arXiv subjects

Yu Zhao

Publications and source records attributed to Yu Zhao.

At least 127 records · Page 7Linked to original sources

arXiv2025

Identifying polycentric urban structure using the minimum cycle basis of road network as building blocks

In a graph, the minimum cycle bases are a set of linearly independent cycles that can be used to represent any cycle within that cycle space of graph. These bases are useful in various contexts, including the intricate analysis of electrical networks, structural engineering endeavors, chemical processes and surface reconstruction techniques etc. This study focuses on six cities in China to explore the topological characteristics, the centrality of nodes and robustness of urban road networks based on motif and minimum cycle bases. Some interesting conclusions are obtained: the frequency of motifs containing cycles exceeds that of random networks with equivalent degree sequences; the frequency distribution of minimum cycle's length and surface areas obey the power-law distribution. The cycle contribution rate is introduced to investigate the centrality of nodes within road networks, and has a significant impact on the total number of cycles in the robustness analysis. Finally, we construct two types of cycle-based dual networks for urban road networks by representing cycles as nodes and establishing edges between two cycles sharing a common node and edge respectively. The results show that cycle-based dual networks exhibit small-world and scale-free properties.

physics.soc-ph↗

arXiv2025

LMM4LMM: Benchmarking and Evaluating Large-multimodal Image Generation with LMMs

Recent breakthroughs in large multimodal models (LMMs) have significantly advanced both text-to-image (T2I) generation and image-to-text (I2T) interpretation. However, many generated images still suffer from issues related to perceptual quality and text-image alignment. Given the high cost and inefficiency of manual evaluation, an automatic metric that aligns with human preferences is desirable. To this end, we present EvalMi-50K, a comprehensive dataset and benchmark for evaluating large-multimodal image generation, which features (i) comprehensive tasks, encompassing 2,100 extensive prompts across 20 fine-grained task dimensions, and (ii) large-scale human-preference annotations, including 100K mean-opinion scores (MOSs) and 50K question-answering (QA) pairs annotated on 50,400 images generated from 24 T2I models. Based on EvalMi-50K, we propose LMM4LMM, an LMM-based metric for evaluating large multimodal T2I generation from multiple dimensions including perception, text-image correspondence, and task-specific accuracy. Extensive experimental results show that LMM4LMM achieves state-of-the-art performance on EvalMi-50K, and exhibits strong generalization ability on other AI-generated image evaluation benchmark datasets, manifesting the generality of both the EvalMi-50K dataset and LMM4LMM metric. Both EvalMi-50K and LMM4LMM will be released at https://github.com/IntMeGroup/LMM4LMM.

cs.CV↗

arXiv2025

Noiser: Bounded Input Perturbations for Attributing Large Language Models

Feature attribution (FA) methods are common post-hoc approaches that explain how Large Language Models (LLMs) make predictions. Accordingly, generating faithful attributions that reflect the actual inner behavior of the model is crucial. In this paper, we introduce Noiser, a perturbation-based FA method that imposes bounded noise on each input embedding and measures the robustness of the model against partially noised input to obtain the input attributions. Additionally, we propose an answerability metric that employs an instructed judge model to assess the extent to which highly scored tokens suffice to recover the predicted output. Through a comprehensive evaluation across six LLMs and three tasks, we demonstrate that Noiser consistently outperforms existing gradient-based, attention-based, and perturbation-based FA methods in terms of both faithfulness and answerability, making it a robust and effective approach for explaining language model predictions.

cs.CL↗

arXiv2025

A method for reversing the laser modulation in a Storage ring

The pursuit of coherent radiation generation remains a key direction in the advancement of storage ring light sources. Despite the potential of laser modulation in achieving this goal, it leads to a significant decline in the quality of the electron beam. Efforts to mitigate this decline have resulted in the proposal of demodulation schemes. However, implementing modulation and demodulation within the storage ring presents significant challenges due to dynamical and spatial constraints within straight sections. In this study, we propose a straightforward and easily implementable method for achieving reversible laser modulation in a storage ring. Notably, our approach circumvents the need for special storage ring requirements, such as lengthy straight sections or bypass section. Simulation results demonstrate a substantial restoration of beam quality following demodulation. This innovative scheme holds great promise for the realization of high repetition rate coherent storage ring light sources.

