arXiv subjects

Yi Chen

Publications and source records attributed to Yi Chen.

At least 127 records · Page 7Linked to original sources

arXiv2025

Analysis note: measurement of thrust and track energy-energy correlator in $e^+e^-$ collisions at 91.2 GeV with DELPHI open data

Recent theoretical developments, as well as experimental measurements at hadron collisions, have renewed interest in studying event shape variables in $e^+e^-$ collisions. We present a measurement of thrust and track-based energy-energy correlator in $e^+e^-$ collisions at center-of-mass energy of 91.2 GeV, using newly released open data from the DELPHI experiment. The event shapes, measured with unprecedented resolution and precision, are compared to various Monte Carlo and analytic predictions. Leveraging DELPHI's unique detector geometry and reconstruction capabilities, the track energy-energy correlator measurement provides data with the highest angular resolution, offering critical inputs for precision tests of QCD in both collinear and back-to-back limits. This note presents the first physics analysis using DELPHI open data and establishes benchmarks necessary for future studies exploiting this legacy dataset.

hep-ex↗

arXiv2025

Moto: Latent Motion Token as the Bridging Language for Learning Robot Manipulation from Videos

Recent developments in Large Language Models pre-trained on extensive corpora have shown significant success in various natural language processing tasks with minimal fine-tuning. This success offers new promise for robotics, which has long been constrained by the high cost of action-labeled data. We ask: given the abundant video data containing interaction-related knowledge available as a rich "corpus", can a similar generative pre-training approach be effectively applied to enhance robot learning? The key challenge is to identify an effective representation for autoregressive pre-training that benefits robot manipulation tasks. Inspired by the way humans learn new skills through observing dynamic environments, we propose that effective robotic learning should emphasize motion-related knowledge, which is closely tied to low-level actions and is hardware-agnostic, facilitating the transfer of learned motions to actual robot actions. To this end, we introduce Moto, which converts video content into latent Motion Token sequences by a Latent Motion Tokenizer, learning a bridging "language" of motion from videos in an unsupervised manner. We pre-train Moto-GPT through motion token autoregression, enabling it to capture diverse visual motion knowledge. After pre-training, Moto-GPT demonstrates the promising ability to produce semantically interpretable motion tokens, predict plausible motion trajectories, and assess trajectory rationality through output likelihood. To transfer learned motion priors to real robot actions, we implement a co-fine-tuning strategy that seamlessly bridges latent motion token prediction and real robot control. Extensive experiments show that the fine-tuned Moto-GPT exhibits superior robustness and efficiency on robot manipulation benchmarks, underscoring its effectiveness in transferring knowledge from video data to downstream visual manipulation tasks.

cs.RO↗

arXiv2025

A Multi-dimensional Semantic Surprise Framework Based on Low-Entropy Semantic Manifolds for Fine-Grained Out-of-Distribution Detection

Out-of-Distribution (OOD) detection is a cornerstone for the safe deployment of AI systems in the open world. However, existing methods treat OOD detection as a binary classification problem, a cognitive flattening that fails to distinguish between semantically close (Near-OOD) and distant (Far-OOD) unknown risks. This limitation poses a significant safety bottleneck in applications requiring fine-grained risk stratification. To address this, we propose a paradigm shift from a conventional probabilistic view to a principled information-theoretic framework. We formalize the core task as quantifying the Semantic Surprise of a new sample and introduce a novel ternary classification challenge: In-Distribution (ID) vs. Near-OOD vs. Far-OOD. The theoretical foundation of our work is the concept of Low-Entropy Semantic Manifolds, which are explicitly structured to reflect the data's intrinsic semantic hierarchy. To construct these manifolds, we design a Hierarchical Prototypical Network. We then introduce the Semantic Surprise Vector (SSV), a universal probe that decomposes a sample's total surprise into three complementary and interpretable dimensions: conformity, novelty, and ambiguity. To evaluate performance on this new task, we propose the Normalized Semantic Risk (nSR), a cost-sensitive metric. Experiments demonstrate that our framework not only establishes a new state-of-the-art (sota) on the challenging ternary task, but its robust representations also achieve top results on conventional binary benchmarks, reducing the False Positive Rate by over 60% on datasets like LSUN.

