arXiv subjects

Shuyu Li

Publications and source records attributed to Shuyu Li.

10 recordsLinked to original sources

arXiv2026

MusicLayout: Explicit Structural Planning for Controllable Text-to-Music Generation

Text-to-music generation has advanced rapidly, but current systems still rely primarily on global text prompts, leaving the structural organization of generated music implicit and difficult to inspect, control, or revise before audio generation. To address this issue, we introduce MusicLayout, an explicit intermediate representation for controlling musical structure in text-to-music generation. MusicLayout describes a musical piece as a time-aligned layout of sections, textures, repetitions, variations, and instrument-level arrangements, serving as an interpretable planning layer between textual intent and the generated music. We integrate MusicLayout into a text-to-music framework built on a unified autoregressive formulation, where the model first generates a MusicLayout representation and subsequently predicts audio tokens conditioned on this representation within a single sequence. The resulting MusicLayout can be inspected and modified prior to audio generation, providing a mechanism for layout-level structural control. We evaluate MusicLayout through layout-conditioned generation, layout manipulation experiments, and matched-data ablations, providing evidence that explicit layout planning can improve long-range structural organization and support layout-level control. We have released the implementation as open source on GitHub at https://github.com/XaryLee/MusicLayout.

cs.SD↗

arXiv2026

Heterogeneity-Adaptive Diffusion Schrodinger Bridge for PET-Guided Whole-Body MRI Translation

While whole-body multimodal medical imaging scanners have been increasingly recognized for more effective medical applications, the excessive long acquisition time in PET-MR scanning is a major obstacle in more efficient clinical practice. Deep learning-based MRI translation provides a potential solution to reduce scan duration. However, current models often focus on specific anatomical regions and face challenges for whole-body scans that consists of highly heterogeneous feature distributions mainly due to (1) different anatomical regions across whole-body, and (2) lesions or pathological tissues. This paper tackles the challenges through a novel Heterogeneity-Adaptive Diffusion Schrodinger Bridge (HA-DSB) framework. By explicitly modeling translation as stochastic transport between source and target distributions, HA-DSB incorporates region context embeddings derived from a vision-language model (VLM) to enable region-specific modeling. To enhance fidelity of the pathological tissue, lesion-aware metabolic prior from PET is integrated directly into the bridge dynamics through a dual-stage guidance mechanism. Specifically, a PET-guided noise modulation module adaptively scales spatial diffusion perturbations during the forward process, while PET features are leveraged during the reverse process to selectively amplify lesion-relevant structures via an attention mechanism. Experiments demonstrate the superiority of our method across different body regions in whole-body MRI translation and show improved translation quality in lesion areas under PET guidance. Our code is available at Github.

cs.CV↗

arXiv2026

StructBreak: Structural Cognitive Overload-Induced Safety Failures in MLLMs

Multimodal Large Language Models (MLLMs) excel at structural reasoning yet suffer from a sharp logical brittleness in structural consistency. We term this phenomenon Structural Cognitive Overload (SCO), a byproduct of the contention between deep reasoning and safety alignment. However, prior work has predominantly targeted typographic and pixel-level perturbations, leaving the study of SCO largely unexplored. To this end, we propose StructBreak, an automated end-to-end framework designed to quantify SCO. By leveraging StructBreak, we uncover a novel higher-order cognitive overload attack paradigm; notably, this attack operates under a practical black-box setting, requiring no internal model access. Consequently, we utilize this framework to establish a comprehensive benchmark spanning ten diverse threat scenarios. Empirical evaluations on six leading MLLMs reveal that SCO readily triggers toxic generation, yielding a 92% average ASR (up to 97% on Gemini 2.5). To elucidate the mechanism of SCO, we further conduct model-level interpretations spanning attention dynamics, latent space topology, and geometric analysis. Our findings reveal that StructBreak acts as a novel structural channel to circumvent safety filters. Furthermore, the limited efficacy of inherent safety mechanisms underscores that current alignment paradigms are insufficient for the era of complex multimodal reasoning.

cs.AI↗

arXiv2026

ShadowMerge: A Novel Poisoning Attack on Graph-Based Agent Memory via Relation-Channel Conflicts