physics.acc-ph↗

arXiv2025

TAU: Modeling Temporal Consistency Through Temporal Attentive U-Net for PPG Peak Detection

Photoplethysmography (PPG) sensors have been widely used in consumer wearable devices to monitor heart rates (HR) and heart rate variability (HRV). Despite the prevalence, PPG signals can be contaminated by motion artifacts induced from daily activities. Existing approaches mainly use the amplitude information to perform PPG peak detection. However, these approaches cannot accurately identify peaks, since motion artifacts may bring random and significant amplitude variations. To improve the performance of PPG peak detection, the time information can be used. Specifically, heart rates exhibit temporal consistency that consecutive heartbeat intervals in a normal person can have limited variations. To leverage the temporal consistency, we propose the Temporal Attentive U-Net, i.e., TAU, to accurately detect peaks from PPG signals. In TAU, we design a time module that encodes temporal consistency in temporal embeddings. We integrate the amplitude information with temporal embeddings using the attention mechanism to estimate peak labels. Our experimental results show that TAU outperforms eleven baselines on heart rate estimation by more than 22.4%. Our TAU model achieves the best performance across various Signal-to-Noise Ratio (SNR) levels. Moreover, we achieve Pearson correlation coefficients higher than 0.9 (p < 0.01) on estimating HRV features from low-noise-level PPG signals.

cs.LG↗

arXiv2025

StratIncon Detector: Analyzing Strategy Inconsistencies Between Real-Time Strategy and Preferred Professional Strategy in MOBA Esports

MOBA (Multiplayer Online Battle Arena) games require a delicate interplay of strategic planning and real-time decision-making, particularly in professional esports, where players exhibit varying levels of skill and strategic insight. While team strategies have been widely studied, analyzing inconsistencies in professional matches remains a significant challenge. The complexity lies in defining and quantifying the difference between real-time and preferred professional strategies, as well as understanding the disparities between them. Establishing direct causal links between specific strategic decisions and game outcomes also demands a comprehensive analysis of the entire match progression. To tackle these challenges, we present the StratIncon Detector, a visual analytics system designed to assist professional players and coaches in efficiently identifying strategic inconsistencies. The system detects real-time strategies, predicts preferred professional strategies, extracts relevant human factors, and uncovers their impact on subsequent game phases. Findings from a case study, a user study with 24 participants, and expert interviews suggest that, compared to traditional methods, the StratIncon Detector enables users to more comprehensively and efficiently identify inconsistencies, infer their causes, evaluate their effects on subsequent game outcomes, and gain deeper insights into team collaboration-ultimately enhancing future teamwork.

cs.HC↗

arXiv2025

Identifying Evidence Subgraphs for Financial Risk Detection via Graph Counterfactual and Factual Reasoning

Company financial risks pose a significant threat to personal wealth and national economic stability, stimulating increasing attention towards the development of efficient andtimely methods for monitoring them. Current approaches tend to use graph neural networks (GNNs) to model the momentum spillover effect of risks. However, due to the black-box nature of GNNs, these methods leave much to be improved for precise and reliable explanations towards company risks. In this paper, we propose CF3, a novel Counterfactual and Factual learning method for company Financial risk detection, which generates evidence subgraphs on company knowledge graphs to reliably detect and explain company financial risks. Specifically, we first propose a meta-path attribution process based on Granger causality, selecting the meta-paths most relevant to the target node labels to construct an attribution subgraph. Subsequently, we propose anedge-type-aware graph generator to identify important edges, and we also devise a layer-based feature masker to recognize crucial node features. Finally, we utilize counterfactual-factual reasoning and a loss function based on attribution subgraphs to jointly guide the learning of the graph generator and feature masker. Extensive experiments on three real-world datasets demonstrate the superior performance of our method compared to state-of-the-art approaches in the field of financial risk detection.

