arXiv subjects

Shuwei Li

Publications and source records attributed to Shuwei Li.

15 recordsLinked to original sources

arXiv2026

UC-VLM: Consistency-Driven Learning for AI-Generated Image Detection with Vision-Language Large Models

Vision-Language Large Models (VLLMs) are promising for AI-generated image (AIGI) detection because they can produce both a prediction and a natural-language output. However, most existing VLLM-based detectors primarily fine-tune the language side while giving limited attention to low-level visual forensic cues. They also often depend on manually crafted prompts or human-annotated rationales, which limits scalability.We present UC-VLM, a unified multi-stage framework for AIGI detection that relies solely on binary supervision. UC-VLM first identifies effective instruction variants automatically. It then reuses the same binary label within a multi-stage training framework: (i) a visual discrimination objective that strengthens sensitivity to non-semantic forensic cues, and (ii) a label-conditioned generation objective that uses the binary label to supervise textual outputs. This design turns weak binary supervision into a shared supervision signal for both the visual pathway and the language output. Our key novelty is a unified multi-stage binary-supervised framework that consistently reuses the same authenticity labels for visual adaptation and label-conditioned text generation, while leveraging automatically optimized instructions to reduce prompt sensitivity without requiring human-written rationales or hand-crafted prompts.Experiments show that UC-VLM achieves 96.1% average accuracy on GenImage, exceeding the strongest prior result by 4.6%, and obtains 69.6% / 77.9% accuracy on Chameleon under ProGAN / SDV1.4 training, surpassing the best baseline by 11.2% / 15.3%, respectively.

cs.CV↗

arXiv2026

FUSE: Frequency-domain Unification and Spectral Energy Alignment for Multi-modal Object Re-Identification

Despite significant progress in multi-modal Re-Identification (ReID), existing methods tend to emphasize low-frequency cues. Consequently, they focus on attributes such as color, illumination, and coarse appearance, while overlooking mid and high-frequency structures that encode geometric, textural, and identity-discriminative details. This imbalance leads to incomplete spectral representations and unstable cross-modal alignment. To overcome these limitations, we introduce FUSE, a frequency-domain framework that reformulates multi-modal ReID as a two-stage process of spectral disentanglement and energy alignment. The proposed Spectral Decomposition Module (SDM) adaptively partitions features into low, mid, and high-frequency subspaces, enabling hierarchical spectral modeling. The Cross-Modal Alignment Module (CAM) further enforces energy alignment and subspace complementarity across modalities via frequency-consistency regularization. In addition, FUSE incorporates learnable frequency modulation to enhance robustness under varying illumination and heterogeneous sensor conditions. Extensive experiments on RGBNT201, RGBNT100, and MSVR310 show that FUSE achieves 9.1\% mAP and 9.5\% Rank-1 improvements, establishing an interpretable frequency-domain paradigm for multi-modal representation learning.

cs.CV↗

arXiv2026

Melt-Quench Failures and Practical Solutions for Universal Machine-Learning Interatomic Potentials in Amorphous Structure Generation

Generating experimentally relevant amorphous structures via melt-quench molecular dynamics is prohibitively expensive at the first-principles level. Universal machine-learning interatomic potentials (uMLIPs) could accelerate such simulations, but their reliability under non-equilibrium conditions remains unclear. Here, we examine eight leading uMLIPs for generating amorphous IrO2, using this electrocatalytically relevant oxide as a diagnostic case. Under the conventional melt-quench protocol, all models yield unphysically expanded structures with densities of 1-4 g/cm3, far below the ab initio molecular dynamics (AIMD) reference value of 10.04 g/cm3. Comparisons against ab initio references show that accurate energies and forces alone do not ensure stable NPT dynamics; correct energy-volume responses and pressure predictions are also essential. We identify two practical remedies: pressure-targeted fine-tuning and a revised NVT-quench/NPT-equilibration protocol that avoids unphysical volume expansion without additional ab initio training data. Both recover IrO2 densities and local structures consistent with AIMD. Across 30 chemically diverse materials, the volume-expansion failure proves general, and the revised protocol substantially improves density predictions, reducing the AIMD-referenced MAE from 2.46 to 0.35 g/cm3. This work establishes practical validation criteria and simulation strategies for robust uMLIP-driven amorphous structure generation.

