arXiv subjects

Yuhao Wang

Publications and source records attributed to Yuhao Wang.

At least 109 records · Page 6Linked to original sources

arXiv2025

AdaDoS: Adaptive DoS Attack via Deep Adversarial Reinforcement Learning in SDN

Existing defence mechanisms have demonstrated significant effectiveness in mitigating rule-based Denial-of-Service (DoS) attacks, leveraging predefined signatures and static heuristics to identify and block malicious traffic. However, the emergence of AI-driven techniques presents new challenges to SDN security, potentially compromising the efficacy of existing defence mechanisms. In this paper, we introduce~AdaDoS, an adaptive attack model that disrupt network operations while evading detection by existing DoS-based detectors through adversarial reinforcement learning (RL). Specifically, AdaDoS models the problem as a competitive game between an attacker, whose goal is to obstruct network traffic without being detected, and a detector, which aims to identify malicious traffic. AdaDoS can solve this game by dynamically adjusting its attack strategy based on feedback from the SDN and the detector. Additionally, recognising that attackers typically have less information than defenders, AdaDoS formulates the DoS-like attack as a partially observed Markov decision process (POMDP), with the attacker having access only to delay information between attacker and victim nodes. We address this challenge with a novel reciprocal learning module, where the student agent, with limited observations, enhances its performance by learning from the teacher agent, who has full observational capabilities in the SDN environment. AdaDoS represents the first application of RL to develop DoS-like attack sequences, capable of adaptively evading both machine learning-based and rule-based DoS-like attack detectors.

cs.CR↗

arXiv2025

VocalBench-DF: A Benchmark for Evaluating Speech LLM Robustness to Disfluency

While Speech Large Language Models (Speech-LLMs) show strong performance in many applications, their robustness is critically under-tested, especially to speech disfluency. Existing evaluations often rely on idealized inputs, overlooking common disfluencies, particularly those associated with conditions like Parkinson's disease. This work investigates whether current Speech-LLMs can maintain performance when interacting with users who have speech impairments. To facilitate this inquiry, we introduce VocalBench-DF, a framework for the systematic evaluation of disfluency across a multi-dimensional taxonomy. Our evaluation of 22 mainstream Speech-LLMs reveals substantial performance degradation, indicating that their real-world readiness is limited. Further analysis identifies phoneme-level processing and long-context modeling as primary bottlenecks responsible for these failures. Strengthening recognition and reasoning capability from components and pipelines can substantially improve robustness. These findings highlight the urgent need for new methods to improve disfluency handling and build truly inclusive Speech-LLMs

cs.CL↗

arXiv2025

When Seeing Is not Enough: Revealing the Limits of Active Reasoning in MLLMs

Multimodal large language models (MLLMs) have shown strong capabilities across a broad range of benchmarks. However, most existing evaluations focus on passive inference, where models perform step-by-step reasoning under complete information. This setup is misaligned with real-world use, where seeing is not enough. This raises a fundamental question: Can MLLMs actively acquire missing evidence under incomplete information? To bridge this gap, we require the MLLMs to actively acquire missing evidence and iteratively refine decisions under incomplete information, by selecting a target image from a candidate pool without task-specific priors. To support systematic study, we propose GuessBench, a benchmark with both perception-oriented and knowledge-oriented images for evaluating active reasoning in MLLMs. We evaluate 20 superior MLLMs and find that performance on active reasoning lags far behind it on passive settings, indicating substantial room for improvement. Further analysis identifies fine-grained perception and timely decision-making as key challenges. Ablation studies show that perceptual enhancements benefit smaller models, whereas thinking-oriented methods provide consistent gains across model sizes. These results suggest promising directions for future research on multimodal active reasoning.

cs.CL↗

arXiv2025

Scenario-Wise Rec: A Multi-Scenario Recommendation Benchmark

Multi Scenario Recommendation (MSR) tasks, referring to building a unified model to enhance performance across all recommendation scenarios, have recently gained much attention. However, current research in MSR faces two significant challenges that hinder the field's development: the absence of uniform procedures for multi-scenario dataset processing, thus hindering fair comparisons, and most models being closed-sourced, which complicates comparisons with current SOTA models. Consequently, we introduce our benchmark, \textbf{Scenario-Wise Rec}, which comprises 6 public datasets and 12 benchmark models, along with a training and evaluation pipeline. Additionally, we validated the benchmark using an industrial advertising dataset, reinforcing its reliability and applicability in real-world scenarios. We aim for this benchmark to offer researchers valuable insights from prior work, enabling the development of novel models based on our benchmark and thereby fostering a collaborative research ecosystem in MSR. Our source code is also publicly available.