cs.CE↗

arXiv2025

Closed-Loop Open-Vocabulary Mobile Manipulation with GPT-4V

Autonomous robot navigation and manipulation in open environments require reasoning and replanning with closed-loop feedback. In this work, we present COME-robot, the first closed-loop robotic system utilizing the GPT-4V vision-language foundation model for open-ended reasoning and adaptive planning in real-world scenarios.COME-robot incorporates two key innovative modules: (i) a multi-level open-vocabulary perception and situated reasoning module that enables effective exploration of the 3D environment and target object identification using commonsense knowledge and situated information, and (ii) an iterative closed-loop feedback and restoration mechanism that verifies task feasibility, monitors execution success, and traces failure causes across different modules for robust failure recovery. Through comprehensive experiments involving 8 challenging real-world mobile and tabletop manipulation tasks, COME-robot demonstrates a significant improvement in task success rate (~35%) compared to state-of-the-art methods. We further conduct comprehensive analyses to elucidate how COME-robot's design facilitates failure recovery, free-form instruction following, and long-horizon task planning.

cs.RO↗

arXiv2025

CNsum:Automatic Summarization for Chinese News Text

Obtaining valuable information from massive data efficiently has become our research goal in the era of Big Data. Text summarization technology has been continuously developed to meet this demand. Recent work has also shown that transformer-based pre-trained language models have achieved great success on various tasks in Natural Language Processing (NLP). Aiming at the problem of Chinese news text summary generation and the application of Transformer structure on Chinese, this paper proposes a Chinese news text summarization model (CNsum) based on Transformer structure, and tests it on Chinese datasets such as THUCNews. The results of the conducted experiments show that CNsum achieves better ROUGE score than the baseline models, which verifies the outperformance of the model.

cs.CL↗

arXiv2025

CoinRobot: Generalized End-to-end Robotic Learning for Physical Intelligence

Physical intelligence holds immense promise for advancing embodied intelligence, enabling robots to acquire complex behaviors from demonstrations. However, achieving generalization and transfer across diverse robotic platforms and environments requires careful design of model architectures, training strategies, and data diversity. Meanwhile existing systems often struggle with scalability, adaptability to heterogeneous hardware, and objective evaluation in real-world settings. We present a generalized end-to-end robotic learning framework designed to bridge this gap. Our framework introduces a unified architecture that supports cross-platform adaptability, enabling seamless deployment across industrial-grade robots, collaborative arms, and novel embodiments without task-specific modifications. By integrating multi-task learning with streamlined network designs, it achieves more robust performance than conventional approaches, while maintaining compatibility with varying sensor configurations and action spaces. We validate our framework through extensive experiments on seven manipulation tasks. Notably, Diffusion-based models trained in our framework demonstrated superior performance and generalizability compared to the LeRobot framework, achieving performance improvements across diverse robotic platforms and environmental conditions.

cs.RO↗

arXiv2025

Q-Filters: Leveraging QK Geometry for Efficient KV Cache Compression

Autoregressive language models rely on a Key-Value (KV) Cache, which avoids re-computing past hidden states during generation, making it faster. As model sizes and context lengths grow, the KV Cache becomes a significant memory bottleneck, which calls for compression methods that limit its size during generation. In this paper, we discover surprising properties of Query (Q) and Key (K) vectors that allow us to efficiently approximate attention scores without computing the attention maps. We propose Q-Filters, a training-free KV Cache compression method that filters out less crucial Key-Value pairs based on a single context-agnostic projection. Contrarily to many alternatives, Q-Filters is compatible with FlashAttention, as it does not require direct access to attention weights. Experimental results in long-context settings demonstrate that Q-Filters is competitive with attention-based compression methods such as SnapKV in retrieval tasks while consistently outperforming efficient compression schemes such as Streaming-LLM in generation setups. Notably, Q-Filters achieves a 99% accuracy in the needle-in-a-haystack task with a x32 compression level while reducing the generation perplexity drop by up to 65% in text generation compared to Streaming-LLM.