cond-mat.mtrl-sci↗

arXiv2026

White-Balance First, Adjust Later: Cross-Camera Color Constancy via Vision-Language Evaluation

Color constancy aims to keep object colors consistent under varying illumination. Cross-camera generalization in color constancy remains challenging because learning-based models often overfit to the color response characteristics of the training camera, resulting in degraded performance on images captured by other cameras. We propose VLM-CC, a feedback-guided framework that formulates color constancy as an iterative refinement process. Instead of directly estimating the illuminant from raw input, VLM-CC performs iterative correction driven by vision-language model (VLM)-based evaluation. At each iteration, the image is white-balanced using the current estimate and converted to pseudo-sRGB. A lightweight LoRA-tuned VLM then assesses the corrected image, identifying the dominant residual color cast and providing qualitative feedback. This feedback is mapped to a residual illumination direction (red, green, or blue) and used to update the illuminant estimate until convergence. Our key idea is to reframe color constancy as an iterative perceptual feedback problem, leveraging VLM evaluation instead of direct RGB regression. By replacing direct RGB estimation with VLM-guided perceptual feedback, VLM-CC achieves state-of-the-art robustness in cross-camera color constancy across multiple datasets. Code will be available at https://github.com/NothingIknow/VLM-CC.

cs.CV↗

arXiv2026

Bridging Day and Night: Target-Class Hallucination Suppression in Unpaired Image Translation

Day-to-night unpaired image translation is important to downstream tasks but remains challenging due to large appearance shifts and the lack of direct pixel-level supervision. Existing methods often introduce semantic hallucinations, where objects from target classes such as traffic signs and vehicles, as well as man-made light effects, are incorrectly synthesized. These hallucinations significantly degrade downstream performance. We propose a novel framework that detects and suppresses hallucinations of target-class features during unpaired translation. To detect hallucination, we design a dual-head discriminator that additionally performs semantic segmentation to identify hallucinated content in background regions. To suppress these hallucinations, we introduce class-specific prototypes, constructed by aggregating features of annotated target-domain objects, which act as semantic anchors for each class. Built upon a Schrodinger Bridge-based translation model, our framework performs iterative refinement, where detected hallucination features are explicitly pushed away from class prototypes in feature space, thus preserving object semantics across the translation trajectory.Experiments show that our method outperforms existing approaches both qualitatively and quantitatively. On the BDD100K dataset, it improves mAP by 15.5% for day-to-night domain adaptation, with a notable 31.7% gain for classes such as traffic lights that are prone to hallucinations.

cs.CV↗

arXiv2026

Aggregating Diverse Cue Experts for AI-Generated Image Detection

The rapid emergence of image synthesis models poses challenges to the generalization of AI-generated image detectors. However, existing methods often rely on model-specific features, leading to overfitting and poor generalization. In this paper, we introduce the Multi-Cue Aggregation Network (MCAN), a novel framework that integrates different yet complementary cues in a unified network. MCAN employs a mixture-of-encoders adapter to dynamically process these cues, enabling more adaptive and robust feature representation. Our cues include the input image itself, which represents the overall content, and high-frequency components that emphasize edge details. Additionally, we introduce a Chromatic Inconsistency (CI) cue, which normalizes intensity values and captures noise information introduced during the image acquisition process in real images, making these noise patterns more distinguishable from those in AI-generated content. Unlike prior methods, MCAN's novelty lies in its unified multi-cue aggregation framework, which integrates spatial, frequency-domain, and chromaticity-based information for enhanced representation learning. These cues are intrinsically more indicative of real images, enhancing cross-model generalization. Extensive experiments on the GenImage, Chameleon, and UniversalFakeDetect benchmark validate the state-of-the-art performance of MCAN. In the GenImage dataset, MCAN outperforms the best state-of-the-art method by up to 7.4% in average ACC across eight different image generators.

cs.CV↗

arXiv2025

Online survival analysis with quantile regression

We propose an online inference method for censored quantile regression with streaming data sets. A key strategy is to approximate the martingale-based unsmooth objective function with a quadratic loss function involving a well-justified second-order expansion. This enables us to derive a new online convex function based on the current data batch and summary statistics of historical data, thereby achieving online updating and occupying low storage space. To estimate the regression parameters, we design a novel majorize-minimize algorithm by reasonably constructing a quadratic surrogate objective function, which renders a closed-form parameter update and thus reduces the computational burden notably. Theoretically, compared to the oracle estimators derived from analyzing the entire raw data once, we posit a weaker assumption on the quantile grid size and show that the proposed online estimators can maintain the same convergence rate and statistical efficiency. Simulation studies and an application demonstrate the satisfactory empirical performance and practical utilities of the proposed online method.

