arXiv subjects

Min Chen

Publications and source records attributed to Min Chen.

At least 73 records · Page 4Linked to original sources

arXiv2025

Background Invariance Testing According to Semantic Proximity

In many applications, machine-learned (ML) models are required to hold some invariance qualities, such as rotation, size, and intensity invariance. Among these, testing for background invariance presents a significant challenge due to the vast and complex data space it encompasses. To evaluate invariance qualities, we first use a visualization-based testing framework which allows human analysts to assess and make informed decisions about the invariance properties of ML models. We show that such informative testing framework is preferred as ML models with the same global statistics (e.g., accuracy scores) can behave differently and have different visualized testing patterns. However, such human analysts might not lead to consistent decisions without a systematic sampling approach to select representative testing suites. In this work, we present a technical solution for selecting background scenes according to their semantic proximity to a target image that contains a foreground object being tested. We construct an ontology for storing knowledge about relationships among different objects using association analysis. This ontology enables an efficient and meaningful search for background scenes of different semantic distances to a target image, enabling the selection of a test suite that is both diverse and reasonable. Compared with other testing techniques, e.g., random sampling, nearest neighbors, or other sampled test suites by visual-language models (VLMs), our method achieved a superior balance between diversity and consistency of human annotations, thereby enhancing the reliability and comprehensiveness of background invariance testing.

cs.CV↗

arXiv2025

Every Activation Boosted: Scaling General Reasoner to 1 Trillion Open Language Foundation

We introduce Ling 2.0, a series reasoning-oriented language foundation built upon the principle that every activation boosts reasoning capability. Designed to scale from tens of billions to one trillion parameters under a unified Mixture-of-Experts (MoE) paradigm, Ling 2.0 emphasizes high sparsity, cross-scale consistency, and efficiency guided by empirical scaling laws. The series includes three non-thinking (instruct) models - Ling-mini-2.0, Ling-flash-2.0, and Ling-1T - ranging from 16B to 1T total parameters and achieving up to 7-fold active-compute efficiency compared with dense counterparts. Ling 2.0 integrates coordinated innovations across model architecture, pre-training, post-training, and infrastructure: a high-sparsity MoE with MTP for efficient reasoning, reasoning-oriented data and mid-training CoT activation, reinforcement-based fine-tuning (DFT, Evo-CoT), and full-scale FP8 training with fine-grained heterogeneous pipelines. At the trillion scale, Ling-1T establishes a new Pareto frontier of reasoning accuracy versus computational efficiency, demonstrating that sparse activation, when properly aligned with reasoning objectives, enables scalable and efficient intelligence. Collectively, Ling 2.0 provides a coherent, open, and efficient foundation for advancing future reasoning and thinking models, including the Ring series built upon the same base.

cs.CL↗

arXiv2025

Gigagauss magnetic fields generated via theta-pinching driven by multiple petawatt-class lasers

Extremely high axial magnetic fields above the gigagauss (GG) level are supposed to exist in neutron stars, which may be a one of the critical parameters for their internal structures and be responsible for the X and gamma-ray emission from these stars. Here we show that such ultrahigh magnetic fields can be produced by multiple petawatt-class lasers interacting with a cuboid solid target with a cylindrical microtube in the middle. It is found that the obliquely incident intense lasers at the target surfaces enable the produced hot electrons to form an azimuthal current and subsequently induce a seed magnetic field along the cylindrical axis inside the microtube as the hot electrons transport into it. This current-field configuration is similar to a theta-pinch device. When the hot electrons and energetic ions produced via target normal sheath acceleration converge towards the microtube axis, the seed magnetic field is dramatically amplified. This process continues until the magnetic pressure near the axis becomes comparable to the thermal pressure contributed both by hot electrons and energetic ions. Later on, as the plasma in the center start to be expelled outward by the magnetic pressure, an electron current ring with extremely high densities is formed, leading to a further boost of the magnetic fields to well above the GG-level. A scaling of the magnetic field strength with laser intensities, pulse durations, incident angles, and target sizes is presented and verified by numerical simulations, which demonstrates the robustness of our scheme. Our scheme is well suited for experimental realization on 100 terawatt-class to petawatt-class femtosecond or picosecond laser facilities with multiple linearly polarized laser beams.