Graph-based agent memory is increasingly used in LLM agents to support structured long-term recall and multi-hop reasoning, but it also creates a new poisoning surface: an attacker can inject a crafted relation into graph memory so that it is later retrieved and influences agent behavior. Existing agent-memory poisoning attacks mainly target flat textual records and are ineffective in graph-based memory because malicious relations often fail to be extracted, merged into the target anchor neighborhood, or retrieved for the victim query. We present SHADOWMERGE, a poisoning attack against graph-based agent memory that exploits relation-channel conflicts. Its key insight is that a poisoned relation can share the same query-activated anchor and canonicalized relation channel as benign evidence while carrying a conflicting value. To realize this, we design AIR, a pipeline that converts the conflict into an ordinary interaction that can be extracted, merged, and retrieved by the graph-memory system. We evaluate SHADOWMERGE on Mem0 and three public real-world datasets: PubMedQA, WebShop, and ToolEmu. SHADOWMERGE achieves 93.8% average attack success rate, improving the best baseline by 50.3 absolute points, while having negligible impact on unrelated benign tasks. Mechanism studies show that SHADOWMERGE overcomes the three key limitations of existing agent-memory poisoning attacks, and defense analysis shows that representative input-side defenses are insufficient to mitigate it. We have responsibly disclosed our findings to affected graph-memory vendors and open sourced SHADOWMERGE.

cs.CR↗

arXiv2025

Diff-V2M: A Hierarchical Conditional Diffusion Model with Explicit Rhythmic Modeling for Video-to-Music Generation

Video-to-music (V2M) generation aims to create music that aligns with visual content. However, two main challenges persist in existing methods: (1) the lack of explicit rhythm modeling hinders audiovisual temporal alignments; (2) effectively integrating various visual features to condition music generation remains non-trivial. To address these issues, we propose Diff-V2M, a general V2M framework based on a hierarchical conditional diffusion model, comprising two core components: visual feature extraction and conditional music generation. For rhythm modeling, we begin by evaluating several rhythmic representations, including low-resolution mel-spectrograms, tempograms, and onset detection functions (ODF), and devise a rhythmic predictor to infer them directly from videos. To ensure contextual and affective coherence, we also extract semantic and emotional features. All features are incorporated into the generator via a hierarchical cross-attention mechanism, where emotional features shape the affective tone via the first layer, while semantic and rhythmic features are fused in the second cross-attention layer. To enhance feature integration, we introduce timestep-aware fusion strategies, including feature-wise linear modulation (FiLM) and weighted fusion, allowing the model to adaptively balance semantic and rhythmic cues throughout the diffusion process. Extensive experiments identify low-resolution ODF as a more effective signal for modeling musical rhythm and demonstrate that Diff-V2M outperforms existing models on both in-domain and out-of-domain datasets, achieving state-of-the-art performance in terms of objective metrics and subjective comparisons. Demo and code are available at https://Tayjsl97.github.io/Diff-V2M-Demo/.

cs.SD↗

arXiv2025

A Survey on Music Generation from Single-Modal, Cross-Modal, and Multi-Modal Perspectives

Multi-modal music generation, using multiple modalities like text, images, and video alongside musical scores and audio as guidance, is an emerging research area with broad applications. This paper reviews this field, categorizing music generation systems from the perspective of modalities. The review covers modality representation, multi-modal data alignment, and their utilization to guide music generation. Current datasets and evaluation methods are also discussed. Key challenges in this area include effective multi-modal integration, large-scale comprehensive datasets, and systematic evaluation methods. Finally, an outlook on future research directions is provided, focusing on creativity, efficiency, multi-modal alignment, and evaluation.

cs.SD↗

arXiv2025

A Comprehensive Survey on Generative AI for Video-to-Music Generation

The burgeoning growth of video-to-music generation can be attributed to the ascendancy of multimodal generative models. However, there is a lack of literature that comprehensively combs through the work in this field. To fill this gap, this paper presents a comprehensive review of video-to-music generation using deep generative AI techniques, focusing on three key components: conditioning input construction, conditioning mechanism, and music generation frameworks. We categorize existing approaches based on their designs for each component, clarifying the roles of different strategies. Preceding this, we provide a fine-grained categorization of video and music modalities, illustrating how different categories influence the design of components within the generation pipelines. Furthermore, we summarize available multimodal datasets and evaluation metrics while highlighting ongoing challenges in the field.