math.ST↗

arXiv2025

Multimodal Modeling of CRISPR-Cas12 Activity Using Foundation Models and Chromatin Accessibility Data

Predicting guide RNA (gRNA) activity is critical for effective CRISPR-Cas12 genome editing but remains challenging due to limited data, variation across protospacer adjacent motifs (PAMs-short sequence requirements for Cas binding), and reliance on large-scale training. We investigate whether pre-trained biological foundation model originally trained on transcriptomic data can improve gRNA activity estimation even without domain-specific pre-training. Using embeddings from existing RNA foundation model as input to lightweight regressor, we show substantial gains over traditional baselines. We also integrate chromatin accessibility data to capture regulatory context, improving performance further. Our results highlight the effectiveness of pre-trained foundation models and chromatin accessibility data for gRNA activity prediction.

q-bio.GN↗

arXiv2025

Interpretable Deep Regression Models with Interval-Censored Failure Time Data

Deep neural networks (DNNs) have become powerful tools for modeling complex data structures through sequentially integrating simple functions in each hidden layer. In survival analysis, recent advances of DNNs primarily focus on enhancing model capabilities, especially in exploring nonlinear covariate effects under right censoring. However, deep learning methods for interval-censored data, where the unobservable failure time is only known to lie in an interval, remain underexplored and limited to specific data type or model. This work proposes a general regression framework for interval-censored data with a broad class of partially linear transformation models, where key covariate effects are modeled parametrically while nonlinear effects of nuisance multi-modal covariates are approximated via DNNs, balancing interpretability and flexibility. We employ sieve maximum likelihood estimation by leveraging monotone splines to approximate the cumulative baseline hazard function. To ensure reliable and tractable estimation, we develop an EM algorithm incorporating stochastic gradient descent. We establish the asymptotic properties of parameter estimators and show that the DNN estimator achieves minimax-optimal convergence. Extensive simulations demonstrate superior estimation and prediction accuracy over state-of-the-art methods. Applying our method to the Alzheimer's Disease Neuroimaging Initiative dataset yields novel insights and improved predictive performance compared to traditional approaches.

stat.ML↗

arXiv2025

InfoSEM: A Deep Generative Model with Informative Priors for Gene Regulatory Network Inference

Inferring Gene Regulatory Networks (GRNs) from gene expression data is crucial for understanding biological processes. While supervised models are reported to achieve high performance for this task, they rely on costly ground truth (GT) labels and risk learning gene-specific biases, such as class imbalances of GT interactions, rather than true regulatory mechanisms. To address these issues, we introduce InfoSEM, an unsupervised generative model that leverages textual gene embeddings as informative priors, improving GRN inference without GT labels. InfoSEM can also integrate GT labels as an additional prior when available, avoiding biases and further enhancing performance. Additionally, we propose a biologically motivated benchmarking framework that better reflects real-world applications such as biomarker discovery and reveals learned biases of existing supervised methods. InfoSEM outperforms existing models by 38.5% across four datasets using textual embeddings prior and further boosts performance by 11.1% when integrating labeled data as priors.

stat.ML↗

arXiv2024

Observation of Co-propagating Chiral Zero Modes in Magnetic Photonic Crystals

Topological singularities, such as Weyl points and Dirac points, can give rise to unidirectional propagation channels known as chiral zero modes (CZMs) when subject to a magnetic field. These CZMs are responsible for intriguing phenomena like the chiral anomaly in quantum systems. The propagation direction of each CZM is determined by both the applied magnetic field and the topological charge of the singularity point. While counter-propagating CZMs have been observed in 2D and 3D systems, the realization of co-propagating CZMs has remained elusive. Here we present the first experimental observation of co-propagating CZMs in magnetic photonic crystals hosting a single pair of ideal Weyl points WPs. By manipulating the crystal's structural configuration, we spatially alter the locations of the WPs, creating pseudo-magnetic fields in opposite directions between them. This arrangement results in a pair of CZMs that possess the same group velocity and co-propagate. Our work opens up new possibilities for topological manipulation of wave propagation and may lead to advancements in optical waveguides, switches, and various other applications.

