arXiv subjects

Chun Yang

Publications and source records attributed to Chun Yang.

At least 19 recordsLinked to original sources

arXiv2026

When Do PEFT Adaptations Leak Structure? Measuring Black-Box Structural Bounds in Public-Base Model Services

Services increasingly deploy public foundation models with private parameter-efficient adaptations, creating a differential information leakage risk when auditors or adversaries can execute the public base model locally and observe victim outputs. We present VectorHijack-SR, a measurement methodology that converts paired victim/base residuals into calibrated structural bounds over PEFT family, layer locality, and coarse rank, while separating metadata visibility from open-world validity and operational exploitability. Our estimator aggregates query-level magnitude, ranking, entropy, margin, length, template, locality, and spectral statistics into service-level representations. A service-disjoint classifier quantifies structural evidence, and a cross-fitted hierarchical rejector evaluates whether a victim lies outside the calibrated LoRA manifold. Across classification backbones, family leakage exceeds uniform chance on BERT/MNLI (8/12), RoBERTa/MNLI (21/24), and DeBERTa-v3 on MNLI (12/18) and AG News (15/18). Rank inference is task dependent: BERT/MNLI and DeBERTa/AG News reach 8/9, whereas DeBERTa/MNLI achieves 4/9 and is statistically compatible with chance after correction. On a ten-seed BERT open-set grid, the rejector achieves pooled AUROC 0.804 (95% CI [0.660, 0.927]) and known accuracy 0.956, but remains limited on structurally close DoRA and LoRA+head variants. Exact-version linkage on five held-out LoRA-r64 services reaches AUC 0.940. Experiments reveal a visibility-exploitability gap: two-stage recovery provides no fair-budget query savings, posterior-selected PEFT underperforms distill-then-convert PEFT (0.356 vs. 0.517), and free-running generation remains near chance. These results show that known-base, rich-output PEFT services can leak actionable structural and version information, while closed-set confidence alone does not establish universal adapter recovery.

cs.CR↗

arXiv2026

M100: An Orchestrated Dataflow Architecture Powering General AI Computing

As deep learning-based AI technologies gain momentum, the demand for general-purpose AI computing architectures continues to grow. While GPGPU-based architectures offer versatility for diverse AI workloads, they often fall short in efficiency and cost-effectiveness. Various Domain-Specific Architectures (DSAs) excel at particular AI tasks but struggle to extend across broader applications or adapt to the rapidly evolving AI landscape. M100 is Li Auto's response: a performant, cost-effective architecture for AI inference in Autonomous Driving (AD), Large Language Models (LLMs), and intelligent human interactions, domains crucial to today's most competitive automobile platforms. M100 employs a dataflow parallel architecture, where compiler-architecture co-design orchestrates not only computation but, more critically, data movement across time and space. Leveraging dataflow computing efficiency, our hardware-software co-design improves system performance while reducing hardware complexity and cost. M100 largely eliminates caching: tensor computations are driven by compiler- and runtime-managed data streams flowing between computing elements and on/off-chip memories, yielding greater efficiency and scalability than cache-based systems. Another key principle was selecting the right operational granularity for scheduling, issuing, and execution across compiler, firmware, and hardware. Recognizing commonalities in AI workloads, we chose the tensor as the fundamental data element. M100 demonstrates general AI computing capability across diverse inference applications, including UniAD (for AD) and LLaMA (for LLMs). Benchmarks show M100 outperforms GPGPU architectures in AD applications with higher utilization, representing a promising direction for future general AI computing.

cs.LG↗

arXiv2025

A Multi-Stage Deep Learning Framework with PKCP-MixUp Augmentation for Pediatric Liver Tumor Diagnosis Using Multi-Phase Contrast-Enhanced CT