eess.AS↗

arXiv2024

MuChin: A Chinese Colloquial Description Benchmark for Evaluating Language Models in the Field of Music

The rapidly evolving multimodal Large Language Models (LLMs) urgently require new benchmarks to uniformly evaluate their performance on understanding and textually describing music. However, due to semantic gaps between Music Information Retrieval (MIR) algorithms and human understanding, discrepancies between professionals and the public, and low precision of annotations, existing music description datasets cannot serve as benchmarks. To this end, we present MuChin, the first open-source music description benchmark in Chinese colloquial language, designed to evaluate the performance of multimodal LLMs in understanding and describing music. We established the Caichong Music Annotation Platform (CaiMAP) that employs an innovative multi-person, multi-stage assurance method, and recruited both amateurs and professionals to ensure the precision of annotations and alignment with popular semantics. Utilizing this method, we built a dataset with multi-dimensional, high-precision music annotations, the Caichong Music Dataset (CaiMD), and carefully selected 1,000 high-quality entries to serve as the test set for MuChin. Based on MuChin, we analyzed the discrepancies between professionals and amateurs in terms of music description, and empirically demonstrated the effectiveness of annotated data for fine-tuning LLMs. Ultimately, we employed MuChin to evaluate existing music understanding models on their ability to provide colloquial descriptions of music. All data related to the benchmark, along with the scoring code and detailed appendices, have been open-sourced (https://github.com/CarlWangChina/MuChin/).

cs.SD↗

arXiv2021

Robust Matrix Factorization with Grouping Effect

Although many techniques have been applied to matrix factorization (MF), they may not fully exploit the feature structure. In this paper, we incorporate the grouping effect into MF and propose a novel method called Robust Matrix Factorization with Grouping effect (GRMF). The grouping effect is a generalization of the sparsity effect, which conducts denoising by clustering similar values around multiple centers instead of just around 0. Compared with existing algorithms, the proposed GRMF can automatically learn the grouping structure and sparsity in MF without prior knowledge, by introducing a naturally adjustable non-convex regularization to achieve simultaneous sparsity and grouping effect. Specifically, GRMF uses an efficient alternating minimization framework to perform MF, in which the original non-convex problem is first converted into a convex problem through Difference-of-Convex (DC) programming, and then solved by Alternating Direction Method of Multipliers (ADMM). In addition, GRMF can be easily extended to the Non-negative Matrix Factorization (NMF) settings. Extensive experiments have been conducted using real-world data sets with outliers and contaminated noise, where the experimental results show that GRMF has promoted performance and robustness, compared to five benchmark algorithms.

cs.LG↗

arXiv2021

Frontoparietal Connectivity Neurofeedback Training for Promotion of Working Memory: An fNIRS Study in Healthy Male Participants

Neurofeedback cognitive training is a promising tool used to promote cognitive functions effectively and efficiently. In this study, we investigated a novel functional near-infrared spectroscopy (fNIRS)-based frontoparietal functional connectivity (FC) neurofeedback training paradigm related to working memory, involving healthy adults. Compared with conventional cognitive training studies, we chose the frontoparietal network, a key brain region for cognitive function modulation, as neurofeedback, yielding a strong targeting effect. In the experiment, 10 participants (test group) received three cognitive training sessions of 15 min using fNIRS-based frontoparietal FC as neurofeedback, and another 10 participants served as the control group. Frontoparietal FC was significantly increased in the test group (p D 0.03), and the cognitive functions (memory and attention) were significantly promoted compared with the control group (accuracy of 3-back test: p D 0.0005, reaction time of 3-back test: p D 0.0009). After additional validations on long-term training effect and on different patient populations, the proposed method exhibited considerable potential to be developed as a fast, effective, and widespread training approach for cognitive function enhancement.

q-bio.NC↗