cs.IR↗

arXiv2025

CS3-Bench: Evaluating and Enhancing Speech-to-Speech LLMs for Mandarin-English Code-Switching

The advancement of multimodal large language models has accelerated the development of speech-to-speech interaction systems. While natural monolingual interaction has been achieved, we find existing models exhibit deficiencies in language alignment. In our proposed Code-Switching Speech-to-Speech Benchmark (CS3-Bench), experiments on 7 mainstream models demonstrate a relative performance drop of up to 66% in knowledge-intensive question answering and varying degrees of misunderstanding in open-ended conversations. Starting from a model with severe performance deterioration, we propose both data constructions and training approaches to improve the language alignment capabilities, specifically employing Chain of Recognition (CoR) to enhance understanding and Keyword Highlighting (KH) to guide generation. Our approach improves the knowledge accuracy from 25.14% to 46.13%, with open-ended understanding rate from 64.5% to 86.5%, and significantly reduces pronunciation errors in the secondary language. CS3-Bench is available at https://huggingface.co/datasets/VocalNet/CS3-Bench.

cs.CL↗

arXiv2025

SimpleDeepSearcher: Deep Information Seeking via Web-Powered Reasoning Trajectory Synthesis

Retrieval-augmented generation (RAG) systems have advanced large language models (LLMs) in complex deep search scenarios requiring multi-step reasoning and iterative information retrieval. However, existing approaches face critical limitations that lack high-quality training trajectories or suffer from the distributional mismatches in simulated environments and prohibitive computational costs for real-world deployment. This paper introduces SimpleDeepSearcher, a lightweight yet effective framework that bridges this gap through strategic data engineering rather than complex training paradigms. Our approach synthesizes high-quality training data by simulating realistic user interactions in live web search environments, coupled with a multi-criteria curation strategy that optimizes the diversity and quality of input and output side. Experiments on five benchmarks across diverse domains demonstrate that SFT on only 871 curated samples yields significant improvements over RL-based baselines. Our work establishes SFT as a viable pathway by systematically addressing the data-scarce bottleneck, offering practical insights for efficient deep search systems. Our code is available at https://github.com/RUCAIBox/SimpleDeepSearcher.

cs.CL↗

arXiv2025

U-Bench: A Comprehensive Understanding of U-Net through 100-Variant Benchmarking

Over the past decade, U-Net has been the dominant architecture in medical image segmentation, leading to the development of thousands of U-shaped variants. Despite its widespread adoption, there is still no comprehensive benchmark to systematically evaluate their performance and utility, largely because of insufficient statistical validation and limited consideration of efficiency and generalization across diverse datasets. To bridge this gap, we present U-Bench, the first large-scale, statistically rigorous benchmark that evaluates 100 U-Net variants across 28 datasets and 10 imaging modalities. Our contributions are threefold: (1) Comprehensive Evaluation: U-Bench evaluates models along three key dimensions: statistical robustness, zero-shot generalization, and computational efficiency. We introduce a novel metric, U-Score, which jointly captures the performance-efficiency trade-off, offering a deployment-oriented perspective on model progress. (2) Systematic Analysis and Model Selection Guidance: We summarize key findings from the large-scale evaluation and systematically analyze the impact of dataset characteristics and architectural paradigms on model performance. Based on these insights, we propose a model advisor agent to guide researchers in selecting the most suitable models for specific datasets and tasks. (3) Public Availability: We provide all code, models, protocols, and weights, enabling the community to reproduce our results and extend the benchmark with future methods. In summary, U-Bench not only exposes gaps in previous evaluations but also establishes a foundation for fair, reproducible, and practically relevant benchmarking in the next decade of U-Net-based segmentation models. The project can be accessed at: https://fenghetan9.github.io/ubench. Code is available at: https://github.com/FengheTan9/U-Bench.