Pediatric liver tumors are one of the most common solid tumors in pediatrics, with differentiation of benign or malignant status and pathological classification critical for clinical treatment. While pathological examination is the gold standard, the invasive biopsy has notable limitations: the highly vascular pediatric liver and fragile tumor tissue raise complication risks such as bleeding; additionally, young children with poor compliance require anesthesia for biopsy, increasing medical costs or psychological trauma. Although many efforts have been made to utilize AI in clinical settings, most researchers have overlooked its importance in pediatric liver tumors. To establish a non-invasive examination procedure, we developed a multi-stage deep learning (DL) framework for automated pediatric liver tumor diagnosis using multi-phase contrast-enhanced CT. Two retrospective and prospective cohorts were enrolled. We established a novel PKCP-MixUp data augmentation method to address data scarcity and class imbalance. We also trained a tumor detection model to extract ROIs, and then set a two-stage diagnosis pipeline with three backbones with ROI-masked images. Our tumor detection model has achieved high performance (mAP=0.871), and the first stage classification model between benign and malignant tumors reached an excellent performance (AUC=0.989). Final diagnosis models also exhibited robustness, including benign subtype classification (AUC=0.915) and malignant subtype classification (AUC=0.979). We also conducted multi-level comparative analyses, such as ablation studies on data and training pipelines, as well as Shapley-Value and CAM interpretability analyses. This framework fills the pediatric-specific DL diagnostic gap, provides actionable insights for CT phase selection and model design, and paves the way for precise, accessible pediatric liver tumor diagnosis.

eess.IV↗

arXiv2025

Who Uses Whose Telescopes? Analyzing the Knowledge Geography and Research Dominance of Global Astronomical Facilities

Large-scale research infrastructures (LSRIs) are central to contemporary science policy, combining massive capital investments with international access regimes. Yet whether open access to these infrastructures translates into more equitable scientific authority remains contested. Astronomy provides a critical case: world-leading observatories are globally shared but embedded in specific national contexts. We compile a novel country--year dataset (1955--2025) linking the location of astronomical facilities with publication usage and authorship roles. This enables us to distinguish between hosting, using, and leading in telescope-based research. Our analysis reveals: (i) usage and impact are heavily concentrated in a small number of facility hubs; (ii) scientific leadership is even more unequal than access or usage (Gini coefficient 0.91 for first/corresponding authorship versus 0.85 for facilities and usage); (iii) hosting and leadership often decouple--countries such as Chile and South Africa mediate large publication volumes without commensurate gains in leading roles; and (iv) global leadership has shifted from U.S. dominance to a multi-hub system centered in the United States, Western Europe, China, Japan, and Australia. These findings challenge the assumption that international access alone democratizes science. We argue that converting participation into leadership requires domestic PI programs, investments in instrumentation and data pipelines, and governance models that distribute credit more equitably. The study highlights how the governance of LSRIs shapes global scientific hierarchies and offers design principles for infrastructures that seek not only to share data but also to broaden scientific authority.

astro-ph.IM↗

arXiv2025

SLiNT: Structure-aware Language Model with Injection and Contrastive Training for Knowledge Graph Completion

Link prediction in knowledge graphs requires integrating structural information and semantic context to infer missing entities. While large language models offer strong generative reasoning capabilities, their limited exploitation of structural signals often results in structural sparsity and semantic ambiguity, especially under incomplete or zero-shot settings. To address these challenges, we propose SLiNT (Structure-aware Language model with Injection and coNtrastive Training), a modular framework that injects knowledge-graph-derived structural context into a frozen LLM backbone with lightweight LoRA-based adaptation for robust link prediction. Specifically, Structure-Guided Neighborhood Enhancement (SGNE) retrieves pseudo-neighbors to enrich sparse entities and mitigate missing context; Dynamic Hard Contrastive Learning (DHCL) introduces fine-grained supervision by interpolating hard positives and negatives to resolve entity-level ambiguity; and Gradient-Decoupled Dual Injection (GDDI) performs token-level structure-aware intervention while preserving the core LLM parameters. Experiments on WN18RR and FB15k-237 show that SLiNT achieves superior or competitive performance compared with both embedding-based and generation-based baselines, demonstrating the effectiveness of structure-aware representation learning for scalable knowledge graph completion.

