arXiv subjects

Chenyang Jiang

Publications and source records attributed to Chenyang Jiang.

13 recordsLinked to original sources

arXiv2026

SMOPD: Selective Token-Entropy Masking for Dirty-History Multi-Turn On-Policy Self-Distillation

Dirty-history rollouts make multi-turn on-policy self-distillation (OPSD) brittle: once a student emits an erroneous intermediate reply, later turns are conditioned on that reply, and uniform distillation can spend loss on tokens that carry little corrective signal. We introduce SMOPD (Selective Masking for On-Policy Distillation), a loss-only stabilization method for multi-turn OPSD. For each generated middle-turn reply, SMOPD ranks token positions by student entropy and removes the lowest-entropy 20% from the clipped generalized Jensen-Shannon distillation loss; final-answer and FULL-preservation losses are unchanged. This design targets token-level uncertainty rather than coarse trajectory outcomes, adds no parameters, and has zero inference-time overhead. We compare SMOPD with a correctness-scaling variant that multiplies a common detached reliability proxy using final-answer correctness. On LiC with Qwen3 models, SMOPD improves SHARDED-view accuracy by 1.0-2.5 percentage points in single-seed 1.7B, 4B, and 8B comparisons, and a small 4B multi-seed check shows a +1.7pp mean SHARDED gain over baseline (two-tailed p = 0.022). Adding the outcome scalar is harmful without masking at 1.7B (-4.0pp) and remains scale-dependent when combined with masking (+1.3pp at 4B, neutral at 1.7B, and -0.5pp at 8B). These archived aggregate results suggest that token-level uncertainty is a more reliable stabilization signal than scalar final-answer correctness in this evaluated dirty-history OPSD setting, while leaving causal mechanism tests and broader benchmark validation to future work.

cs.LG↗

arXiv2026

Video as Natural Augmentation: Towards Unified AI-Generated Image and Video Detection

AI-generated content (AIGC) is rapidly improving, creating an urgent need for detectors that generalize across data sources, deployment pipelines, and visual modalities. A strongly generalizable detector should remain robust under distributional variations. However, we identify a consistent failure mode: SOTA AI-generated image detectors often collapse when applied to frames extracted from videos. Through systematic analysis, we show that this cross-modal gap arises from both entangled synthesis-agnostic video processing shifts, including color conversion, codec compression, resizing, and blur, and model-specific fingerprints introduced by modern video generators. Motivated by these findings, we propose VINA (Video as Natural Augmentation), a unified AIGC detection framework that jointly trains on image and video data. VINA uses video frames as physically grounded natural augmentations and further introduces a cross-modal supervised contrastive objective to align image and video representations under a shared real/fake decision boundary. Extensive experiments on 14 image, video, and in-the-wild benchmarks show that VINA delivers bidirectional gains, improves robustness and transferability, and achieves state-of-the-art performance across nearly all evaluated settings without complex augmentation or dataset-specific tuning.

cs.CV↗

arXiv2026

Preserving Forgery Artifacts: AI-Generated Video Detection at Native Scale

The rapid advancement of video generation models has enabled the creation of highly realistic synthetic media, raising significant societal concerns regarding the spread of misinformation. However, current detection methods suffer from critical limitations. They rely on preprocessing operations like fixed-resolution resizing and cropping. These operations not only discard subtle, high-frequency forgery traces but also cause spatial distortion and significant information loss. Furthermore, existing methods are often trained and evaluated on outdated datasets that fail to capture the sophistication of modern generative models. To address these challenges, we introduce a comprehensive dataset and a novel detection framework. First, we curate a large-scale dataset of over 140K videos from 15 state-of-the-art open-source and commercial generators, along with Magic Videos benchmark designed specifically for evaluating ultra-realistic synthetic content. In addition, we propose a novel detection framework built on the Qwen2.5-VL Vision Transformer, which operates natively at variable spatial resolutions and temporal durations. This native-scale approach effectively preserves the high-frequency artifacts and spatiotemporal inconsistencies typically lost during conventional preprocessing. Extensive experiments demonstrate that our method achieves superior performance across multiple benchmarks, underscoring the critical importance of native-scale processing and establishing a robust new baseline for AI-generated video detection.