physics.plasm-ph↗

arXiv2025

GradEscape: A Gradient-Based Evader Against AI-Generated Text Detectors

In this paper, we introduce GradEscape, the first gradient-based evader designed to attack AI-generated text (AIGT) detectors. GradEscape overcomes the undifferentiable computation problem, caused by the discrete nature of text, by introducing a novel approach to construct weighted embeddings for the detector input. It then updates the evader model parameters using feedback from victim detectors, achieving high attack success with minimal text modification. To address the issue of tokenizer mismatch between the evader and the detector, we introduce a warm-started evader method, enabling GradEscape to adapt to detectors across any language model architecture. Moreover, we employ novel tokenizer inference and model extraction techniques, facilitating effective evasion even in query-only access. We evaluate GradEscape on four datasets and three widely-used language models, benchmarking it against four state-of-the-art AIGT evaders. Experimental results demonstrate that GradEscape outperforms existing evaders in various scenarios, including with an 11B paraphrase model, while utilizing only 139M parameters. We have successfully applied GradEscape to two real-world commercial AIGT detectors. Our analysis reveals that the primary vulnerability stems from disparity in text expression styles within the training data. We also propose a potential defense strategy to mitigate the threat of AIGT evaders. We open-source our GradEscape for developing more robust AIGT detectors.

cs.CR↗

arXiv2025

Coherently Enhanced Axion-Photon Conversion via Seeded Photons for Short-Pulse Axion Detection

We propose a seeded axion-photon conversion scheme to enhance the sensitivity of light-shining-through-a-wall (LSW) experiments for axion detection, where the axions are generated from short pulse lasers and the usual resonant cavity is not applicable. By injecting a weak, coherent seed electromagnetic (EM) field into the axion-photon conversion region, the axion-induced EM field can constructively interfere with the seed field, amplifying the number of regenerated photons to a level exceeding that of the unseeded scenario. We evaluate the expected signal enhancement, statistical limits from Poisson counting with seed fluctuations and background, and the potential improvement in coupling sensitivity. Compared to a standard LSW setup, the seeded scheme can achieve orders-of-magnitude higher photon yield per axion, potentially surpassing resonance-enhanced experiments in certain parameter regimes. This approach presents a promising pathway to extend the reach of laboratory axion searches, particularly in scenarios where the resonant cavities are impractical.

hep-ph↗

arXiv2025

An Analytic Theory of Quantum Imaginary Time Evolution

Quantum imaginary time evolution (QITE) algorithm is one of the most promising variational quantum algorithms (VQAs), bridging the current era of Noisy Intermediate-Scale Quantum devices and the future of fully fault-tolerant quantum computing. Although practical demonstrations of QITE and its potential advantages over the general VQA trained with vanilla gradient descent (GD) in certain tasks have been reported, a first-principle, theoretical understanding of QITE remains limited. Here, we aim to develop an analytic theory for the dynamics of QITE. First, we show that QITE can be interpreted as a form of a general VQA trained with Quantum Natural Gradient Descent (QNGD), where the inverse quantum Fisher information matrix serves as the learning-rate tensor. This equivalence is established not only at the level of gradient update rules, but also through the action principle: the variational principle can be directly connected to the geometric geodesic distance in the quantum Fisher information metric, up to an integration constant. Second, for wide quantum neural networks, we employ the quantum neural tangent kernel framework to construct an analytic model for QITE. We prove that QITE always converges faster than GD-based VQA, though this advantage is suppressed by the exponential growth of Hilbert space dimension. This helps explain certain experimental results in quantum computational chemistry. Our theory encompasses linear, quadratic, and more general loss functions. We validate the analytic results through numerical simulations. Our findings establish a theoretical foundation for QITE dynamics and provide analytic insights for the first-principle design of variational quantum algorithms.

quant-ph↗

arXiv2025

Towards Symmetry-Aware Efficient Simulation of Quantum Systems and Beyond

The efficient simulation of complex quantum systems remains a central challenge due to the exponential growth of Hilbert space with system size. Tensor network methods have long been established as powerful approximation schemes, and their efficiency can be further enhanced by incorporating physics-informed priors. A prominent example is symmetry: recent progress on $U(1)$-symmetric tensor networks, accelerated on GPUs and scaled to supercomputers, shows how conserved charges induce block-sparse structures that reduce computational cost and enable larger simulations. The same principle extends to general symmetries, inspiring equivariant neural networks in machine learning and guiding symmetry-preserving ansatze in variational quantum algorithms. Beyond symmetry, physics-informed design also includes strategies such as hybrid tensor networks and parallel sequential circuits, which pursue efficiency from complementary principles. This Perspective argues that physics-informed tensor networks, grounded in both symmetry and beyond-symmetry insights, provide unifying strategies for scalable approaches in quantum simulation, computation, and machine learning.

