integrate modern AI models with our formal system. AI is now capable of providing deductive reasoning solutions to IMO-level plane geometry problems, just like handling other natural languages, and these proofs are readable, traceable, and verifiable. We propose the geometry formalization theory (GFT) to guide the development of the geometry formal system. Based on the GFT, we have established the FormalGeo, which consists of 88 geometric predicates and 196 theorems. It can represent, validate, and solve IMO-level geometry problems. we also have crafted the FGPS (formal geometry problem solver) in Python. It serves as both an interactive assistant for verifying problem-solving processes and an automated problem solver. We've annotated the formalgeo7k and formalgeo-imo datasets. The former contains 6,981 (expand to 133,818 through data augmentation) geometry problems, while the latter includes 18 (expand to 2,627 and continuously increasing) IMO-level challenging geometry problems. All annotated problems include detailed formal language descriptions and solutions. Implementation of the formal system and experiments validate the correctness and utility of the GFT. The backward depth-first search method only yields a 2.42% problem-solving failure rate, and we can incorporate deep learning techniques to achieve lower one. The source code of FGPS and datasets are available at https://github.com/BitSecret/FGPS.

cs.AI↗

arXiv2023

Quantum Fusion of Independent Networks Based on Multi-user Entanglement Swapping

With the advance development in quantum science, constructing a large-scale quantum network has become a hot area of future quantum information technology. Future quantum networks promise to enable many fantastic applications and will unlock fundamentally new technologies in information security and large-scale computation. The future quantum internet is required to connect quantum information processors to achieve unparalleled capabilities in secret communication and enable quantum communication between any two points on Earth. However, the existing quantum networks are basically constructed to realize the communication between the end users in their own networks. How to bridge different independent networks to form a fully-connected quantum internet becomes a pressing challenge for future networks. Here, we demonstrate the quantum fusion of two independent networks for the first time based on multiuser entanglement swapping, to merge two 10-user networks into a larger network with 18 users in quantum correlation layer. By performing the Bell state measurement between two nonneighboring nodes, the users from different networks can establish entanglement and ultimately every pair of the 18 users are able to communicate with each other using the swapped states. Our approach opens attractive opportunities for the establishment of quantum entanglement between remote nodes in different networks, which facilitates versatile quantum information interconnects and has great application in constructing large-scale intercity quantum communication networks.

quant-ph↗

arXiv2023

Positivity from Cosmological Correlators

Effective field theories in flat space and in anti-de Sitter space are constrained by causality and unitarity, often in the form of positivity bounds. Similar bounds have been harder to demonstrate in cosmological backgrounds, where the roles of unitarity and causality are more obscure. Fortunately, the expansion of the universe ensures that late-time cosmological correlators are effectively classical and the role of unitarity is played by classical statistical inequalities. For multi-field inflation, the resulting positivity constraints have long been known in terms of the Suyama-Yamaguchi inequality. In this paper, we demonstrate that similar statistical bounds imply nontrivial constraints for massive fields in the early universe. We show that any real anomalous dimensions for principal series fields in de Sitter space must be positive. We also derive a limit on the amplitude of oscillatory signals from inflation, including those arising in cosmological collider physics. Finally, we demonstrate that these constraints manifest themselves directly in the two-point statistics of matter and galaxies that will be measured in upcoming surveys.

hep-th↗

arXiv2023

'Tax-free' 3DMM Conditional Face Generation

3DMM conditioned face generation has gained traction due to its well-defined controllability; however, the trade-off is lower sample quality: Previous works such as DiscoFaceGAN and 3D-FM GAN show a significant FID gap compared to the unconditional StyleGAN, suggesting that there is a quality tax to pay for controllability. In this paper, we challenge the assumption that quality and controllability cannot coexist. To pinpoint the previous issues, we mathematically formalize the problem of 3DMM conditioned face generation. Then, we devise simple solutions to the problem under our proposed framework. This results in a new model that effectively removes the quality tax between 3DMM conditioned face GANs and the unconditional StyleGAN.

cs.CV↗

arXiv2023

Inflationary Adler Conditions

We derive a new soft theorem that corresponds to the spontaneous breaking of Lorentz boosts. This is motivated by the dynamics of inflation in the sub-horizon (flat-space) limit, where spacetime becomes flat but Lorentz boosts are still broken. In this limit, the scattering amplitudes become sensible observables. We relate the soft emission of a Goldstone boson to the (non-relativistic) Lorentz boost of the hard scattering amplitudes. This is the on-shell avatar of the spontaneous breaking of Lorentz boosts, analogous to the Adler zero of pions in the chiral symmetry breaking. We comment on several applications to inflation, including the demonstration that Dirac-Born-Infeld Inflation is the unique theory that has an emergent Lorentz invariance when the boosts are spontaneously broken.

hep-th↗

arXiv2022

FERV39k: A Large-Scale Multi-Scene Dataset for Facial Expression Recognition in Videos

Current benchmarks for facial expression recognition (FER) mainly focus on static images, while there are limited datasets for FER in videos. It is still ambiguous to evaluate whether performances of existing methods remain satisfactory in real-world application-oriented scenes. For example, the "Happy" expression with high intensity in Talk-Show is more discriminating than the same expression with low intensity in Official-Event. To fill this gap, we build a large-scale multi-scene dataset, coined as FERV39k. We analyze the important ingredients of constructing such a novel dataset in three aspects: (1) multi-scene hierarchy and expression class, (2) generation of candidate video clips, (3) trusted manual labelling process. Based on these guidelines, we select 4 scenarios subdivided into 22 scenes, annotate 86k samples automatically obtained from 4k videos based on the well-designed workflow, and finally build 38,935 video clips labeled with 7 classic expressions. Experiment benchmarks on four kinds of baseline frameworks were also provided and further analysis on their performance across different scenes and some challenges for future research were given. Besides, we systematically investigate key components of DFER by ablation studies. The baseline framework and our project will be available.

cs.CV↗

arXiv2022

A Flat Space Analogue for the Quantum Origin of Structure

The analytic structure of non-Gaussian correlators in inflationary cosmologies has recently been proposed as a test of the quantum origin of structure in the universe. To further understand this proposal, we explore the analogous equal-time in-in correlators in flat space and show they exhibit the same features as their cosmological counterparts. The quantum vacuum is uniquely identified by in-in correlators with a total energy pole and no additional poles at physical momenta. We tie this behavior directly to the S-matrix and show that poles at physical momenta always arise from scattering of particles present in the initial state. We relate these flat-space in-in correlators to the probability amplitude for exciting multiple Unruh-de Witt detectors. Localizing the detectors in spacetime, through the uncertainty principle, provides the energy and momentum needed to excite the vacuum and explains the connection to cosmological particle production. In addition, the entanglement of these detectors provides a probe of the entangled state of the underlying field and connects the properties of the correlators to the range of entanglement of the detectors.

hep-th↗

arXiv2021

A 15-user quantum secure direct communication network

Quantum secure direct communication (QSDC) based on entanglement can directly transmit confidential information. However, the inability to simultaneously distinguish the four sets of encoded entangled states limits its practical application. Here, we explore a deterministic QSDC network based on time-energy entanglement and sum-frequency generation. 15 users are in a fully connected QSDC network, and the fidelity of the entangled state shared by any two users is greater than 97%. The results show that when any two users are performing QSDC over 40 kilometers of optical fiber, the fidelity of the entangled state shared by them is still greater than 95%, and the rate of information transmission can be maintained above 1Kbp/s. Our Letter demonstrates the feasibility of a proposed QSDC network, and hence lays the foundation for the realization of satellite-based long-distance and global QSDC in the future.

quant-ph↗