arXiv subjects

Li Su

Publications and source records attributed to Li Su.

At least 37 records · Page 2Linked to original sources

arXiv2025

A signless Laplacian spectral Erdös-Stone-Simonovits theorem

The celebrated Erdős--Stone--Simonovits theorem states that $\mathrm{ex}(n,F)= \big(1-\frac{1}{χ(F)-1}+o(1) \big)\frac{n^{2}}{2}$, where $χ(F)$ is the chromatic number of $F$. In 2009, Nikiforov proved a spectral extension of the Erdős--Stone--Simonovits theorem in terms of the adjacency spectral radius. In this paper, we shall establish a unified extension in terms of the signless Laplacian spectral radius. Let $q(G)$ be the signless Laplacian spectral radius of $G$ and we denote $\mathrm{ex}_{q}(n,F) =\max \{q(G):|G|=n ~\mbox{and}~F\nsubseteq G\}$. It is known that the Erdős--Stone--Simonovits type result for the signless Laplacian spectral radius does not hold for even cycles. We prove that if $F$ is a graph with $χ(F)\geq 3$, then $\mathrm{ex}_{q}(n,F)=\big(1-\frac{1}{χ(F)-1}+o(1) \big)2n$. This solves a problem proposed by Li, Liu and Feng (2022), which gives an entirely satisfactory answer to the problem of estimating $\mathrm{ex}_q(n,F)$. Furthermore, it extends the aforementioned result of Erdős, Stone and Simonovits as well as the spectral result of Nikiforov. Our result indicates that the Erdős--Stone--Simonovits type result regarding the signless Laplacian spectral radius is valid in general.

math.CO↗

arXiv2025

Robust estimation of optimal dynamic treatment regimes with nonignorable missing covariates

Estimating optimal dynamic treatment regimes (DTRs) using observational data is often challenged by nonignorable missing covariates arsing from informative monitoring of patients in clinical practice. To address nonignorable missingness of pseudo-outcomes induced by nonignorable missing covariates, a weighted Q-learning approach using parametric Q-function models and a semiparametric missingness propensity model has recently been proposed. However, misspecification of parametric Q-functions at later stages of a DTR can propagate estimation errors to earlier stages via the pseudo-outcomes themselves and indirectly through biased estimation of the missingness propensity of the pseudo-outcomes. This robustness concern motivates us to develop a direct-search-based optimal DTR estimator built on a robust and efficient value estimator, where nonparametric methods are employed for treatment propensity and Q-function estimation, and inverse probability weighting is applied using missingness propensity estimated with the aid of nonresponse instrumental variables. Specifically, in our value estimator, we replace weights estimated by prediction models of treatment propensity with stable weights estimated by balancing covariate functions in a reproducing-kernel Hilbert space (RKHS). Augmented by Q-functions estimated by RKHS-based smoothing splines, our value estimator mitigates the misspecification risk of the weighted Q-learning approach while maintaining the efficiency gain from employing pseudo-outcomes in missing data scenarios. The asymptotic properties of the proposed estimator are derived, and simulations demonstrate its superior performance over weighted Q-learning under model misspecification. We apply the proposed methods to investigate the optimal fluid strategy for sepsis patients using data from the MIMIC database.

stat.ME↗

arXiv2025

An LLM-based Self-Evolving Security Framework for 6G Space-Air-Ground Integrated Networks

Recently emerged 6G space-air-ground integrated networks (SAGINs), which integrate satellites, aerial networks, and terrestrial communications, offer ubiquitous coverage for various mobile applications. However, the highly dynamic, open, and heterogeneous nature of SAGINs poses severe security issues. Forming a defense line of SAGINs suffers from two preliminary challenges: 1) accurately understanding massive unstructured multi-dimensional threat information to generate defense strategies against various malicious attacks, 2) rapidly adapting to potential unknown threats to yield more effective security strategies. To tackle the above two challenges, we propose a novel security framework for SAGINs based on Large Language Models (LLMs), which consists of two key ingredients LLM-6GNG and 6G-INST. Our proposed LLM-6GNG leverages refined chain-of-thought (CoT) reasoning and dynamic multi-agent mechanisms to analyze massive unstructured multi-dimensional threat data and generate comprehensive security strategies, thus addressing the first challenge. Our proposed 6G-INST relies on a novel self-evolving method to automatically update LLM-6GNG, enabling it to accommodate unknown threats under dynamic communication environments, thereby addressing the second challenge. Additionally, we prototype the proposed framework with ns-3, OpenAirInterface (OAI), and software-defined radio (SDR). Experiments on three benchmarks demonstrate the effectiveness of our framework. The results show that our framework produces highly accurate security strategies that remain robust against a variety of unknown attacks. We will release our code to contribute to the community.