stat.ML↗

arXiv2025

A Method to Improve the Performance of Reinforcement Learning Based on the Y Operator for a Class of Stochastic Differential Equation-Based Child-Mother Systems

This paper introduces a novel operator, termed the Y operator, to elevate control performance in Actor-Critic(AC) based reinforcement learning for systems governed by stochastic differential equations(SDEs). The Y operator ingeniously integrates the stochasticity of a class of child-mother system into the Critic network's loss function, yielding substantial advancements in the control performance of RL algorithms.Additionally, the Y operator elegantly reformulates the challenge of solving partial differential equations for the state-value function into a parallel problem for the drift and diffusion functions within the system's SDEs.A rigorous mathematical proof confirms the operator's validity.This transformation enables the Y Operator-based Reinforcement Learning(YORL) framework to efficiently tackle optimal control problems in both model-based and data-driven systems.The superiority of YORL is demonstrated through linear and nonlinear numerical examples showing its enhanced performance over existing methods post convergence.

cs.AI↗

arXiv2025

Beyond Human Demonstrations: Diffusion-Based Reinforcement Learning to Generate Data for VLA Training

Vision-language-action (VLA) models have shown strong generalization across tasks and embodiments; however, their reliance on large-scale human demonstrations limits their scalability owing to the cost and effort of manual data collection. Reinforcement learning (RL) offers a potential alternative to generate demonstrations autonomously, yet conventional RL algorithms often struggle on long-horizon manipulation tasks with sparse rewards. In this paper, we propose a modified diffusion policy optimization algorithm to generate high-quality and low-variance trajectories, which contributes to a diffusion RL-powered VLA training pipeline. Our algorithm benefits from not only the high expressiveness of diffusion models to explore complex and diverse behaviors but also the implicit regularization of the iterative denoising process to yield smooth and consistent demonstrations. We evaluate our approach on the LIBERO benchmark, which includes 130 long-horizon manipulation tasks, and show that the generated trajectories are smoother and more consistent than both human demonstrations and those from standard Gaussian RL policies. Further, training a VLA model exclusively on the diffusion RL-generated data achieves an average success rate of 81.9%, which outperforms the model trained on human data by +5.3% and that on Gaussian RL-generated data by +12.6%. The results highlight our diffusion RL as an effective alternative for generating abundant, high-quality, and low-variance demonstrations for VLA models.

cs.RO↗

arXiv2025

Delving into Cryptanalytic Extraction of PReLU Neural Networks

The machine learning problem of model extraction was first introduced in 1991 and gained prominence as a cryptanalytic challenge starting with Crypto 2020. For over three decades, research in this field has primarily focused on ReLU-based neural networks. In this work, we take the first step towards the cryptanalytic extraction of PReLU neural networks, which employ more complex nonlinear activation functions than their ReLU counterparts. We propose a raw output-based parameter recovery attack for PReLU networks and extend it to more restrictive scenarios where only the top-m probability scores are accessible. Our attacks are rigorously evaluated through end-to-end experiments on diverse PReLU neural networks, including models trained on the MNIST dataset. To the best of our knowledge, this is the first practical demonstration of PReLU neural network extraction across three distinct attack scenarios.

cs.CR↗

arXiv2025

Metamaterials and Fluid Flows

Understanding and controlling the dynamic interactions between fluid flows and solid materials and structures-a field known as fluid-structure interaction -is central not only to established disciplines such as aerospace and naval engineering but also to emerging technologies such as energy harvesting, soft robotics, and biomedical devices. In recent years, the advent of metamaterials-rationally designed composites with properties beyond their constituents, often not found in conventional materials-has provided exciting opportunities for rethinking and redesigning fluid-structure interaction. The premise of engineering the internal structure of materials interfacing with fluid flows is opening a new horizon for precise and effective manipulation and control of coupled fluidic, acoustic, and elastodynamics responses. This review focuses on this relatively unexplored interdisciplinary theme with broad real-world technological significance. Key performance metrics, such as fuel consumption of transport systems, efficiency of renewable energy extraction, mitigation of noise emissions, and resilience to structural fatigue, depend on the control of interactions between flow, acoustic, and vibration mechanisms. Flow control, for example, which spans a wealth of regimes such as laminar, transitional, turbulent, and unsteady separated flows, is highly influenced by the ability to tailor fluid-structure interaction behavior. We survey and discuss theoretical frameworks that describe the interplay between fluids and elastic solids, with a focus on contemporary work and emerging concepts. The paper is organised into three main sections-flow-structure interactions, acoustic-structure interactions, and exotic metamaterial concepts with potential impact on fluid-structure interaction-and concludes with perspectives on current challenges and future directions in this rapidly expanding area of research.