cs.CV↗

arXiv2025

SAFER: Advancing Safety Alignment via Efficient Ex-Ante Reasoning

Recent advancements in large language models (LLMs) have accelerated progress toward artificial general intelligence, yet their potential to generate harmful content poses critical safety challenges. Existing alignment methods often struggle to cover diverse safety scenarios and remain vulnerable to adversarial attacks. In this work, we propose SAFER, a framework for Safety Alignment via eFficient Ex-Ante Reasoning. Our approach instantiates structured Ex-Ante reasoning through initial assessment, rule verification, and path calibration, and embeds predefined safety rules to provide transparent and verifiable safety judgments. Specifically, our approach consists of two training stages: (1) supervised fine-tuning with synthetic traces to teach the multi-stage Ex-Ante reasoning, and (2) step-level reasoning preference optimization to jointly enhance safety, utility, and efficiency. Experiments on multiple open-source LLMs demonstrate that SAFER significantly enhances safety performance while maintaining helpfulness and response efficiency.

cs.CL↗

arXiv2025

Empowering Denoising Sequential Recommendation with Large Language Model Embeddings

Sequential recommendation aims to capture user preferences by modeling sequential patterns in user-item interactions. However, these models are often influenced by noise such as accidental interactions, leading to suboptimal performance. Therefore, to reduce the effect of noise, some works propose explicitly identifying and removing noisy items. However, we find that simply relying on collaborative information may result in an over-denoising problem, especially for cold items. To overcome these limitations, we propose a novel framework: Interest Alignment for Denoising Sequential Recommendation (IADSR) which integrates both collaborative and semantic information. Specifically, IADSR is comprised of two stages: in the first stage, we obtain the collaborative and semantic embeddings of each item from a traditional sequential recommendation model and an LLM, respectively. In the second stage, we align the collaborative and semantic embeddings and then identify noise in the interaction sequence based on long-term and short-term interests captured in the collaborative and semantic modalities. Our extensive experiments on four public datasets validate the effectiveness of the proposed framework and its compatibility with different sequential recommendation systems.

cs.IR↗

arXiv2025

Silent Leaks: Implicit Knowledge Extraction Attack on RAG Systems through Benign Queries

Retrieval-Augmented Generation (RAG) systems enhance large language models (LLMs) by incorporating external knowledge bases, but this may expose them to extraction attacks, leading to potential copyright and privacy risks. However, existing extraction methods typically rely on malicious inputs such as prompt injection or jailbreaking, making them easily detectable via input- or output-level detection. In this paper, we introduce Implicit Knowledge Extraction Attack (IKEA), which conducts Knowledge Extraction on RAG systems through benign queries. Specifically, IKEA first leverages anchor concepts-keywords related to internal knowledge-to generate queries with a natural appearance, and then designs two mechanisms that lead anchor concepts to thoroughly "explore" the RAG's knowledge: (1) Experience Reflection Sampling, which samples anchor concepts based on past query-response histories, ensuring their relevance to the topic; (2) Trust Region Directed Mutation, which iteratively mutates anchor concepts under similarity constraints to further exploit the embedding space. Extensive experiments demonstrate IKEA's effectiveness under various defenses, surpassing baselines by over 80% in extraction efficiency and 90% in attack success rate. Moreover, the substitute RAG system built from IKEA's extractions shows comparable performance to the original RAG and outperforms those based on baselines across multiple evaluation tasks, underscoring the stealthy copyright infringement risk in RAG systems.

cs.CR↗

arXiv2025

Foggy Crowd Counting: Combining Physical Priors and KAN-Graph

Aiming at the key challenges of crowd counting in foggy environments, such as long-range target blurring, local feature degradation, and image contrast attenuation, this paper proposes a crowd-counting method with a physical a priori of atmospheric scattering, which improves crowd counting accuracy under complex meteorological conditions through the synergistic optimization of the physical mechanism and data-driven.Specifically, first, the method introduces a differentiable atmospheric scattering model and employs transmittance dynamic estimation and scattering parameter adaptive calibration techniques to accurately quantify the nonlinear attenuation laws of haze on targets with different depths of field.Secondly, the MSA-KAN was designed based on the Kolmogorov-Arnold Representation Theorem to construct a learnable edge activation function. By integrating a multi-layer progressive architecture with adaptive skip connections, it significantly enhances the model's nonlinear representation capability in feature-degraded regions, effectively suppressing feature confusion under fog interference.Finally, we further propose a weather-aware GCN that dynamically constructs spatial adjacency matrices using deep features extracted by MSA-KAN. Experiments on four public datasets demonstrate that our method achieves a 12.2\%-27.5\% reduction in MAE metrics compared to mainstream algorithms in dense fog scenarios.