cs.CL↗

arXiv2025

Monitoring AGNs with H$β$ Asymmetry. V. Long-term Variation and Evolution of the Broad H$β$ Emission-Line Profiles

The physical origins of the diverse emission-line asymmetries observed in the spectra of active galactic nuclei (AGNs) remain incompletely understood. Monitoring the temporal variations of line profiles offers a promising approach to investigating the underlying physics. In this study, we present an analysis of the broad H$β$ emission line profiles of eight AGNs observed from the end of 2016 to May 2023 as part of the reverberation mapping campaign titled "Monitoring AGNs with H$β$ Asymmetry" (MAHA), utilizing data obtained from the Wyoming Infrared Observatory (WIRO) 2.3-meter telescope. We measure the temporal variations of line asymmetry, width, and central velocity shift for the eight objects. Our findings reveal that the variation in asymmetry is positively correlated with H$β$ flux in five of the eight objects, while the remaining objects exhibit negative or complex correlations. Furthermore, we observe anti-correlations between line width and H$β$ flux for most objects, indicating the presence of the "breathing" phenomenon in their H$β$ emission lines. In contrast, two objects demonstrate an "anti-breathing" phenomenon or complex behavior. We discuss the physical origins of the temporal variations in line profiles and propose the possibility of decomposing the variations in H$β$ asymmetry and width into components: one that corresponds to short-term variations in H$β$ flux and another that reflects long-term variations in continuum light curves, perhaps driven by radiation pressure.

astro-ph.GA↗

arXiv2025

Structured Packing in LLM Training Improves Long Context Utilization

Recent advancements in long-context large language models have attracted significant attention, yet their practical applications often suffer from suboptimal context utilization. This study investigates structuring training data to enhance semantic interdependence, demonstrating that this approach effectively improves context utilization. To this end, we introduce the Structured Packing for Long Context (SPLiCe) method, which utilizes retrieval to collate mutually relevant documents into long and coherent training examples. We validate SPLiCe empirically across models of varying sizes -- 3B, 7B, and 13B -- achieving improved performance in long-context tasks, such as Qasper and HotpotQA. Remarkably, even brief fine-tuning with SPLiCe is sufficient to realize these benefits. Additionally, SPLiCe effectively mitigates the lost-in-middle phenomenon often observed in large models. Our comprehensive analysis of SPLiCe explores its design choices and reveals intriguing transfer effects; for instance, training on programming code enhances performance on natural language tasks.

cs.CL↗

arXiv2025

Multimodal Graph-Based Variational Mixture of Experts Network for Zero-Shot Multimodal Information Extraction

Multimodal information extraction on social media is a series of fundamental tasks to construct the multimodal knowledge graph. The tasks aim to extract the structural information in free texts with the incorporate images, including: multimodal named entity typing and multimodal relation extraction. However, the growing number of multimodal data implies a growing category set and the newly emerged entity types or relations should be recognized without additional training. To address the aforementioned challenges, we focus on the zero-shot multimodal information extraction tasks which require using textual and visual modalities for recognizing unseen categories. Compared with text-based zero-shot information extraction models, the existing multimodal ones make the textual and visual modalities aligned directly and exploit various fusion strategies to improve their performances. But the existing methods ignore the fine-grained semantic correlation of text-image pairs and samples. Therefore, we propose the multimodal graph-based variational mixture of experts network (MG-VMoE) which takes the MoE network as the backbone and exploits it for aligning multimodal representations in a fine-grained way. Considering to learn informative representations of multimodal data, we design each expert network as a variational information bottleneck to process two modalities in a uni-backbone. Moreover, we also propose the multimodal graph-based virtual adversarial training to learn the semantic correlation between the samples. The experimental results on the two benchmark datasets demonstrate the superiority of MG-VMoE over the baselines.

