arXiv subjects

Shuo Yang

Publications and source records attributed to Shuo Yang.

At least 199 records · Page 11Linked to original sources

arXiv2025

Look-Back: Implicit Visual Re-focusing in MLLM Reasoning

Multimodal Large Language Models (MLLMs) have achieved remarkable progress in multimodal reasoning. However, they often excessively rely on textual information during the later stages of inference, neglecting the crucial integration of visual input. Current methods typically address this by explicitly injecting visual information to guide the reasoning process. In this work, through an analysis of MLLM attention patterns, we made an intriguing observation: with appropriate guidance, MLLMs can spontaneously re-focus their attention on visual inputs during the later stages of reasoning, even without explicit visual information injection. This spontaneous shift in focus suggests that MLLMs are intrinsically capable of performing visual fusion reasoning. Building on this insight, we introduce Look-Back, an implicit approach designed to guide MLLMs to ``look back" at visual information in a self-directed manner during reasoning. Look-Back empowers the model to autonomously determine when, where, and how to re-focus on visual inputs, eliminating the need for explicit model-structure constraints or additional input. We demonstrate that Look-Back significantly enhances the model's reasoning and perception capabilities, as evidenced by extensive empirical evaluations on multiple multimodal benchmarks.

cs.CV↗

arXiv2025

Isogeometric contact analysis in subsea umbilical and power cables

Subsea umbilical and power cables contain a large number of contact interfaces between different geometries and materials. These complex interactions rise significant challenges for accurately considering contact surface properties by using traditional analytical solutions or finite element methods. These properties have been identified as the most sensitive parameters when performing the numerical simulation for stress analysis. Therefore, it is essential to apply a novel approach for contact analysis which improves the accuracy and efficiency for predicting contact properties. This paper presents an isogeometric analysis (IGA) approach addressing contact problems in dynamic umbilicals and power cables. Firstly, this isogeometric contact algorithm is formulated in MATLAB as a tool including the geometry description, contact detection and penalty function. Secondly, the contact interface between a steel tube and an outer sheath in an dynamic umbilical is established by this IGA contact algorithm and validated against that in ABAQUS for proving the accuracy and efficiency of IGA. Finally, the effects of element refinement, geometrical description, penalty factor on the accuracy, efficiency and stability of IGA are discussed.

math.NA↗

arXiv2025

Generative AI for Vulnerability Detection in 6G Wireless Networks: Advances, Case Study, and Future Directions

The rapid advancement of 6G wireless networks, IoT, and edge computing has significantly expanded the cyberattack surface, necessitating more intelligent and adaptive vulnerability detection mechanisms. Traditional security methods, while foundational, struggle with zero-day exploits, adversarial threats, and context-dependent vulnerabilities in highly dynamic network environments. Generative AI (GAI) emerges as a transformative solution, leveraging synthetic data generation, multimodal reasoning, and adaptive learning to enhance security frameworks. This paper explores the integration of GAI-powered vulnerability detection in 6G wireless networks, focusing on code auditing, protocol security, cloud-edge defenses, and hardware protection. We introduce a three-layer framework comprising the Technology Layer, Capability Layer, and Application Layer to systematically analyze the role of VAEs, GANs, LLMs, and GDMs in securing next-generation wireless ecosystems. To demonstrate practical implementation, we present a case study on LLM-driven code vulnerability detection, highlighting its effectiveness, performance, and challenges. Finally, we outline future research directions, including lightweight models, high-authenticity data generation, external knowledge integration, and privacy-preserving technologies. By synthesizing current advancements and open challenges, this work provides a roadmap for researchers and practitioners to harness GAI for building resilient and adaptive security solutions in 6G networks.

cs.CR↗

arXiv2025

SCISSOR: Mitigating Semantic Bias through Cluster-Aware Siamese Networks for Robust Classification