cs.CV↗

arXiv2025

Online Bayesian Risk-Averse Reinforcement Learning

In this paper, we study the Bayesian risk-averse formulation in reinforcement learning (RL). To address the epistemic uncertainty due to a lack of data, we adopt the Bayesian Risk Markov Decision Process (BRMDP) to account for the parameter uncertainty of the unknown underlying model. We derive the asymptotic normality that characterizes the difference between the Bayesian risk value function and the original value function under the true unknown distribution. The results indicate that the Bayesian risk-averse approach tends to pessimistically underestimate the original value function. This discrepancy increases with stronger risk aversion and decreases as more data become available. We then utilize this adaptive property in the setting of online RL as well as online contextual multi-arm bandits (CMAB), a special case of online RL. We provide two procedures using posterior sampling for both the general RL problem and the CMAB problem. We establish a sub-linear regret bound, with the regret defined as the conventional regret for both the RL and CMAB settings. Additionally, we establish a sub-linear regret bound for the CMAB setting with the regret defined as the Bayesian risk regret. Finally, we conduct numerical experiments to demonstrate the effectiveness of the proposed algorithm in addressing epistemic uncertainty and verifying the theoretical properties.

cs.LG↗

arXiv2025

Asymptotic Theory of the Best-Choice Rerandomization using the Mahalanobis Distance

Rerandomization, a design that utilizes pretreatment covariates and improves their balance between different treatment groups, has received attention recently in both theory and practice. From a survey by Bruhn and McKenzie (2009), there are at least two types of rerandomization that are used in practice: the first rerandomizes the treatment assignment until covariate imbalance is below a prespecified threshold; the second randomizes the treatment assignment multiple times and chooses the one with the best covariate balance. In this paper we will consider the second type of rerandomization, namely the best-choice rerandomization, whose theory and inference are still lacking in the literature. In particular, we will focus on the best-choice rerandomization that uses the Mahalanobis distance to measure covariate imbalance, which is one of the most commonly used imbalance measure for multivariate covariates and is invariant to affine transformations of covariates. We will study the large-sample repeatedly sampling properties of the best-choice rerandomization, allowing both the number of covariates and the number of tried complete randomizations to increase with the sample size. We show that the asymptotic distribution of the difference-in-means estimator is more concentrated around the true average treatment effect under rerandomization than under the complete randomization, and propose large-sample accurate confidence intervals for rerandomization that are shorter than that for the completely randomized experiment. We further demonstrate that, with moderate number of covariates and with the number of tried randomizations increasing polynomially with the sample size, the best-choice rerandomization can achieve the ideally optimal precision that one can expect even with perfectly balanced covariates. The developed theory and methods are also illustrated using real field experiments.

stat.ME↗

arXiv2025

A Hybrid Hinge-Beam Continuum Robot with Passive Safety Capping for Real-Time Fatigue Awareness

Cable-driven continuum robots offer high flexibility and lightweight design, making them well-suited for tasks in constrained and unstructured environments. However, prolonged use can induce mechanical fatigue from plastic deformation and material degradation, compromising performance and risking structural failure. In the state of the art, fatigue estimation of continuum robots remains underexplored, limiting long-term operation. To address this, we propose a fatigue-aware continuum robot with three key innovations: (1) a Hybrid Hinge-Beam structure where TwistBeam and BendBeam decouple torsion and bending: passive revolute joints in the BendBeam mitigate stress concentration, while TwistBeam's limited torsional deformation reduces BendBeam stress magnitude, enhancing durability; (2) a Passive Stopper that safely constrains motion via mechanical constraints and employs motor torque sensing to detect corresponding limit torque, ensuring safety and enabling data collection; and (3) a real-time fatigue-awareness method that estimates stiffness from motor torque at the limit pose, enabling online fatigue estimation without additional sensors. Experiments show that the proposed design reduces fatigue accumulation by about 49% compared with a conventional design, while passive mechanical limiting combined with motor-side sensing allows accurate estimation of structural fatigue and damage. These results confirm the effectiveness of the proposed architecture for safe and reliable long-term operation.