cs.CR↗

arXiv2025

Exploring Hallucination of Large Multimodal Models in Video Understanding: Benchmark, Analysis and Mitigation

The hallucination of large multimodal models (LMMs), providing responses that appear correct but are actually incorrect, limits their reliability and applicability. This paper aims to study the hallucination problem of LMMs in video modality, which is dynamic and more challenging compared to static modalities like images and text. From this motivation, we first present a comprehensive benchmark termed HAVEN for evaluating hallucinations of LMMs in video understanding tasks. It is built upon three dimensions, i.e., hallucination causes, hallucination aspects, and question formats, resulting in 6K questions. Then, we quantitatively study 7 influential factors on hallucinations, e.g., duration time of videos, model sizes, and model reasoning, via experiments of 16 LMMs on the presented benchmark. In addition, inspired by recent thinking models like OpenAI o1, we propose a video-thinking model to mitigate the hallucinations of LMMs via supervised reasoning fine-tuning (SRFT) and direct preference optimization (TDPO)-- where SRFT enhances reasoning capabilities while TDPO reduces hallucinations in the thinking process. Extensive experiments and analyses demonstrate the effectiveness. Remarkably, it improves the baseline by 7.65% in accuracy on hallucination evaluation and reduces the bias score by 4.5%. The code and data are public at https://github.com/Hongcheng-Gao/HAVEN.

cs.CV↗

arXiv2025

BrainNet-MoE: Brain-Inspired Mixture-of-Experts Learning for Neurological Disease Identification

The Lewy body dementia (LBD) is the second most common neurodegenerative dementia after Alzheimer's disease (AD). Early differentiation between AD and LBD is crucial because they require different treatment approaches, but this is challenging due to significant clinical overlap, heterogeneity, complex pathogenesis, and the rarity of LBD. While recent advances in artificial intelligence (AI) demonstrate powerful learning capabilities and offer new hope for accurate diagnosis, existing methods primarily focus on designing "neural-level networks". Our work represents a pioneering effort in modeling system-level artificial neural network called BrainNet-MoE for brain modeling and diagnosing. Inspired by the brain's hierarchical organization of bottom-up sensory integration and top-down control, we design a set of disease-specific expert groups to process brain sub-network under different condition, A disease gate mechanism guides the specializa-tion of expert groups, while a transformer layer enables communication be-tween all sub-networks, generating a comprehensive whole-brain represen-tation for downstream disease classification. Experimental results show superior classification accuracy with interpretable insights into how brain sub-networks contribute to different neurodegenerative conditions.

cs.LG↗

arXiv2024

Computational Analysis of Yaredawi YeZema Silt in Ethiopian Orthodox Tewahedo Church Chants

Despite its musicological, cultural, and religious significance, the Ethiopian Orthodox Tewahedo Church (EOTC) chant is relatively underrepresented in music research. Historical records, including manuscripts, research papers, and oral traditions, confirm Saint Yared's establishment of three canonical EOTC chanting modes during the 6th century. This paper attempts to investigate the EOTC chants using music information retrieval (MIR) techniques. Among the research questions regarding the analysis and understanding of EOTC chants, Yaredawi YeZema Silt, namely the mode of chanting adhering to Saint Yared's standards, is of primary importance. Therefore, we consider the task of Yaredawi YeZema Silt classification in EOTC chants by introducing a new dataset and showcasing a series of classification experiments for this task. Results show that using the distribution of stabilized pitch contours as the feature representation on a simple neural network-based classifier becomes an effective solution. The musicological implications and insights of such results are further discussed through a comparative study with the previous ethnomusicology literature on EOTC chants. By making this dataset publicly accessible, we aim to promote future exploration and analysis of EOTC chants and highlight potential directions for further research, thereby fostering a deeper understanding and preservation of this unique spiritual and cultural heritage.

eess.AS↗

arXiv2024

Zema Dataset: A Comprehensive Study of Yaredawi Zema with a Focus on Horologium Chants