cs.CV↗

arXiv2026

Multimodal Dataset Distillation via Phased Teacher Models

Multimodal dataset distillation aims to construct compact synthetic datasets that enable efficient compression and knowledge transfer from large-scale image-text data. However, existing approaches often fail to capture the complex, dynamically evolving knowledge embedded in the later training stages of teacher models. This limitation leads to degraded student performance and compromises the quality of the distilled data. To address critical challenges such as pronounced cross-stage performance gaps and unstable teacher trajectories, we propose Phased Teacher Model with Shortcut Trajectory (PTM-ST) -- a novel phased distillation framework. PTM-ST leverages stage-aware teacher modeling and a shortcut-based trajectory construction strategy to accurately fit the teacher's learning dynamics across distinct training phases. This enhances both the stability and expressiveness of the distillation process. Through theoretical analysis and comprehensive experiments, we show that PTM-ST significantly mitigates optimization oscillations and inter-phase knowledge gaps, while also reducing storage overhead. Our method consistently surpasses state-of-the-art baselines on Flickr30k and COCO, achieving up to 13.5% absolute improvement and an average gain of 9.53% on Flickr30k. Code: https://github.com/Previsior/PTM-ST.

cs.CV↗

arXiv2026

Development and extension of a monochromatic neutron beamline for neutron polarimetry device characterization at the Spallation Neutron Source

The precise manipulation and analysis of neutron spin states are foundational for a wide range of physics experiments, from fundamental symmetry tests to materials science. To enable systematic characterization of neutron polarimetry devices, we have constructed and extended a monochromatic neutron beamline at the Spallation Neutron Source, Oak Ridge National Laboratory. The beamline delivers monochromatic neutrons and provides a flexible platform for deploying and evaluating advanced neutron spin manipulation instruments. We describe the design and commissioning of the extended beamline and present a proof-of-concept neutron polarimetry study using three devices: a supermirror neutron polarizer, a Mezei spin flipper, and an in situ neutron 3He spin analyzer system. Performance metrics, optimization strategies, and systematic effects are discussed, demonstrating the beamline utility for neutron instrumentation testing. These results establish the extended monochromatic beamline as a useful resource for the development and validation of neutron polarimetry technologies.

physics.ins-det↗

arXiv2025

High-efficiency loading of 2,400 Ytterbium atoms in optical tweezer arrays

Neutral atom arrays have emerged as a powerful platform for quantum computation, simulation, and metrology.Among them, alkaline-earth-like atoms exhibit distinct advantages, including long coherence time, high-fidelity Rydberg gates, and erasure correction for efficient quantum error correction. However, their scalability has lagged behind that of the alkali atoms. Here, we report 2400 ytterbium-174 atoms trapped in an optical tweezer array with enhanced loading efficiency of 83.5(1)\% via blue-detuned light-assisted collisions. We develop a quantitative model of the collision dynamics and find good agreement between the calculated inelastic collision rates and the experimentally measured loading efficiencies.Notably, the loading efficiency is largely maintained for array sizes ranging from dozens to thousands, exhibiting excellent scalability. We further demonstrate that the enhancement exists robustly across a range of interatomic potentials, suggesting its utility for other atomic species. To establish the capability of the $^{174}$Yb arrays toward universal quantum computation, we propose to encode the qubit in the ground-clock state manifold and estimate a 99.9\% two-qubit gate fidelity with experimentally feasible parameters. Our work advances the prospects for realizing large-scale quantum computers using alkaline-earth-like atoms.