cs.RO↗

arXiv2025

Sigma: Siamese Mamba Network for Multi-Modal Semantic Segmentation

Multi-modal semantic segmentation significantly enhances AI agents' perception and scene understanding, especially under adverse conditions like low-light or overexposed environments. Leveraging additional modalities (X-modality) like thermal and depth alongside traditional RGB provides complementary information, enabling more robust and reliable prediction. In this work, we introduce Sigma, a Siamese Mamba network for multi-modal semantic segmentation utilizing the advanced Mamba. Unlike conventional methods that rely on CNNs, with their limited local receptive fields, or Vision Transformers (ViTs), which offer global receptive fields at the cost of quadratic complexity, our model achieves global receptive fields with linear complexity. By employing a Siamese encoder and innovating a Mamba-based fusion mechanism, we effectively select essential information from different modalities. A decoder is then developed to enhance the channel-wise modeling ability of the model. Our proposed method is rigorously evaluated on both RGB-Thermal and RGB-Depth semantic segmentation tasks, demonstrating its superiority and marking the first successful application of State Space Models (SSMs) in multi-modal perception tasks. Code is available at https://github.com/zifuwan/Sigma.

cs.CV↗

arXiv2025

Lightweight Kinematic and Static Modeling of Cable-Driven Continuum Robots via Actuation-Space Energy Formulation

Continuum robots, inspired by octopus arms and elephant trunks, combine dexterity with intrinsic compliance, making them well suited for unstructured and confined environments. Yet their continuously deformable morphology poses challenges for motion planning and control, calling for accurate but lightweight models. We propose the Lightweight Actuation Space Energy Modeling (LASEM) framework for cable driven continuum robots, which formulates actuation potential energy directly in actuation space. LASEM yields an analytical forward model derived from geometrically nonlinear beam and rod theories via Hamilton's principle, while avoiding explicit modeling of cable backbone contact. It accepts both force and displacement inputs, thereby unifying kinematic and static formulations. Assuming the friction is neglected, the framework generalizes to nonuniform geometries, arbitrary cable routings, distributed loading and axial extensibility, while remaining computationally efficient for real-time use. Numerical simulations validate its accuracy, and a semi-analytical iterative scheme is developed for inverse kinematics. To address discretization in practical robots, LASEM further reformulates the functional minimization as a numerical optimization, which also naturally incorporates cable potential energy without explicit contact modeling.

cs.RO↗

arXiv2025

Faster and Better: Reinforced Collaborative Distillation and Self-Learning for Infrared-Visible Image Fusion

Infrared and visible image fusion plays a critical role in enhancing scene perception by combining complementary information from different modalities. Despite recent advances, achieving high-quality image fusion with lightweight models remains a significant challenge. To bridge this gap, we propose a novel collaborative distillation and self-learning framework for image fusion driven by reinforcement learning. Unlike conventional distillation, this approach not only enables the student model to absorb image fusion knowledge from the teacher model, but more importantly, allows the student to perform self-learning on more challenging samples to enhance its capabilities. Particularly, in our framework, a reinforcement learning agent explores and identifies a more suitable training strategy for the student. The agent takes both the student's performance and the teacher-student gap as inputs, which leads to the generation of challenging samples to facilitate the student's self-learning. Simultaneously, it dynamically adjusts the teacher's guidance strength based on the student's state to optimize the knowledge transfer. Experimental results demonstrate that our method can significantly improve student performance and achieve better fusion results compared to existing techniques.

cs.CV↗

arXiv2025

Empowering Large Language Model for Sequential Recommendation via Multimodal Embeddings and Semantic IDs

Sequential recommendation (SR) aims to capture users' dynamic interests and sequential patterns based on their historical interactions. Recently, the powerful capabilities of large language models (LLMs) have driven their adoption in SR. However, we identify two critical challenges in existing LLM-based SR methods: 1) embedding collapse when incorporating pre-trained collaborative embeddings and 2) catastrophic forgetting of quantized embeddings when utilizing semantic IDs. These issues dampen the model scalability and lead to suboptimal recommendation performance. Therefore, based on LLMs like Llama3-8B-instruct, we introduce a novel SR framework named MME-SID, which integrates multimodal embeddings and quantized embeddings to mitigate embedding collapse. Additionally, we propose a Multimodal Residual Quantized Variational Autoencoder (MM-RQ-VAE) with maximum mean discrepancy as the reconstruction loss and contrastive learning for alignment, which effectively preserve intra-modal distance information and capture inter-modal correlations, respectively. To further alleviate catastrophic forgetting, we initialize the model with the trained multimodal code embeddings. Finally, we fine-tune the LLM efficiently using LoRA in a multimodal frequency-aware fusion manner. Extensive experiments on three public datasets validate the superior performance of MME-SID thanks to its capability to mitigate embedding collapse and catastrophic forgetting. The implementation code and datasets are publicly available for reproduction: https://github.com/Applied-Machine-Learning-Lab/MME-SID.

cs.IR↗