cs.CL↗

arXiv2025

Stationarity Exploration for Multivariate Time Series Forecasting

Deep learning-based time series forecasting has found widespread applications. Recently, converting time series data into the frequency domain for forecasting has become popular for accurately exploring periodic patterns. However, existing methods often cannot effectively explore stationary information from complex intertwined frequency components. In this paper, we propose a simple yet effective Amplitude-Phase Reconstruct Network (APRNet) that models the inter-relationships of amplitude and phase, which prevents the amplitude and phase from being constrained by different physical quantities, thereby decoupling the distinct characteristics of signals for capturing stationary information. Specifically, we represent the multivariate time series input across sequence and channel dimensions, highlighting the correlation between amplitude and phase at multiple interaction frequencies. We propose a novel Kolmogorov-Arnold-Network-based Local Correlation (KLC) module to adaptively fit local functions using univariate functions, enabling more flexible characterization of stationary features across different amplitudes and phases. This significantly enhances the model's capability to capture time-varying patterns. Extensive experiments demonstrate the superiority of our APRNet against the state-of-the-arts (SOTAs).

cs.LG↗

arXiv2025

Semantic-Enhanced Time-Series Forecasting via Large Language Models

Time series forecasting plays a significant role in finance, energy, meteorology, and IoT applications. Recent studies have leveraged the generalization capabilities of large language models (LLMs) to adapt to time series forecasting, achieving promising performance. However, existing studies focus on token-level modal alignment, instead of bridging the intrinsic modality gap between linguistic knowledge structures and time series data patterns, greatly limiting the semantic representation. To address this issue, we propose a novel Semantic-Enhanced LLM (SE-LLM) that explores the inherent periodicity and anomalous characteristics of time series to embed into the semantic space to enhance the token embedding. This process enhances the interpretability of tokens for LLMs, thereby activating the potential of LLMs for temporal sequence analysis. Moreover, existing Transformer-based LLMs excel at capturing long-range dependencies but are weak at modeling short-term anomalies in time-series data. Hence, we propose a plugin module embedded within self-attention that models long-term and short-term dependencies to effectively adapt LLMs to time-series analysis. Our approach freezes the LLM and reduces the sequence dimensionality of tokens, greatly reducing computational consumption. Experiments demonstrate the superiority performance of our SE-LLM against the state-of-the-art (SOTA) methods.

cs.LG↗

arXiv2025

The role of preprints in open science: Accelerating knowledge transfer from science to technology

Preprints have become increasingly essential in the landscape of open science, facilitating not only the exchange of knowledge within the scientific community but also bridging the gap between science and technology. However, the impact of preprints on technological innovation, given their unreviewed nature, remains unclear. This study fills this gap by conducting a comprehensive scientometric analysis of patent citations to bioRxiv preprints submitted between 2013 and 2021, measuring and accessing the contribution of preprints in accelerating knowledge transfer from science to technology. Our findings reveal a growing trend of patent citations to bioRxiv preprints, with a notable surge in 2020, primarily driven by the COVID-19 pandemic. Preprints play a critical role in accelerating innovation, not only expedite the dissemination of scientific knowledge into technological innovation but also enhance the visibility of early research results in the patenting process, while journals remain essential for academic rigor and reliability. The substantial number of post-online-publication patent citations highlights the critical role of the open science model-particularly the "open access" effect of preprints-in amplifying the impact of science on technological innovation. This study provides empirical evidence that open science policies encouraging the early sharing of research outputs, such as preprints, contribute to more efficient linkage between science and technology, suggesting an acceleration in the pace of innovation, higher innovation quality, and economic benefits.