cs.MM↗

arXiv2025

Grammar Induction from Visual, Speech and Text

Grammar Induction could benefit from rich heterogeneous signals, such as text, vision, and acoustics. In the process, features from distinct modalities essentially serve complementary roles to each other. With such intuition, this work introduces a novel \emph{unsupervised visual-audio-text grammar induction} task (named \textbf{VAT-GI}), to induce the constituent grammar trees from parallel images, text, and speech inputs. Inspired by the fact that language grammar natively exists beyond the texts, we argue that the text has not to be the predominant modality in grammar induction. Thus we further introduce a \emph{textless} setting of VAT-GI, wherein the task solely relies on visual and auditory inputs. To approach the task, we propose a visual-audio-text inside-outside recursive autoencoder (\textbf{VaTiora}) framework, which leverages rich modal-specific and complementary features for effective grammar parsing. Besides, a more challenging benchmark data is constructed to assess the generalization ability of VAT-GI system. Experiments on two benchmark datasets demonstrate that our proposed VaTiora system is more effective in incorporating the various multimodal signals, and also presents new state-of-the-art performance of VAT-GI.

cs.CL↗

arXiv2025

On the peak height distribution of non-stationary Gaussian random fields: 1D general covariance and scale space

We study the peak height distribution of certain non-stationary Gaussian random fields. The explicit peak height distribution of smooth, non-stationary Gaussian processes in 1D with general covariance is derived. The formula is determined by two parameters, each of which has a clear statistical meaning. For multidimensional non-stationary Gaussian random fields, we generalize these results to the setting of scale space fields, which play an important role in peak detection by helping to handle peaks of different spatial extents. We demonstrate that these properties not only offer a better interpretation of the scale space field but also simplify the computation of the peak height distribution. Finally, two efficient numerical algorithms are proposed as a general solution for computing the peak height distribution of smooth multidimensional Gaussian random fields in applications.

stat.ME↗

arXiv2025

Utilizing Effective Dynamic Graph Learning to Shield Financial Stability from Risk Propagation

Financial risks can propagate across both tightly coupled temporal and spatial dimensions, posing significant threats to financial stability. Moreover, risks embedded in unlabeled data are often difficult to detect. To address these challenges, we introduce GraphShield, a novel approach with three key innovations: Enhanced Cross-Domain Infor mation Learning: We propose a dynamic graph learning module to improve information learning across temporal and spatial domains. Advanced Risk Recognition: By leveraging the clustering characteristics of risks, we construct a risk recognizing module to enhance the identification of hidden threats. Risk Propagation Visualization: We provide a visualization tool for quantifying and validating nodes that trigger widespread cascading risks. Extensive experiments on two real-world and two open-source datasets demonstrate the robust performance of our framework. Our approach represents a significant advancement in leveraging artificial intelligence to enhance financial stability, offering a powerful solution to mitigate the spread of risks within financial networks.

q-fin.RM↗

arXiv2025

Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering

Large language models (LLMs) can store a significant amount of factual knowledge in their parameters. However, their parametric knowledge may conflict with the information provided in the context -- this phenomenon, known as \emph{context-memory knowledge conflicts}, can lead to undesirable model behaviour, such as reliance on outdated or incorrect information. Analysing the internal activations of LLMs, we find that they can internally register the signals of knowledge conflict at mid-layers. Such signals allow us to detect whether a knowledge conflict occurs and use \emph{inference-time} intervention strategies to resolve it. In this work, we propose \textsc{SpARE}, a \emph{training-free} representation engineering method that uses pre-trained sparse auto-encoders (SAEs) to control the knowledge selection behaviour of LLMs. \textsc{SpARE} identifies the functional features that control the knowledge selection behaviours and applies them to edit the internal activations of LLMs at inference time. Our experimental results show that \textsc{SpARE} can effectively control the usage of either knowledge source to resolve knowledge conflict in open-domain question-answering tasks, surpassing existing representation engineering methods ($+10\%$) as well as contrastive decoding methods ($+15\%$).

cs.CL↗