Computational music research plays a critical role in advancing music production, distribution, and understanding across various musical styles worldwide. Despite the immense cultural and religious significance, the Ethiopian Orthodox Tewahedo Church (EOTC) chants are relatively underrepresented in computational music research. This paper contributes to this field by introducing a new dataset specifically tailored for analyzing EOTC chants, also known as Yaredawi Zema. This work provides a comprehensive overview of a 10-hour dataset, 369 instances, creation, and curation process, including rigorous quality assurance measures. Our dataset has a detailed word-level temporal boundary and reading tone annotation along with the corresponding chanting mode label of audios. Moreover, we have also identified the chanting options associated with multiple chanting notations in the manuscript by annotating them accordingly. Our goal in making this dataset available to the public 1 is to encourage more research and study of EOTC chants, including lyrics transcription, lyric-to-audio alignment, and music generation tasks. Such research work will advance knowledge and efforts to preserve this distinctive liturgical music, a priceless cultural artifact for the Ethiopian people.

eess.AS↗

arXiv2024

Query-centric Audio-Visual Cognition Network for Moment Retrieval, Segmentation and Step-Captioning

Video has emerged as a favored multimedia format on the internet. To better gain video contents, a new topic HIREST is presented, including video retrieval, moment retrieval, moment segmentation, and step-captioning. The pioneering work chooses the pre-trained CLIP-based model for video retrieval, and leverages it as a feature extractor for other three challenging tasks solved in a multi-task learning paradigm. Nevertheless, this work struggles to learn the comprehensive cognition of user-preferred content, due to disregarding the hierarchies and association relations across modalities. In this paper, guided by the shallow-to-deep principle, we propose a query-centric audio-visual cognition (QUAG) network to construct a reliable multi-modal representation for moment retrieval, segmentation and step-captioning. Specifically, we first design the modality-synergistic perception to obtain rich audio-visual content, by modeling global contrastive alignment and local fine-grained interaction between visual and audio modalities. Then, we devise the query-centric cognition that uses the deep-level query to perform the temporal-channel filtration on the shallow-level audio-visual representation. This can cognize user-preferred content and thus attain a query-centric audio-visual representation for three tasks. Extensive experiments show QUAG achieves the SOTA results on HIREST. Further, we test QUAG on the query-based video summarization task and verify its good generalization.

cs.CV↗

arXiv2024

Weighted Q-learning for optimal dynamic treatment regimes with nonignorable missing covariates

Dynamic treatment regimes (DTRs) formalize medical decision-making as a sequence of rules for different stages, mapping patient-level information to recommended treatments. In practice, estimating an optimal DTR using observational data from electronic medical record (EMR) databases can be complicated by nonignorable missing covariates resulting from informative monitoring of patients. Since complete case analysis can provide consistent estimation of outcome model parameters under the assumption of outcome-independent missingness, Q-learning is a natural approach to accommodating nonignorable missing covariates. However, the backward induction algorithm used in Q-learning can introduce challenges, as nonignorable missing covariates at later stages can result in nonignorable missing pseudo-outcomes at earlier stages, leading to suboptimal DTRs, even if the longitudinal outcome variables are fully observed. To address this unique missing data problem in DTR settings, we propose two weighted Q-learning approaches where inverse probability weights for missingness of the pseudo-outcomes are obtained through estimating equations with valid nonresponse instrumental variables or sensitivity analysis. The asymptotic properties of the weighted Q-learning estimators are derived, and the finite-sample performance of the proposed methods is evaluated and compared with alternative methods through extensive simulation studies. Using EMR data from the Medical Information Mart for Intensive Care database, we apply the proposed methods to investigate the optimal fluid strategy for sepsis patients in intensive care units.

stat.ME↗

arXiv2024

Distortion Recovery: A Two-Stage Method for Guitar Effect Removal

Removing audio effects from electric guitar recordings makes it easier for post-production and sound editing. An audio distortion recovery model not only improves the clarity of the guitar sounds but also opens up new opportunities for creative adjustments in mixing and mastering. While progress have been made in creating such models, previous efforts have largely focused on synthetic distortions that may be too simplistic to accurately capture the complexities seen in real-world recordings. In this paper, we tackle the task by using a dataset of guitar recordings rendered with commercial-grade audio effect VST plugins. Moreover, we introduce a novel two-stage methodology for audio distortion recovery. The idea is to firstly process the audio signal in the Mel-spectrogram domain in the first stage, and then use a neural vocoder to generate the pristine original guitar sound from the processed Mel-spectrogram in the second stage. We report a set of experiments demonstrating the effectiveness of our approach over existing methods, through both subjective and objective evaluation metrics.