quant-ph↗

arXiv2025

Rectifying Soft-Label Entangled Bias in Long-Tailed Dataset Distillation

Dataset distillation compresses large-scale datasets into compact, highly informative synthetic data, significantly reducing storage and training costs. However, existing research primarily focuses on balanced datasets and struggles to perform under real-world long-tailed distributions. In this work, we emphasize the critical role of soft labels in long-tailed dataset distillation and uncover the underlying mechanisms contributing to performance degradation. Specifically, we derive an imbalance-aware generalization bound for model trained on distilled dataset. We then identify two primary sources of soft-label bias, which originate from the distillation model and the distilled images, through systematic perturbation of the data imbalance levels. To address this, we propose ADSA, an Adaptive Soft-label Alignment module that calibrates the entangled biases. This lightweight module integrates seamlessly into existing distillation pipelines and consistently improves performance. On ImageNet-1k-LT with EDC and IPC=50, ADSA improves tail-class accuracy by up to 11.8% and raises overall accuracy to 41.4%. Extensive experiments demonstrate that ADSA provides a robust and generalizable solution under limited label budgets and across a range of distillation techniques. Code is available at: https://github.com/j-cyoung/ADSA_DD.git.

cs.CV↗

arXiv2025

Parameterizing Dataset Distillation via Gaussian Splatting

Dataset distillation aims to compress training data while preserving training-aware knowledge, alleviating the reliance on large-scale datasets in modern model training. Dataset parameterization provides a more efficient storage structure for dataset distillation, reducing redundancy and accommodating richer information. However, existing methods either rely on complex auxiliary modules or fail to balance representational capacity and efficiency. In this paper, we propose GSDD, a simple, novel, and effective dataset parameterization technique for Dataset Distillation based on Gaussian Splatting. We adapt CUDA-based splatting operators for parallel training in batch, enabling high-quality rendering with minimal computational and memory overhead. Gaussian primitives can effectively capture meaningful training features, allowing a sparse yet expressive representation of individual images. Leveraging both high representational capacity and efficiency, GSDD substantially increases the diversity of distilled datasets under a given storage budget, thereby improving distillation performance. Beyond achieving competitive results on multiple standard benchmarks, GSDD also delivers significant performance gains on large-scale datasets such as ImageNet-1K and on video distillation tasks. In addition, we conduct comprehensive benchmarks to evaluate the computational efficiency, memory footprint, and cross-GPU architectural stability of GSDD. Code is available on https://github.com/j-cyoung/GSDatasetDistillation

cs.CV↗

arXiv2025

First Full Dalitz Plot Measurement in Neutron $\beta$-Decay using the Nab Spectrometer and Implications for New Physics

Precision measurements of observables in neutron $\beta$-decay are used to test the Standard Model description of the weak interaction and search for evidence of new physics. The Nab experiment at the Fundamental Neutron Physics Beamline at the Spallation Neutron Source was constructed to measure correlations in neutron decay by utilizing an asymmetric spectrometer and novel detection system to accurately reconstruct the proton momentum and electron energy for each $\beta$-decay. This work describes the detection of neutron $\beta$-decay products in the Nab spectrometer and presents the first full Dalitz plot representation of the phase space of neutron $\beta$-decay for all electrons >100 keV. In addition, new constraints are placed on a possible excited neutron state, hypothesized to explain the disagreement between the appearance and disappearance neutron lifetime techniques.

nucl-ex↗

arXiv2024

Robust Reinforcement Learning under Diffusion Models for Data with Jumps

Reinforcement Learning (RL) has proven effective in solving complex decision-making tasks across various domains, but challenges remain in continuous-time settings, particularly when state dynamics are governed by stochastic differential equations (SDEs) with jump components. In this paper, we address this challenge by introducing the Mean-Square Bipower Variation Error (MSBVE) algorithm, which enhances robustness and convergence in scenarios involving significant stochastic noise and jumps. We first revisit the Mean-Square TD Error (MSTDE) algorithm, commonly used in continuous-time RL, and highlight its limitations in handling jumps in state dynamics. The proposed MSBVE algorithm minimizes the mean-square quadratic variation error, offering improved performance over MSTDE in environments characterized by SDEs with jumps. Simulations and formal proofs demonstrate that the MSBVE algorithm reliably estimates the value function in complex settings, surpassing MSTDE's performance when faced with jump processes. These findings underscore the importance of alternative error metrics to improve the resilience and effectiveness of RL algorithms in continuous-time frameworks.

cs.LG↗

arXiv2023

Artificial Intelligence System for Detection and Screening of Cardiac Abnormalities using Electrocardiogram Images