cs.DL↗

arXiv2025

Bridging the Gap between Hardware Fuzzing and Industrial Verification

As hardware design complexity increases, hardware fuzzing emerges as a promising tool for automating the verification process. However, a significant gap still exists before it can be applied in industry. This paper aims to summarize the current progress of hardware fuzzing from an industry-use perspective and propose solutions to bridge the gap between hardware fuzzing and industrial verification. First, we review recent hardware fuzzing methods and analyze their compatibilities with industrial verification. We establish criteria to assess whether a hardware fuzzing approach is compatible. Second, we examine whether current verification tools can efficiently support hardware fuzzing. We identify the bottlenecks in hardware fuzzing performance caused by insufficient support from the industrial environment. To overcome the bottlenecks, we propose a prototype, HwFuzzEnv, providing the necessary support for hardware fuzzing. With this prototype, the previous hardware fuzzing method can achieve a several hundred times speedup in industrial settings. Our work could serve as a reference for EDA companies, encouraging them to enhance their tools to support hardware fuzzing efficiently in industrial verification.

cs.CR↗

arXiv2024

SAN: Structure-Aware Network for Complex and Long-tailed Chinese Text Recognition

In text recognition, complex glyphs and tail classes have always been factors affecting model performance. Specifically for Chinese text recognition, the lack of shape-awareness can lead to confusion among close complex characters. Since such characters are often tail classes that appear less frequently in the training-set, making it harder for the model to capture its shape information. Hence in this work, we propose a structure-aware network utilizing the hierarchical composition information to improve the recognition performance of complex characters. Implementation-wise, we first propose an auxiliary radical branch and integrate it into the base recognition network as a regularization term, which distills hierarchical composition information into the feature extractor. A Tree-Similarity-based weighting mechanism is then proposed to further utilize the depth information in the hierarchical representation. Experiments demonstrate that the proposed approach can significantly improve the performances of complex characters and tail characters, yielding a better overall performance. Code is available at https://github.com/Levi-ZJY/SAN.

cs.CV↗

arXiv2024

Biodynamic Analysis of Alpine Skiing with a Skier-Ski-Snow Interaction Model

This study establishes a skier-ski-snow interaction (SSSI) model that integrates a 3D full-body musculoskeletal model, a flexible ski model, a ski-snow contact model, and an air resistance model. An experimental method is developed to collect kinematic and kinetic data using IMUs, GPS, and plantar pressure measurement insoles, which are cost-effective and capable of capturing motion in large-scale field conditions. The ski-snow interaction parameters are optimized for dynamic alignment with snow conditions and individual turning techniques. Forward-inverse dynamics simulation is performed using only the skier's posture as model input and leaving the translational degrees of freedom (DOFs) between the pelvis and the ground unconstrained. The effectiveness of our model is further verified by comparing the simulated results with the collected GPS and plantar pressure data. The correlation coefficient between the simulated ski-snow contact force and the measured plantar pressure data is 0.964, and the error between the predicted motion trajectory and GPS data is 0.7%. By extracting kinematic and kinetic parameters from skiers of different skill levels, quantitative performance analysis helps quantify ski training. The SSSI model with the parameter optimization algorithm of the ski-snow interaction allows for the description of skiing characteristics across varied snow conditions and different turning techniques, such as carving and skidding. Our research advances the understanding of alpine skiing dynamics, informing the development of training programs and facility designs to enhance athlete performance and safety.

physics.soc-ph↗

arXiv2024

Video-Language Alignment via Spatio-Temporal Graph Transformer

Video-language alignment is a crucial multi-modal task that benefits various downstream applications, e.g., video-text retrieval and video question answering. Existing methods either utilize multi-modal information in video-text pairs or apply global and local alignment techniques to promote alignment precision. However, these methods often fail to fully explore the spatio-temporal relationships among vision tokens within video and across different video-text pairs. In this paper, we propose a novel Spatio-Temporal Graph Transformer module to uniformly learn spatial and temporal contexts for video-language alignment pre-training (dubbed STGT). Specifically, our STGT combines spatio-temporal graph structure information with attention in transformer block, effectively utilizing the spatio-temporal contexts. In this way, we can model the relationships between vision tokens, promoting video-text alignment precision for benefiting downstream tasks. In addition, we propose a self-similarity alignment loss to explore the inherent self-similarity in the video and text. With the initial optimization achieved by contrastive learning, it can further promote the alignment accuracy between video and text. Experimental results on challenging downstream tasks, including video-text retrieval and video question answering, verify the superior performance of our method.