Shortcut learning undermines model generalization to out-of-distribution data. While the literature attributes shortcuts to biases in superficial features, we show that imbalances in the semantic distribution of sample embeddings induce spurious semantic correlations, compromising model robustness. To address this issue, we propose SCISSOR (Semantic Cluster Intervention for Suppressing ShORtcut), a Siamese network-based debiasing approach that remaps the semantic space by discouraging latent clusters exploited as shortcuts. Unlike prior data-debiasing approaches, SCISSOR eliminates the need for data augmentation and rewriting. We evaluate SCISSOR on 6 models across 4 benchmarks: Chest-XRay and Not-MNIST in computer vision, and GYAFC and Yelp in NLP tasks. Compared to several baselines, SCISSOR reports +5.3 absolute points in F1 score on GYAFC, +7.3 on Yelp, +7.7 on Chest-XRay, and +1 on Not-MNIST. SCISSOR is also highly advantageous for lightweight models with ~9.5% improvement on F1 for ViT on computer vision datasets and ~11.9% for BERT on NLP. Our study redefines the landscape of model generalization by addressing overlooked semantic biases, establishing SCISSOR as a foundational framework for mitigating shortcut learning and fostering more robust, bias-resistant AI systems.

cs.LG↗

arXiv2025

Accelerated gradient flows for large bending deformations of nonlinear plates

In this paper, we propose novel algorithms integrated projection-free techniques with accelerated gradient flows to minimize bending energies for nonlinear plates with non-convex metric constraints. We discuss the stability and constraint consistency in a semi-discrete setting for both bilayer and prestrained plates. The proposed algorithms exhibit substantial improvements in efficiency and accuracy compared to the current state-of-the-art methods based on gradient flows.

math.NA↗

arXiv2025

HRGS: Hierarchical Gaussian Splatting for Memory-Efficient High-Resolution 3D Reconstruction

3D Gaussian Splatting (3DGS) has made significant strides in real-time 3D scene reconstruction, but faces memory scalability issues in high-resolution scenarios. To address this, we propose Hierarchical Gaussian Splatting (HRGS), a memory-efficient framework with hierarchical block-level optimization. First, we generate a global, coarse Gaussian representation from low-resolution data. Then, we partition the scene into multiple blocks, refining each block with high-resolution data. The partitioning involves two steps: Gaussian partitioning, where irregular scenes are normalized into a bounded cubic space with a uniform grid for task distribution, and training data partitioning, where only relevant observations are retained for each block. By guiding block refinement with the coarse Gaussian prior, we ensure seamless Gaussian fusion across adjacent blocks. To reduce computational demands, we introduce Importance-Driven Gaussian Pruning (IDGP), which computes importance scores for each Gaussian and removes those with minimal contribution, speeding up convergence and reducing memory usage. Additionally, we incorporate normal priors from a pretrained model to enhance surface reconstruction quality. Our method enables high-quality, high-resolution 3D scene reconstruction even under memory constraints. Extensive experiments on three benchmarks show that HRGS achieves state-of-the-art performance in high-resolution novel view synthesis (NVS) and surface reconstruction tasks.

cs.CV↗

arXiv2025

RealFactBench: A Benchmark for Evaluating Large Language Models in Real-World Fact-Checking

Large Language Models (LLMs) hold significant potential for advancing fact-checking by leveraging their capabilities in reasoning, evidence retrieval, and explanation generation. However, existing benchmarks fail to comprehensively evaluate LLMs and Multimodal Large Language Models (MLLMs) in realistic misinformation scenarios. To bridge this gap, we introduce RealFactBench, a comprehensive benchmark designed to assess the fact-checking capabilities of LLMs and MLLMs across diverse real-world tasks, including Knowledge Validation, Rumor Detection, and Event Verification. RealFactBench consists of 6K high-quality claims drawn from authoritative sources, encompassing multimodal content and diverse domains. Our evaluation framework further introduces the Unknown Rate (UnR) metric, enabling a more nuanced assessment of models' ability to handle uncertainty and balance between over-conservatism and over-confidence. Extensive experiments on 7 representative LLMs and 4 MLLMs reveal their limitations in real-world fact-checking and offer valuable insights for further research. RealFactBench is publicly available at https://github.com/kalendsyang/RealFactBench.git.

cs.CL↗

arXiv2025

Bridging the Gap between Discrete Agent Strategies in Game Theory and Continuous Motion Planning in Dynamic Environments