physics.comp-ph↗

arXiv2025

Catapult Dynamics and Phase Transitions in Quadratic Nets

Neural networks trained with gradient descent can undergo non-trivial phase transitions as a function of the learning rate. In \cite{lewkowycz2020large} it was discovered that wide neural nets can exhibit a catapult phase for super-critical learning rates, where the training loss grows exponentially quickly at early times before rapidly decreasing to a small value. During this phase the top eigenvalue of the neural tangent kernel (NTK) also undergoes significant evolution. In this work, we will prove that the catapult phase exists in a large class of models, including quadratic models and two-layer, homogenous neural nets. To do this, we show that for a certain range of learning rates the weight norm decreases whenever the loss becomes large. We also empirically study learning rates beyond this theoretically derived range and show that the activation map of ReLU nets trained with super-critical learning rates becomes increasingly sparse as we increase the learning rate.

cs.LG↗

arXiv2025

Towards Non-Invasive Sediment Monitoring Using Muography: A Pilot Run at the Shanghai Outer Ring Tunnel

This study demonstrates the application of cosmic-ray muography as a non-invasive method for monitoring sediment accumulation and tidal influences in the Shanghai Outer Ring Tunnel, an immersed tube tunnel located beneath the Huangpu River in Shanghai, China. A portable, dual-layer plastic scintillator detector was deployed to conduct muon flux scans along the tunnel's length and to continuously monitor muon flux, allowing for the study of tidal effects. Geant4 simulations validated the correlation between muon attenuation and overburden thickness, incorporating sediment, water, and concrete layers. Key findings include a strong anti-correlation between the measured muon flux and the water levels observed at a nearby tide gauge. The results align with geotechnical data and simulations, especially in the region of interest, confirming muography's sensitivity to sediment dynamics. This work establishes muography as a robust tool for long-term, real-time monitoring of submerged infrastructure, offering significant advantages over conventional invasive techniques. The study underscores the potential for integrating muography into civil engineering practices to enhance safety and operational resilience in tidal environments.

physics.app-ph↗

arXiv2025

PointDreamer: Zero-shot 3D Textured Mesh Reconstruction from Colored Point Cloud

Faithfully reconstructing textured meshes is crucial for many applications. Compared to text or image modalities, leveraging 3D colored point clouds as input (colored-PC-to-mesh) offers inherent advantages in comprehensively and precisely replicating the target object's 360° characteristics. While most existing colored-PC-to-mesh methods suffer from blurry textures or require hard-to-acquire 3D training data, we propose PointDreamer, a novel framework that harnesses 2D diffusion prior for superior texture quality. Crucially, unlike prior 2D-diffusion-for-3D works driven by text or image inputs, PointDreamer successfully adapts 2D diffusion models to 3D point cloud data by a novel project-inpaint-unproject pipeline. Specifically, it first projects the point cloud into sparse 2D images and then performs diffusion-based inpainting. After that, diverging from most existing 3D reconstruction or generation approaches that predict texture in 3D/UV space thus often yielding blurry texture, PointDreamer achieves high-quality texture by directly unprojecting the inpainted 2D images to the 3D mesh. Furthermore, we identify for the first time a typical kind of unprojection artifact appearing in occlusion borders, which is common in other multiview-image-to-3D pipelines but less-explored. To address this, we propose a novel solution named the Non-Border-First (NBF) unprojection strategy. Extensive qualitative and quantitative experiments on various synthetic and real-scanned datasets demonstrate that PointDreamer, though zero-shot, exhibits SoTA performance (30% improvement on LPIPS score from 0.118 to 0.068), and is robust to noisy, sparse, or even incomplete input data. Code at: https://github.com/YuQiao0303/PointDreamer.

cs.CV↗

arXiv2025

Fancy123: One Image to High-Quality 3D Mesh Generation via Plug-and-Play Deformation