The artificial intelligence (AI) system has achieved expert-level performance in electrocardiogram (ECG) signal analysis. However, in underdeveloped countries or regions where the healthcare information system is imperfect, only paper ECGs can be provided. Analysis of real-world ECG images (photos or scans of paper ECGs) remains challenging due to complex environments or interference. In this study, we present an AI system developed to detect and screen cardiac abnormalities (CAs) from real-world ECG images. The system was evaluated on a large dataset of 52,357 patients from multiple regions and populations across the world. On the detection task, the AI system obtained area under the receiver operating curve (AUC) of 0.996 (hold-out test), 0.994 (external test 1), 0.984 (external test 2), and 0.979 (external test 3), respectively. Meanwhile, the detection results of AI system showed a strong correlation with the diagnosis of cardiologists (cardiologist 1 (R=0.794, p<1e-3), cardiologist 2 (R=0.812, p<1e-3)). On the screening task, the AI system achieved AUCs of 0.894 (hold-out test) and 0.850 (external test). The screening performance of the AI system was better than that of the cardiologists (AI system (0.846) vs. cardiologist 1 (0.520) vs. cardiologist 2 (0.480)). Our study demonstrates the feasibility of an accurate, objective, easy-to-use, fast, and low-cost AI system for CA detection and screening. The system has the potential to be used by healthcare professionals, caregivers, and general users to assess CAs based on real-world ECG images.

cs.CV↗

arXiv2022

MetaVA: Curriculum Meta-learning and Pre-fine-tuning of Deep Neural Networks for Detecting Ventricular Arrhythmias based on ECGs

Ventricular arrhythmias (VA) are the main causes of sudden cardiac death. Developing machine learning methods for detecting VA based on electrocardiograms (ECGs) can help save people's lives. However, developing such machine learning models for ECGs is challenging because of the following: 1) group-level diversity from different subjects and 2) individual-level diversity from different moments of a single subject. In this study, we aim to solve these problems in the pre-training and fine-tuning stages. For the pre-training stage, we propose a novel model agnostic meta-learning (MAML) with curriculum learning (CL) method to solve group-level diversity. MAML is expected to better transfer the knowledge from a large dataset and use only a few recordings to quickly adapt the model to a new person. CL is supposed to further improve MAML by meta-learning from easy to difficult tasks. For the fine-tuning stage, we propose improved pre-fine-tuning to solve individual-level diversity. We conduct experiments using a combination of three publicly available ECG datasets. The results show that our method outperforms the compared methods in terms of all evaluation metrics. Ablation studies show that MAML and CL could help perform more evenly, and pre-fine-tuning could better fit the model to training data.

cs.LG↗

arXiv2021

Neutron diffraction study of magnetism in van der Waals layered MnBi$_{2n}$Te$_{3n+1}$

Two-dimensional van der Waals MnBi$_{2n}$Te$_{3n+1}$ (n = 1, 2, 3, 4) compounds have been recently found to be intrinsic magnetic topological insulators rendering quantum anomalous Hall effect and diverse topological states. Here, we summarize and compare the crystal and magnetic structures of this family, and discuss the effects of chemical composition on their magnetism. We found that a considerable fraction of Bi occupies at the Mn sites in MnBi$_{2n}$Te$_{3n+1}$ (n = 1, 2, 3, 4) while Mn is no detectable at the non-magnetic atomic sites within the resolution of neutron diffraction experiments. The occupancy of Mn monotonically decreases with the increase of n. The polarized neutron diffraction on the representative MnBi$_{4}$Te$_{7}$ reveals that its magnetization density is exclusively accumulated at the Mn site, in good agreement with the results from the unpolarized neutron diffraction. The defects of Bi at the Mn site naturally explain the continuously reduced saturated magnetic moments from n = 1 to n = 4. The experimentally estimated critical exponents of all the compounds generally suggest a three-dimensional character of magnetism. Our work provides material-specified structural parameters that may be useful for band structure calculations to understand the observed topological surface states and for designing quantum magnetic materials through chemical doping.

cond-mat.str-el↗