Generating competitive strategies and performing continuous motion planning simultaneously in an adversarial setting is a challenging problem. In addition, understanding the intent of other agents is crucial to deploying autonomous systems in adversarial multi-agent environments. Existing approaches either discretize agent action by grouping similar control inputs, sacrificing performance in motion planning, or plan in uninterpretable latent spaces, producing hard-to-understand agent behaviors. This paper proposes an agent strategy representation via Policy Characteristic Space that maps the agent policies to a pre-specified low-dimensional space. Policy Characteristic Space enables the discretization of agent policy switchings while preserving continuity in control. Also, it provides intepretability of agent policies and clear intentions of policy switchings. Then, regret-based game-theoretic approaches can be applied in the Policy Characteristic Space to obtain high performance in adversarial environments. Our proposed method is assessed by conducting experiments in an autonomous racing scenario using scaled vehicles. Statistical evidence shows that our method significantly improves the win rate of ego agent and the method also generalizes well to unseen environments.

cs.RO↗

arXiv2025

BDF schemes for accelerated gradient flows in projection-free approximation of nonconvex constrained variational minimization

We propose novel algorithms combining accelerated gradient flows with linearized projection-free treatments of non-convex constraints and BDF pseudo-temporal discretization for quadratic energy minimization. A general framework is developed to analyze constraint violations in such projection-free techniques for quadratic constraints. This analysis proves to be universal to all projection-free iterative methods, and constraint error bounds depend solely on iterate regularity. For BDF-k(k=1,2,3,4), we derive both unconditional and conditional high-order constraint violation estimates for accelerated gradient flows using our framework. We further discover a new family of BDF-k accelerated gradient methods achieving modified energy stability for arbitrary positive integer k. Numerical experiments validate our theoretical results and demonstrate superior efficiency and accuracy compared to existing gradient flow approaches.

math.NA↗

arXiv2025

Efficient Quantum Circuit Compilation for Near-Term Quantum Advantage

Quantum noise in real-world devices poses a significant challenge in achieving practical quantum advantage, since accurately compiled and executed circuits are typically deep and highly susceptible to decoherence. To facilitate the implementation of complex quantum algorithms on noisy hardware, we propose an approximate method for compiling target quantum circuits into brick-wall layouts. This new circuit design consists of two-qubit CNOT gates that can be directly implemented on real quantum computers, in conjunction with optimized one-qubit gates, to approximate the essential dynamics of the original circuit while significantly reducing its depth. Our approach is evaluated through numerical simulations of time-evolution circuits for the critical Ising model, quantum Fourier transformation, and Haar-random quantum circuits, as well as experiments on IBM quantum platforms. By accounting for compilation error and circuit noise, we demonstrate that time evolution and quantum Fourier transformation circuits achieve high compression rates, while random quantum circuits are less compressible. The degree of compression is related to the rate of entanglement accumulation in the target circuit. In particular, experiments on IBM platforms achieve a compression rate of $12.5$ for $N=12$, significantly extending the application of current quantum devices. Furthermore, large-scale numerical simulations for system sizes up to $N=30$ reveal that the optimal depth $d_{\rm max}$ to achieve maximal overall fidelity is independent of system size $N$, suggesting the scalability of our method for large quantum devices in terms of quantum resources.

quant-ph↗

arXiv2025

MAGIC-VQA: Multimodal And Grounded Inference with Commonsense Knowledge for Visual Question Answering

Visual Question Answering (VQA) requires reasoning across visual and textual modalities, yet Large Vision-Language Models (LVLMs) often lack integrated commonsense knowledge, limiting their robustness in real-world scenarios. To address this, we introduce MAGIC-VQA, a novel framework that enhances VQA by systematically integrating commonsense knowledge with LVLMs. MAGIC-VQA employs a three-stage process: (1) Explicit Knowledge Integration from external sources, (2) By-Type Post-Processing for contextual refinement, and (3) Implicit Knowledge Augmentation using a Graph Neural Network (GNN) for structured reasoning. While GNNs bring greater depth to structured inference, they enable superior relational inference beyond LVLMs. MAGIC-VQA bridges a key gap by unifying commonsensse knowledge with LVLM-driven reasoning, eliminating the need for extensive pre-training or complex prompt tuning. Our framework achieves state-of-the-art performance on benchmark datasets, significantly improving commonsense reasoning in VQA.