Generating 3D meshes from a single image is an important but ill-posed task. Existing methods mainly adopt 2D multiview diffusion models to generate intermediate multiview images, and use the Large Reconstruction Model (LRM) to create the final meshes. However, the multiview images exhibit local inconsistencies, and the meshes often lack fidelity to the input image or look blurry. We propose Fancy123, featuring two enhancement modules and an unprojection operation to address the above three issues, respectively. The appearance enhancement module deforms the 2D multiview images to realign misaligned pixels for better multiview consistency. The fidelity enhancement module deforms the 3D mesh to match the input image. The unprojection of the input image and deformed multiview images onto LRM's generated mesh ensures high clarity, discarding LRM's predicted blurry-looking mesh colors. Extensive qualitative and quantitative experiments verify Fancy123's SoTA performance with significant improvement. Also, the two enhancement modules are plug-and-play and work at inference time, allowing seamless integration into various existing single-image-to-3D methods. Code at: https://github.com/YuQiao0303/Fancy123

cs.CV↗

arXiv2025

AutoGeTS: Knowledge-based Automated Generation of Text Synthetics for Improving Text Classification

When developing text classification models for real world applications, one major challenge is the difficulty to collect sufficient data for all text classes. In this work, we address this challenge by utilizing large language models (LLMs) to generate synthetic data and using such data to improve the performance of the models without waiting for more real data to be collected and labelled. As an LLM generates different synthetic data in response to different input examples, we formulate an automated workflow, which searches for input examples that lead to more ``effective'' synthetic data for improving the model concerned. We study three search strategies with an extensive set of experiments, and use experiment results to inform an ensemble algorithm that selects a search strategy according to the characteristics of a class. Our further experiments demonstrate that this ensemble approach is more effective than each individual strategy in our automated workflow for improving classification models using LLMs.

cs.CL↗

arXiv2025

Giant plateau-like topological Hall effect controlled by tailoring the magnetic exchange stiffness in a kagome magnet

The ferrimagnet TbMn6Sn6 has attracted vast attention, because its pristine Mn kagome lattice with strong spin-orbit coupling and out-of-plane Tb-Mn exchange supports quantum-limit Chern topological magnetism which can be described by the simple spinless Haldane model. We unveil herein that engineering the kagome lattice through partial substitution of Mn with nonmagnetic Cr induces a striking structural reorganization-Cr preferentially concentrates within a single Mn layer per unit cell, reducing the crystal symmetry from the D6h point group to the C2. This tailored structure configuration gives rise to a plateau-like topological Hall effect (THE), achieving a record-breaking resistivity of 19.1 ohm cm among bulk systems. Complementary magnetic force microscopy measurements unveil a magnetic domain transition near 1 T at 180 K, aligning with the field-dependent phase diagram of the THE. Our direct visualization of the magnetic domain structure underscores the critical role of broken kagome lattice symmetry in generating distinct exchange stiffness between the two Mn layers. These findings establish a new paradigm for exploring exotic states in kagome topological magnets and provide a proof-of-principle strategy for unraveling the interplay between magnetism and emergent topological properties in kagome systems.

cond-mat.str-el↗

arXiv2025

Met$^2$Net: A Decoupled Two-Stage Spatio-Temporal Forecasting Model for Complex Meteorological Systems

The increasing frequency of extreme weather events due to global climate change urges accurate weather prediction. Recently, great advances have been made by the \textbf{end-to-end methods}, thanks to deep learning techniques, but they face limitations of \textit{representation inconsistency} in multivariable integration and struggle to effectively capture the dependency between variables, which is required in complex weather systems. Treating different variables as distinct modalities and applying a \textbf{two-stage training approach} from multimodal models can partially alleviate this issue, but due to the inconformity in training tasks between the two stages, the results are often suboptimal. To address these challenges, we propose an implicit two-stage training method, configuring separate encoders and decoders for each variable. In detailed, in the first stage, the Translator is frozen while the Encoders and Decoders learn a shared latent space, in the second stage, the Encoders and Decoders are frozen, and the Translator captures inter-variable interactions for prediction. Besides, by introducing a self-attention mechanism for multivariable fusion in the latent space, the performance achieves further improvements. Empirically, extensive experiments show the state-of-the-art performance of our method. Specifically, it reduces the MSE for near-surface air temperature and relative humidity predictions by 28.82\% and 23.39\%, respectively. The source code is available at https://github.com/ShremG/Met2Net.