cond-mat.soft↗

arXiv2025

DQEN: Dual Query Enhancement Network for DETR-based HOI Detection

Human-Object Interaction (HOI) detection focuses on localizing human-object pairs and recognizing their interactions. Recently, the DETR-based framework has been widely adopted in HOI detection. In DETR-based HOI models, queries with clear meaning are crucial for accurately detecting HOIs. However, prior works have typically relied on randomly initialized queries, leading to vague representations that limit the model's effectiveness. Meanwhile, humans in the HOI categories are fixed, while objects and their interactions are variable. Therefore, we propose a Dual Query Enhancement Network (DQEN) to enhance object and interaction queries. Specifically, object queries are enhanced with object-aware encoder features, enabling the model to focus more effectively on humans interacting with objects in an object-aware way. On the other hand, we design a novel Interaction Semantic Fusion module to exploit the HOI candidates that are promoted by the CLIP model. Semantic features are extracted to enhance the initialization of interaction queries, thereby improving the model's ability to understand interactions. Furthermore, we introduce an Auxiliary Prediction Unit aimed at improving the representation of interaction features. Our proposed method achieves competitive performance on both the HICO-Det and the V-COCO datasets. The source code is available at https://github.com/lzzhhh1019/DQEN.

cs.CV↗

arXiv2025

Sylow numbers and the structure of finite groups

Suppose that the finite group $G=AB$ is a mutually permutable product of two subgroups $A$ and $B$. By using Sylow numbers of $A$ and $B$, we present some new bounds of the $p$-length $l_p(G)$ of a $p$-solvable group $G$ and the nilpotent length $F_l(G)$ and the derived length $dl(G/Φ(G))$ of a solvable group $G$. Some known results of Zhang in J. Algebra 1995, 176 are extended.

math.GR↗

arXiv2025

Identify, Isolate, and Purge: Mitigating Hallucinations in LVLMs via Self-Evolving Distillation

Large Vision-Language Models (LVLMs) have demonstrated remarkable advancements in numerous areas such as multimedia. However, hallucination issues significantly limit their credibility and application potential. Existing mitigation methods typically rely on external tools or the comparison of multi-round inference, which significantly increase inference time. In this paper, we propose \textbf{SE}lf-\textbf{E}volving \textbf{D}istillation (\textbf{SEED}), which identifies hallucinations within the inner knowledge of LVLMs, isolates and purges them, and then distills the purified knowledge back into the model, enabling self-evolution. Furthermore, we identified that traditional distillation methods are prone to inducing void spaces in the output space of LVLMs. To address this issue, we propose a Mode-Seeking Evolving approach, which performs distillation to capture the dominant modes of the purified knowledge distribution, thereby avoiding the chaotic results that could emerge from void spaces. Moreover, we introduce a Hallucination Elimination Adapter, which corrects the dark knowledge of the original model by learning purified knowledge. Extensive experiments on multiple benchmarks validate the superiority of our SEED, demonstrating substantial improvements in mitigating hallucinations for representative LVLM models such as LLaVA-1.5 and InternVL2. Remarkably, the F1 score of LLaVA-1.5 on the hallucination evaluation metric POPE-Random improved from 81.3 to 88.3.

cs.LG↗

arXiv2025

Executive Accountability Systems and the Environmental Violations of State-Owned Enterprises in China