cs.SD↗

arXiv2024

Distractors-Immune Representation Learning with Cross-modal Contrastive Regularization for Change Captioning

Change captioning aims to succinctly describe the semantic change between a pair of similar images, while being immune to distractors (illumination and viewpoint changes). Under these distractors, unchanged objects often appear pseudo changes about location and scale, and certain objects might overlap others, resulting in perturbational and discrimination-degraded features between two images. However, most existing methods directly capture the difference between them, which risk obtaining error-prone difference features. In this paper, we propose a distractors-immune representation learning network that correlates the corresponding channels of two image representations and decorrelates different ones in a self-supervised manner, thus attaining a pair of stable image representations under distractors. Then, the model can better interact them to capture the reliable difference features for caption generation. To yield words based on the most related difference features, we further design a cross-modal contrastive regularization, which regularizes the cross-modal alignment by maximizing the contrastive alignment between the attended difference features and generated words. Extensive experiments show that our method outperforms the state-of-the-art methods on four public datasets. The code is available at https://github.com/tuyunbin/DIRL.

cs.CV↗

arXiv2024

Inference procedures in sequential trial emulation with survival outcomes: comparing confidence intervals based on the sandwich variance estimator, bootstrap and jackknife

Sequential trial emulation (STE) is an approach to estimating causal treatment effects by emulating a sequence of target trials from observational data. In STE, inverse probability weighting is commonly utilised to address time-varying confounding and/or dependent censoring. Then structural models for potential outcomes are applied to the weighted data to estimate treatment effects. For inference, the simple sandwich variance estimator is popular but conservative, while nonparametric bootstrap is computationally expensive, and a more efficient alternative, linearised estimating function (LEF) bootstrap, has not been adapted to STE. We evaluated the performance of various methods for constructing confidence intervals (CIs) of marginal risk differences in STE with survival outcomes by comparing the coverage of CIs based on nonparametric/LEF bootstrap, jackknife, and the sandwich variance estimator through simulations. LEF bootstrap CIs demonstrated the best coverage with small/moderate sample sizes, low event rates and low treatment prevalence, which were the motivating scenarios for STE. They were less affected by treatment group imbalance and faster to compute than nonparametric bootstrap CIs. With large sample sizes and medium/high event rates, the sandwich-variance-estimator-based CIs had the best coverage and were the fastest to compute. These findings offer guidance in constructing CIs in causal survival analysis using STE.

stat.ME↗

arXiv2024

A Study on Synthesizing Expressive Violin Performances: Approaches and Comparisons

Expressive music synthesis (EMS) for violin performance is a challenging task due to the disagreement among music performers in the interpretation of expressive musical terms (EMTs), scarcity of labeled recordings, and limited generalization ability of the synthesis model. These challenges create trade-offs between model effectiveness, diversity of generated results, and controllability of the synthesis system, making it essential to conduct a comparative study on EMS model design. This paper explores two violin EMS approaches. The end-to-end approach is a modification of a state-of-the-art text-to-speech generator. The parameter-controlled approach is based on a simple parameter sampling process that can render note lengths and other parameters compatible with MIDI-DDSP. We study these two approaches (in total, three model variants) through objective and subjective experiments and discuss several key issues of EMS based on the results.

cs.SD↗

arXiv2024

Accommodating informative visit times for analysing irregular longitudinal data: a sensitivity analysis approach with balancing weights estimators

Irregular longitudinal data with informative visit times arise when patients' visits are partly driven by concurrent disease outcomes. However, existing methods such as inverse intensity weighting (IIW), often overlook or have not adequately assess the influence of informative visit times on estimation and inference. Based on novel balancing weights estimators, we propose a new sensitivity analysis approach to addressing informative visit times within the IIW framework. The balancing weights are obtained by balancing observed history variable distributions over time and including a selection function with specified sensitivity parameters to characterise the additional influence of the concurrent outcome on the visit process. A calibration procedure is proposed to anchor the range of the sensitivity parameters to the amount of variation in the visit process that could be additionally explained by the concurrent outcome given the observed history and time. Simulations demonstrate that our balancing weights estimators outperform existing weighted estimators for robustness and efficiency. We provide an R Markdown tutorial of the proposed methods and apply them to analyse data from a clinic-based cohort of psoriatic arthritis.

stat.ME↗

arXiv2024

MOSA: Music Motion with Semantic Annotation Dataset for Cross-Modal Music Processing