cs.LG↗

arXiv2025

Data Virtualization for Machine Learning

Nowadays, machine learning (ML) teams have multiple concurrent ML workflows for different applications. Each workflow typically involves many experiments, iterations, and collaborative activities and commonly takes months and sometimes years from initial data wrangling to model deployment. Organizationally, there is a large amount of intermediate data to be stored, processed, and maintained. \emph{Data virtualization} becomes a critical technology in an infrastructure to serve ML workflows. In this paper, we present the design and implementation of a data virtualization service, focusing on its service architecture and service operations. The infrastructure currently supports six ML applications, each with more than one ML workflow. The data virtualization service allows the number of applications and workflows to grow in the coming years.

cs.SE↗

arXiv2025

Variable Selection for Stratified Sampling Designs in Semiparametric Accelerated Failure Time Models with Clustered Failure Times

In large-scale epidemiological studies, statistical inference is often complicated by high-dimensional covariates under stratified sampling designs for failure times. Variable selection methods developed for full cohort data do not extend naturally to stratified sampling designs, and appropriate adjustments for the sampling scheme are necessary. Further challenges arise when the failure times are clustered and exhibit within-cluster dependence. As an alternative of Cox proportional hazards (PH) model when the PH assumption is not valid, the penalized Buckley-James (BJ) estimating method for accelerated failure time (AFT) models can potentially handle within-cluster correlation in such setting by incorporating generalized estimating equation (GEE) techniques, though its practical implementation remains hindered by computational instability. We propose a regularized estimating method within the GEE framework for stratified sampling designs, in the spirit of the penalized BJ method but with a reliable inference procedure. We establish the consistency and asymptotic normality of the proposed estimators and show that they achieve the oracle property. Extensive simulation studies demonstrate that our method outperforms existing methods that ignore sampling bias or within-cluster dependence. Moreover, the regularization scheme effectively selects relevant variables even with moderate sample sizes. The proposed methodology is illustrated through applications to a dental study.

stat.ME↗

arXiv2025

RealCam-I2V: Real-World Image-to-Video Generation with Interactive Complex Camera Control

Recent advancements in camera-trajectory-guided image-to-video generation offer higher precision and better support for complex camera control compared to text-based approaches. However, they also introduce significant usability challenges, as users often struggle to provide precise camera parameters when working with arbitrary real-world images without knowledge of their depth nor scene scale. To address these real-world application issues, we propose RealCam-I2V, a novel diffusion-based video generation framework that integrates monocular metric depth estimation to establish 3D scene reconstruction in a preprocessing step. During training, the reconstructed 3D scene enables scaling camera parameters from relative to metric scales, ensuring compatibility and scale consistency across diverse real-world images. In inference, RealCam-I2V offers an intuitive interface where users can precisely draw camera trajectories by dragging within the 3D scene. To further enhance precise camera control and scene consistency, we propose scene-constrained noise shaping, which shapes high-level noise and also allows the framework to maintain dynamic and coherent video generation in lower noise stages. RealCam-I2V achieves significant improvements in controllability and video quality on the RealEstate10K and out-of-domain images. We further enables applications like camera-controlled looping video generation and generative frame interpolation. Project page: https://zgctroy.github.io/RealCam-I2V.

cs.CV↗

arXiv2025

From Bias to Behavior: Learning Bull-Bear Market Dynamics with Contrastive Modeling

Financial markets exhibit highly dynamic and complex behaviors shaped by both historical price trajectories and exogenous narratives, such as news, policy interpretations, and social media sentiment. The heterogeneity in these data and the diverse insight of investors introduce biases that complicate the modeling of market dynamics. Unlike prior work, this paper explores the potential of bull and bear regimes in investor-driven market dynamics. Through empirical analysis on real-world financial datasets, we uncover a dynamic relationship between bias variation and behavioral adaptation, which enhances trend prediction under evolving market conditions. To model this mechanism, we propose the Bias to Behavior from Bull-Bear Dynamics model (B4), a unified framework that jointly embeds temporal price sequences and external contextual signals into a shared latent space where opposing bull and bear forces naturally emerge, forming the foundation for bias representation. Within this space, an inertial pairing module pairs temporally adjacent samples to preserve momentum, while the dual competition mechanism contrasts bullish and bearish embeddings to capture behavioral divergence. Together, these components allow B4 to model bias-driven asymmetry, behavioral inertia, and market heterogeneity. Experimental results on real-world financial datasets demonstrate that our model not only achieves superior performance in predicting market trends but also provides interpretable insights into the interplay of biases, investor behaviors, and market dynamics.

cs.LG↗