cs.CV↗

arXiv2024

Arbitrary Time Information Modeling via Polynomial Approximation for Temporal Knowledge Graph Embedding

Distinguished from traditional knowledge graphs (KGs), temporal knowledge graphs (TKGs) must explore and reason over temporally evolving facts adequately. However, existing TKG approaches still face two main challenges, i.e., the limited capability to model arbitrary timestamps continuously and the lack of rich inference patterns under temporal constraints. In this paper, we propose an innovative TKGE method (PTBox) via polynomial decomposition-based temporal representation and box embedding-based entity representation to tackle the above-mentioned problems. Specifically, we decompose time information by polynomials and then enhance the model's capability to represent arbitrary timestamps flexibly by incorporating the learnable temporal basis tensor. In addition, we model every entity as a hyperrectangle box and define each relation as a transformation on the head and tail entity boxes. The entity boxes can capture complex geometric structures and learn robust representations, improving the model's inductive capability for rich inference patterns. Theoretically, our PTBox can encode arbitrary time information or even unseen timestamps while capturing rich inference patterns and higher-arity relations of the knowledge base. Extensive experiments on real-world datasets demonstrate the effectiveness of our method.

cs.AI↗

arXiv2024

Transformer-based Reasoning for Learning Evolutionary Chain of Events on Temporal Knowledge Graph

Temporal Knowledge Graph (TKG) reasoning often involves completing missing factual elements along the timeline. Although existing methods can learn good embeddings for each factual element in quadruples by integrating temporal information, they often fail to infer the evolution of temporal facts. This is mainly because of (1) insufficiently exploring the internal structure and semantic relationships within individual quadruples and (2) inadequately learning a unified representation of the contextual and temporal correlations among different quadruples. To overcome these limitations, we propose a novel Transformer-based reasoning model (dubbed ECEformer) for TKG to learn the Evolutionary Chain of Events (ECE). Specifically, we unfold the neighborhood subgraph of an entity node in chronological order, forming an evolutionary chain of events as the input for our model. Subsequently, we utilize a Transformer encoder to learn the embeddings of intra-quadruples for ECE. We then craft a mixed-context reasoning module based on the multi-layer perceptron (MLP) to learn the unified representations of inter-quadruples for ECE while accomplishing temporal knowledge reasoning. In addition, to enhance the timeliness of the events, we devise an additional time prediction task to complete effective temporal information within the learned unified representation. Extensive experiments on six benchmark datasets verify the state-of-the-art performance and the effectiveness of our method.

cs.AI↗

arXiv2024

Inverse-like Antagonistic Scene Text Spotting via Reading-Order Estimation and Dynamic Sampling

Scene text spotting is a challenging task, especially for inverse-like scene text, which has complex layouts, e.g., mirrored, symmetrical, or retro-flexed. In this paper, we propose a unified end-to-end trainable inverse-like antagonistic text spotting framework dubbed IATS, which can effectively spot inverse-like scene texts without sacrificing general ones. Specifically, we propose an innovative reading-order estimation module (REM) that extracts reading-order information from the initial text boundary generated by an initial boundary module (IBM). To optimize and train REM, we propose a joint reading-order estimation loss consisting of a classification loss, an orthogonality loss, and a distribution loss. With the help of IBM, we can divide the initial text boundary into two symmetric control points and iteratively refine the new text boundary using a lightweight boundary refinement module (BRM) for adapting to various shapes and scales. To alleviate the incompatibility between text detection and recognition, we propose a dynamic sampling module (DSM) with a thin-plate spline that can dynamically sample appropriate features for recognition in the detected text region. Without extra supervision, the DSM can proactively learn to sample appropriate features for text recognition through the gradient returned by the recognition module. Extensive experiments on both challenging scene text and inverse-like scene text datasets demonstrate that our method achieves superior performance both on irregular and inverse-like text spotting.