cs.CL↗

arXiv2025

Hyperbolic Dual Feature Augmentation for Open-Environment

Feature augmentation generates novel samples in the feature space, providing an effective way to enhance the generalization ability of learning algorithms with hyperbolic geometry. Most hyperbolic feature augmentation is confined to closed-environment, assuming the number of classes is fixed (\emph{i.e.}, seen classes) and generating features only for these classes. In this paper, we propose a hyperbolic dual feature augmentation method for open-environment, which augments features for both seen and unseen classes in the hyperbolic space. To obtain a more precise approximation of the real data distribution for efficient training, (1) we adopt a neural ordinary differential equation module, enhanced by meta-learning, estimating the feature distributions of both seen and unseen classes; (2) we then introduce a regularizer to preserve the latent hierarchical structures of data in the hyperbolic space; (3) we also derive an upper bound for the hyperbolic dual augmentation loss, allowing us to train a hyperbolic model using infinite augmentations for seen and unseen classes. Extensive experiments on five open-environment tasks: class-incremental learning, few-shot open-set recognition, few-shot learning, zero-shot learning, and general image classification, demonstrate that our method effectively enhances the performance of hyperbolic algorithms in open-environment.

cs.CV↗

arXiv2025

HashAttention: Semantic Sparsity for Faster Inference

Leveraging long contexts is crucial for advanced AI systems, but attention computation poses a scalability challenge. While scaled dot-product attention (SDPA) exhibits token sparsity, i.e. only a few pivotal tokens significantly contribute to output, exploiting this sparsity remains challenging. Existing methods either suffer from quality degradation or require substantial additional resources. We show that identifying pivotal tokens is a Maximum Inner Product Search (MIPS) problem. However, existing MIPS solutions are not well-suited for SDPA, as they are not GPU-friendly and often underperform due to the separated query and key distributions. This paper introduces HashAttention, framing pivotal token identification as a recommendation problem. Given a query, HashAttention encodes keys and queries in Hamming space, capturing the required semantic similarity, using learned mapping functions. HashAttention efficiently identifies pivotal tokens for a given query using bitwise operations and computes attention using only these tokens, improving the overall attention efficiency. Trained on generic data, HashAttention reduces tokens used by up to $16\times$ with minimal quality loss, requiring only 32 bits of auxiliary memory per token. Sparsity can be further improved to $32\times$ through task-specific fine-tuning. On A100 GPU, at $32\times$ sparsity, incorporating HashAttention reduces attention latency by up to $4.3\times$ in GPT-FAST and $2.54\times$ in FlashDecode, and achieves up to $3.12\times$ higher throughput for GPT-FAST.

cs.LG↗

arXiv2025

Chain-of-Thought for Autonomous Driving: A Comprehensive Survey and Future Prospects

The rapid evolution of large language models in natural language processing has substantially elevated their semantic understanding and logical reasoning capabilities. Such proficiencies have been leveraged in autonomous driving systems, contributing to significant improvements in system performance. Models such as OpenAI o1 and DeepSeek-R1, leverage Chain-of-Thought (CoT) reasoning, an advanced cognitive method that simulates human thinking processes, demonstrating remarkable reasoning capabilities in complex tasks. By structuring complex driving scenarios within a systematic reasoning framework, this approach has emerged as a prominent research focus in autonomous driving, substantially improving the system's ability to handle challenging cases. This paper investigates how CoT methods improve the reasoning abilities of autonomous driving models. Based on a comprehensive literature review, we present a systematic analysis of the motivations, methodologies, challenges, and future research directions of CoT in autonomous driving. Furthermore, we propose the insight of combining CoT with self-learning to facilitate self-evolution in driving systems. To ensure the relevance and timeliness of this study, we have compiled a dynamic repository of literature and open-source projects, diligently updated to incorporate forefront developments. The repository is publicly available at https://github.com/cuiyx1720/Awesome-CoT4AD.

cs.RO↗

arXiv2025

MDVT: Enhancing Multimodal Recommendation with Model-Agnostic Multimodal-Driven Virtual Triplets