Executive accountability is increasingly viewed as a critical mechanism for improving corporate environmental performance, especially in state-owned enterprises (SOEs) that dominate high-emission sectors such as energy, infrastructure, and heavy industry. This study examines whether China's Accountability System for Irregular Operations and Investments (ASIOI) curbs environmental violations in SOEs. Exploiting the staggered regional implementation of ASIOI as a quasi-natural experiment, we find that the policy leads to a significant reduction in SOE environmental misconduct. Drawing on a criminology-based cost-benefit framework, we identify three underlying mechanisms: strengthened internal controls, increased green investment, and enhanced green innovation. Further analyses reveal that the deterrent effect of ASIOI is more pronounced in SOEs that exhibit weaker regulatory oversight and stronger incentives to commit violations. By focusing on politically embedded SOEs, this study shows how accountability mechanisms can catalyze proactive green transformation, enhancing the strategic role of public governance in sustainability transitions.

econ.GN↗

arXiv2025

Harmonic balance-automatic differentiation method: an out-of-the-box and efficient solver for general nonlinear dynamics simulation

The Harmonic Balance-Alternating Frequency-Time domain (HB-AFT) method is extensively employed for dynamic response analysis of nonlinear systems. However, its application to high-dimensional complex systems is constrained by the manual derivation of Jacobian matrices during Newton-Raphson iterations, which become computationally intractable or error-prone for intricate nonlinearities. The Harmonic Balance-Automatic Differentiation (HB-AD) method is proposed to address this limitation, in which AD is integrated with the harmonic balance framework. This approach eliminates all manual derivations by leveraging AD to compute exact Jacobians numerically, enabling generic and efficient analysis of high-dimensional complex nonlinear systems. The implementation utilizes advanced deep learning frameworks for native parallel computing and CUDA acceleration, and combines AD with arc-length continuation, establishing an out-of-the-box and high efficiency computational architecture. Users need only supply the system's dynamic equations, HB-AD then autonomously trace the complete panorama of periodic responses -- including stable/unstable solution branches. Computational experiments on a rotor system with squeeze-film damper (SFD) demonstrate HB-AD's capability in handling complex nonlinear expressions with automated Jacobian calculations. For a high-dimensional aero-engine rotor-bearing-casing system with complex bearing nonlinearities, HB-AD achieves 17-fold higher efficiency than traditional HB-AFT and 144-fold acceleration over the Newmark method. The HB-AD method is a synergistic merger of computational mechanics and machine learning primitives, delivers an easy to use, general-purpose, high efficiency platform for high-fidelity dynamic characterization of high-dimensional engineering systems.

cs.CE↗

arXiv2025

Metric Learning in an RKHS

Metric learning from a set of triplet comparisons in the form of "Do you think item h is more similar to item i or item j?", indicating similarity and differences between items, plays a key role in various applications including image retrieval, recommendation systems, and cognitive psychology. The goal is to learn a metric in the RKHS that reflects the comparisons. Nonlinear metric learning using kernel methods and neural networks have shown great empirical promise. While previous works have addressed certain aspects of this problem, there is little or no theoretical understanding of such methods. The exception is the special (linear) case in which the RKHS is the standard Euclidean space $\mathbb{R}^d$; there is a comprehensive theory for metric learning in $\mathbb{R}^d$. This paper develops a general RKHS framework for metric learning and provides novel generalization guarantees and sample complexity bounds. We validate our findings through a set of simulations and experiments on real datasets. Our code is publicly available at https://github.com/RamyaLab/metric-learning-RKHS.

stat.ML↗

arXiv2025

GovRelBench:A Benchmark for Government Domain Relevance

Current evaluations of LLMs in the government domain primarily focus on safety considerations in specific scenarios, while the assessment of the models' own core capabilities, particularly domain relevance, remains insufficient. To address this gap, we propose GovRelBench, a benchmark specifically designed for evaluating the core capabilities of LLMs in the government domain. GovRelBench consists of government domain prompts and a dedicated evaluation tool, GovRelBERT. During the training process of GovRelBERT, we introduce the SoftGovScore method: this method trains a model based on the ModernBERT architecture by converting hard labels to soft scores, enabling it to accurately compute the text's government domain relevance score. This work aims to enhance the capability evaluation framework for large models in the government domain, providing an effective tool for relevant research and practice. Our code and dataset are available at https://github.com/pan-xi/GovRelBench.

cs.AI↗

arXiv2025

VAGU & GtS: LLM-Based Benchmark and Framework for Joint Video Anomaly Grounding and Understanding