cond-mat.mes-hall↗

arXiv2023

NFT.mine: An xDeepFM-based Recommender System for Non-fungible Token (NFT) Buyers

Non-fungible token (NFT) is a tradable unit of data stored on the blockchain which can be associated with some digital asset as a certification of ownership. The past several years have witnessed the exponential growth of the NFT market. In 2021, the NFT market reached its peak with more than $40 billion trades. Despite the booming NFT market, most NFT-related studies focus on its technical aspect, such as standards, protocols, and security, while our study aims at developing a pioneering recommender system for NFT buyers. In this paper, we introduce an extreme deep factorization machine (xDeepFM)-based recommender system, NFT.mine, which achieves real-time data collection, data cleaning, feature extraction, training, and inference. We used data from OpenSea, the most influential NFT trading platform, to testify the performance of NFT.mine. As a result, experiments showed that compared to traditional models such as logistic regression, naive Bayes, random forest, etc., NFT.mine outperforms them with higher AUC and lower cross entropy loss and outputs personalized recommendations for NFT buyers.

cs.CR↗

arXiv2023

Realization of a quadrupole topological insulator phase in a gyromagnetic photonic crystal

The field of topological photonics was initiated with the realization of a Chern insulator phase in a gyromagnetic photonic crystal (PhC) with broken time-reversal symmetry (T), hosting chiral edge states that are topologically protected propagating modes. Recent advances in higher-order band topology have discovered another type of topological state, as manifested by those modes localized at the corners of a sample, which are known as corner states. Here we report the realization of a quadrupole higher-order topological insulator phase in a gyromagnetic PhC, induced by a topological phase transition from the previously demonstrated Chern insulator phase. The evolution of the boundary modes from propagating chiral edge states to localized corner states has been characterized by microwave measurements. We also demonstrate topological bound states in the continuum, when the gyromagnetic PhC is magnetically tuned. These results extend the quadrupole topological insulator phase into T-broken systems, and integrate topologically protected propagating and localized modes in the same platform.

physics.optics↗

arXiv2022

MIMT: Multi-Illuminant Color Constancy via Multi-Task Local Surface and Light Color Learning

The assumption of a uniform light color distribution is no longer applicable in scenes that have multiple light colors. Most color constancy methods are designed to deal with a single light color, and thus are erroneous when applied to multiple light colors. The spatial variability in multiple light colors causes the color constancy problem to be more challenging and requires the extraction of local surface/light information. Motivated by this, we introduce a multi-task learning method to discount multiple light colors in a single input image. To have better cues of the local surface/light colors under multiple light color conditions, we design a novel multi-task learning framework. Our framework includes auxiliary tasks of achromatic-pixel detection and surface-color similarity prediction, providing better cues for local light and surface colors, respectively. Moreover, to ensure that our model maintains the constancy of surface colors regardless of the variations of light colors, a novel local surface color feature preservation scheme is developed. We demonstrate that our model achieves 47.1% improvement (from 4.69 mean angular error to 2.48) compared to a state-of-the-art multi-illuminant color constancy method on a multi-illuminant dataset (LSMI).

cs.CV↗

arXiv2017

Observation of Giant Exchange Bias and Topological Hall Effect in Manganese Nitride Films

Magnetic and magneto-transport properties of manganese nitride films grown by molecular beam epitaxy have been investigated. Due to the mixed ferrimagnetic (FI) phase ($ε$-phase with TFI ~ 738 K) and the antiferromagnetic phase ($ζ$-phase with TN ~ 273 K), we observe magnetization hysteresis loops with non-zero exchange bias below TN, reaching ~ 0.22 T at 5 K. This indicates that noncollinear spins exist at the interfaces between two phases, creating a competition between interfacial Dzyaloshinskii-Moriya (DM) and exchange interactions. Strikingly, in addition to the normal Hall effect by Lorentz force and anomalous Hall effect by magnetization, we observe new contribution namely topological Hall effect below 75 K. This verifies the existence of topological spin texture, which is the consequence of competing interactions controlled by both applied field and temperature. Our work demonstrates that spintronic devices may be fabricated exploiting rich magnetic properties of different phases.

cond-mat.mtrl-sci↗