The data sparsity problem significantly hinders the performance of recommender systems, as traditional models rely on limited historical interactions to learn user preferences and item properties. While incorporating multimodal information can explicitly represent these preferences and properties, existing works often use it only as side information, failing to fully leverage its potential. In this paper, we propose MDVT, a model-agnostic approach that constructs multimodal-driven virtual triplets to provide valuable supervision signals, effectively mitigating the data sparsity problem in multimodal recommendation systems. To ensure high-quality virtual triplets, we introduce three tailored warm-up threshold strategies: static, dynamic, and hybrid. The static warm-up threshold strategy exhaustively searches for the optimal number of warm-up epochs but is time-consuming and computationally intensive. The dynamic warm-up threshold strategy adjusts the warm-up period based on loss trends, improving efficiency but potentially missing optimal performance. The hybrid strategy combines both, using the dynamic strategy to find the approximate optimal number of warm-up epochs and then refining it with the static strategy in a narrow hyper-parameter space. Once the warm-up threshold is satisfied, the virtual triplets are used for joint model optimization by our enhanced pair-wise loss function without causing significant gradient skew. Extensive experiments on multiple real-world datasets demonstrate that integrating MDVT into advanced multimodal recommendation models effectively alleviates the data sparsity problem and improves recommendation performance, particularly in sparse data scenarios.

cs.IR↗

arXiv2025

Boundary anomaly detection in two-dimensional subsystem symmetry-protected topological phases

We generalize the topological response theory to detect the boundary anomalies of linear subsystem symmetries. This approach allows us to distinguish different subsystem symmetry-protected topological (SSPT) phases and uncover new ones. We focus on the cases where the mixed anomaly exists within the adjacent subsystems. Using numerical simulations, we demonstrate the power of this method by identifying strong and weak $Z_2^τ\times Z_2^σ$ SSPT phases in a tunable tensor network state. Our analysis reveals an intrinsic $Z_2$ SSPT phase characterized by its degenerate entanglement spectrum. Furthermore, we extend the anomaly indicator to mixed-state density matrices and show that quantum anomalies of subsystem symmetry can persist under both uniform and alternating disorders. This finding establishes a connection between boundary quantum anomalies in pure and mixed states. Our work provides a numerical method to detect quantum anomalies of subsystem symmetries, offering new insights into the study of topological quantum phases.

cond-mat.str-el↗

arXiv2025

METOR: A Unified Framework for Mutual Enhancement of Objects and Relationships in Open-vocabulary Video Visual Relationship Detection

Open-vocabulary video visual relationship detection aims to detect objects and their relationships in videos without being restricted by predefined object or relationship categories. Existing methods leverage the rich semantic knowledge of pre-trained vision-language models such as CLIP to identify novel categories. They typically adopt a cascaded pipeline to first detect objects and then classify relationships based on the detected objects, which may lead to error propagation and thus suboptimal performance. In this paper, we propose Mutual EnhancemenT of Objects and Relationships (METOR), a query-based unified framework to jointly model and mutually enhance object detection and relationship classification in open-vocabulary scenarios. Under this framework, we first design a CLIP-based contextual refinement encoding module that extracts visual contexts of objects and relationships to refine the encoding of text features and object queries, thus improving the generalization of encoding to novel categories. Then we propose an iterative enhancement module to alternatively enhance the representations of objects and relationships by fully exploiting their interdependence to improve recognition performance. Extensive experiments on two public datasets, VidVRD and VidOR, demonstrate that our framework achieves state-of-the-art performance.

cs.CV↗

arXiv2025

Strong-to-weak spontaneous symmetry breaking meets average symmetry-protected topological order

Recent studies have unveiled new possibilities for discovering intrinsic quantum phases that are unique to open systems, including phases with average symmetry-protected topological (ASPT) order and strong-to-weak spontaneous symmetry breaking (SWSSB) order in systems with global symmetry. In this work, we propose a new class of phases, termed the double ASPT phase, which emerges from a nontrivial extension of these two orders. This new phase is absent from prior studies and cannot exist in conventional closed systems. Using the recently developed imaginary-Lindbladian formalism, we explore the phase diagram of a one-dimensional open system with $\mathbb{Z}_2^σ\times \mathbb{Z}_2^τ$ symmetry. We identify universal critical behaviors along each critical line and observe the emergence of an intermediate phase that completely breaks the $\mathbb{Z}_2^σ$ symmetry, leading to the formation of two triple points in the phase diagram. These two triple points are topologically distinct and connected by a domain-wall decoration duality map. Our results promote the establishment of a complete classification for quantum phases in open systems with various symmetry conditions.

cond-mat.str-el↗