Video Anomaly Detection (VAD) aims to identify anomalous events in videos and accurately determine their time intervals. Current VAD methods mainly fall into two categories: traditional DNN-based approaches that focus on temporal localization, and LLM-based approaches that emphasize semantic understanding. Both anomaly understanding and grounding are essential for comprehensive video anomaly detection and can complement each other. However, no existing model or dataset supports both tasks simultaneously. To address this, we introduce VAGU (Video Anomaly Grounding and Understanding), the first benchmark to integrate both tasks. Each VAGU instance includes annotations for anomaly category, semantic explanation, precise temporal grounding and Video QA. We also provide multiple-choice Video QA for objective evaluation. Based on this dataset, we propose Glance then Scrutinize (GtS), a training-free framework guided by textual prompts. The framework first enables coarse localization of high-probability anomalous regions, followed by detailed anomaly interpretation and temporal boundary refinement. Additionally, we propose the JeAUG metric, which jointly evaluates semantic interpretability and temporal precision, overcoming the limitations of traditional metrics. Extensive experiments verify the effectiveness of our benchmark, framework, and evaluation metric.

cs.CV↗

arXiv2025

The Evolution of Video Anomaly Detection: A Unified Framework from DNN to MLLM

Video anomaly detection (VAD) aims to identify and ground anomalous behaviors or events in videos, serving as a core technology in the fields of intelligent surveillance and public safety. With the advancement of deep learning, the continuous evolution of deep model architectures has driven innovation in VAD methodologies, significantly enhancing feature representation and scene adaptability, thereby improving algorithm generalization and expanding application boundaries. More importantly, the rapid development of multi-modal large language (MLLMs) and large language models (LLMs) has introduced new opportunities and challenges to the VAD field. Under the support of MLLMs and LLMs, VAD has undergone significant transformations in terms of data annotation, input modalities, model architectures, and task objectives. The surge in publications and the evolution of tasks have created an urgent need for systematic reviews of recent advancements. This paper presents the first comprehensive survey analyzing VAD methods based on MLLMs and LLMs, providing an in-depth discussion of the changes occurring in the VAD field in the era of large models and their underlying causes. Additionally, this paper proposes a unified framework that encompasses both deep neural network (DNN)-based and LLM-based VAD methods, offering a thorough analysis of the new VAD paradigms empowered by LLMs, constructing a classification system, and comparing their strengths and weaknesses. Building on this foundation, this paper focuses on current VAD methods based on MLLMs/LLMs. Finally, based on the trajectory of technological advancements and existing bottlenecks, this paper distills key challenges and outlines future research directions, offering guidance for the VAD community.

cs.CV↗

arXiv2025

Analysis note: measurement of thrust in $e^{+}e^{-}$ collisions at $\sqrt{s}$ = 91 GeV with archived ALEPH data

A measurement of the thrust distribution in $e^{+}e^{-}$ collisions at $\sqrt{s} = 91.2$ GeV with archived data from the ALEPH experiment at the Large Electron-Positron Collider is presented. The thrust distribution is reconstructed from charged and neutral particles resulting from hadronic $Z$-boson decays. For the first time with $e^{+}e^{-}$ data, detector effects are corrected using a machine learning based method for unbinned unfolding. The measurement provides new input for resolving current discrepancies between theoretical calculations and experimental determinations of $α_{s}$, constraining non-perturbative effects through logarithmic moments, developing differential hadronization models, and enabling new precision studies using the archived data.

hep-ex↗

arXiv2025

An Age-based Study into Interactive Narrative Visualization Engagement

Research has shown that an audiences' age impacts their engagement in digital media. Interactive narrative visualization is an increasingly popular form of digital media that combines data visualization and storytelling to convey important information. However, audience age is often overlooked by interactive narrative visualization authors. Using an established visualization engagement questionnaire, we ran an empirical experiment where we compared end-user engagement to audience age. We found a small difference in engagement scores where older age cohorts were less engaged than the youngest age cohort. Our qualitative analysis revealed that the terminology and overall understanding of interactive narrative patterns integrated into narrative visualization was more apparent in the feedback from younger age cohorts relative to the older age cohorts. We conclude this paper with a series of recommendations for authors of interactive narrative visualization on how to design inclusively for audiences according to their age.

cs.HC↗