cs.CV↗

arXiv2023

Regression-Oriented Knowledge Distillation for Lightweight Ship Orientation Angle Prediction with Optical Remote Sensing Images

Ship orientation angle prediction (SOAP) with optical remote sensing images is an important image processing task, which often relies on deep convolutional neural networks (CNNs) to make accurate predictions. This paper proposes a novel framework to reduce the model sizes and computational costs of SOAP models without harming prediction accuracy. First, a new SOAP model called Mobile-SOAP is designed based on MobileNetV2, achieving state-of-the-art prediction accuracy. Four tiny SOAP models are also created by replacing the convolutional blocks in Mobile-SOAP with four small-scale networks, respectively. Then, to transfer knowledge from Mobile-SOAP to four lightweight models, we propose a novel knowledge distillation (KD) framework termed SOAP-KD consisting of a novel feature-based guidance loss and an optimized synthetic samples-based knowledge transfer mechanism. Lastly, extensive experiments on the FGSC-23 dataset confirm the superiority of Mobile-SOAP over existing models and also demonstrate the effectiveness of SOAP-KD in improving the prediction performance of four specially designed tiny models. Notably, by using SOAP-KD, the test mean absolute error of the ShuffleNetV2x1.0-based model is only 8% higher than that of Mobile-SOAP, but its number of parameters and multiply-accumulate operations (MACs) are respectively 61.6% and 60.8% less.

cs.CV↗

arXiv2023

Ion steric effect induces giant enhancement of thermoelectric conversion in electrolyte-filled nanochannels

Ionic thermoelectricity in nanochannels has received increasing attention because of its advantages such as high Seebeck coefficient and low cost. However, most studies have focused on dilute simple electrolytes that neglect the effects of finite ion sizes and short-range electrostatic correlation. Here, we reveal a new thermoelectric mechanism arising from the coupling of ion steric effect due to finite ion sizes and ion thermodiffusion in electric double layers, using both theoretical and numerical methods. We show that this mechanism can significantly enhance the thermoelectric response in nanoconfined electrolytes, depending on the properties of electrolytes and nanochannels. Compared to the previously known mechanisms, the new mechanism can increase the Seebeck coefficient by 100\% or even one order of magnitude enhancement under optimal conditions. Moreover, we demonstrate that the short-range electrostatic correlation can help preserve the Seebeck coefficient enhancement in weaker confinement or in more concentrated electrolytes.

cond-mat.soft↗

arXiv2022

Excitonic density-waves, bi-excitons and orbital selective pairing in two-orbital correlated chains

We present a comprehensive study of a one-dimensional two-orbital model at and below quarter-filling that realizes a number of unconventional phases. In particular, we find an excitonic density wave in which excitons quasi-condense with finite center of mass momentum and an order parameter that changes phase with wave-vector $Q$. In this phase, excitons behave as hard-core bosons without charge order. In addition, excitons can pair to form bi-excitons in a state that is close to a charge density-wave instability. When pairing dominates over the inter-orbital repulsion, we encounter a regime in which one orbital is metallic, while the other forms a spin gapped superconductor, a genuine orbital selective paired state. All these results are supported by both, analytical and numerical calculations. By assuming a quasi-classical approximation, we solve the three-body hole-electron-spinon problem and show that excitons are held together by forming a bound state with spinons. In order to preserve the antiferromagnetic background, excitons acquire a dispersion that has a minimum away from $k=0$. The full characterization of the different phases is obtained by means of extensive density matrix renormalization group calculations.

cond-mat.str-el↗