In cross-modal music processing, translation between visual, auditory, and semantic content opens up new possibilities as well as challenges. The construction of such a transformative scheme depends upon a benchmark corpus with a comprehensive data infrastructure. In particular, the assembly of a large-scale cross-modal dataset presents major challenges. In this paper, we present the MOSA (Music mOtion with Semantic Annotation) dataset, which contains high quality 3-D motion capture data, aligned audio recordings, and note-by-note semantic annotations of pitch, beat, phrase, dynamic, articulation, and harmony for 742 professional music performances by 23 professional musicians, comprising more than 30 hours and 570 K notes of data. To our knowledge, this is the largest cross-modal music dataset with note-level annotations to date. To demonstrate the usage of the MOSA dataset, we present several innovative cross-modal music information retrieval (MIR) and musical content generation tasks, including the detection of beats, downbeats, phrase, and expressive contents from audio, video and motion data, and the generation of musicians' body motion from given music audio. The dataset and codes are available alongside this publication (https://github.com/yufenhuang/MOSA-Music-mOtion-and-Semantic-Annotation-dataset).

cs.SD↗

arXiv2024

Context-aware Difference Distilling for Multi-change Captioning

Multi-change captioning aims to describe complex and coupled changes within an image pair in natural language. Compared with single-change captioning, this task requires the model to have higher-level cognition ability to reason an arbitrary number of changes. In this paper, we propose a novel context-aware difference distilling (CARD) network to capture all genuine changes for yielding sentences. Given an image pair, CARD first decouples context features that aggregate all similar/dissimilar semantics, termed common/difference context features. Then, the consistency and independence constraints are designed to guarantee the alignment/discrepancy of common/difference context features. Further, the common context features guide the model to mine locally unchanged features, which are subtracted from the pair to distill locally difference features. Next, the difference context features augment the locally difference features to ensure that all changes are distilled. In this way, we obtain an omni-representation of all changes, which is translated into linguistic sentences by a transformer decoder. Extensive experiments on three public datasets show CARD performs favourably against state-of-the-art methods.The code is available at https://github.com/tuyunbin/CARD.

cs.CV↗

arXiv2024

BEAST: Online Joint Beat and Downbeat Tracking Based on Streaming Transformer

Many deep learning models have achieved dominant performance on the offline beat tracking task. However, online beat tracking, in which only the past and present input features are available, still remains challenging. In this paper, we propose BEAt tracking Streaming Transformer (BEAST), an online joint beat and downbeat tracking system based on the streaming Transformer. To deal with online scenarios, BEAST applies contextual block processing in the Transformer encoder. Moreover, we adopt relative positional encoding in the attention layer of the streaming Transformer encoder to capture relative timing position which is critically important information in music. Carrying out beat and downbeat experiments on benchmark datasets for a low latency scenario with maximum latency under 50 ms, BEAST achieves an F1-measure of 80.04% in beat and 46.78% in downbeat, which is a substantial improvement of about 5 percentage points over the state-of-the-art online beat tracking model.

cs.SD↗

arXiv2024

TrialEmulation: An R Package to Emulate Target Trials for Causal Analysis of Observational Time-to-event Data

Randomised controlled trials (RCTs) are regarded as the gold standard for estimating causal treatment effects on health outcomes. However, RCTs are not always feasible, because of time, budget or ethical constraints. Observational data such as those from electronic health records (EHRs) offer an alternative way to estimate the causal effects of treatments. Recently, the `target trial emulation' framework was proposed by Hernan and Robins (2016) to provide a formal structure for estimating causal treatment effects from observational data. To promote more widespread implementation of target trial emulation in practice, we develop the R package TrialEmulation to emulate a sequence of target trials using observational time-to-event data, where individuals who start to receive treatment and those who have not been on the treatment at the baseline of the emulated trials are compared in terms of their risks of an outcome event. Specifically, TrialEmulation provides (1) data preparation for emulating a sequence of target trials, (2) calculation of the inverse probability of treatment and censoring weights to handle treatment switching and dependent censoring, (3) fitting of marginal structural models for the time-to-event outcome given baseline covariates, (4) estimation and inference of marginal intention to treat and per-protocol effects of the treatment in terms of marginal risk differences between treated and untreated for a user-specified target trial population. In particular, TrialEmulation can accommodate large data sets (e.g., from EHRs) within memory constraints of R by processing data in chunks and applying case-control sampling. We demonstrate the functionality of TrialEmulation using a simulated data set that mimics typical observational time-to-event data in practice.

stat.ME↗