Gongli Xi

Packet-Level DDoS Data Augmentation Using Dual-Stream Temporal-Field Diffusion

Gongli Xi, Ye Tian, Yannan Hu, Zhang Y et autres

cn (code pays fourni par la source)

HyBridge: hybrid decoupling-to-recoupling adaptation of vision-language models for real-time video action recognition

Mengyu Yang, Ye Tian, Lanshan Zhang, Gongli Xi et autres

cn (code pays fourni par la source)

Large Vision-Language Models Get Lost in Attention

Gongli Xi, Ye Tian, Mengyu Yang, Huahui Yi et autres

Despite the rapid evolution of training paradigms, the decoder backbone of large vision--language models (LVLMs) remains fundamentally rooted in the residual-connection Transformer architecture. Therefore, deciphering the distinct roles of internal modules is critical for understanding model mechanics and guiding architectural optimization. While …

CoPHo: Classifier-guided Conditional Topology Generation with Persistent Homology

Gongli Xi, Ye Tian, Mengyu Yang, Zhenyu Zhao et autres

The structure of topology underpins much of the research on performance and robustness, yet available topology data are typically scarce, necessitating the generation of synthetic graphs with desired properties for testing or release. Prior diffusion-based approaches either embed conditions into the diffusion …

cn (code pays fourni par la source)

SaFeR-ToolKit: Structured Reasoning via Virtual Tool Calling for Multimodal Safety

Zixuan Xu, Tiancheng He, Huahui Yi, Kun Wang et autres

Vision-language models remain susceptible to multimodal jailbreaks and over-refusal because safety hinges on both visual evidence and user intent, while many alignment pipelines supervise only the final response. To address this, we present SaFeR-ToolKit, which formalizes safety decision-making as a checkable protocol. …

SEC : Enabling MLLMs for Low-Latency IoT Video Analysis via Semantic-Aware Edge–Cloud Collaboration

Mengyu Yang, Ye Tian, Peizhuang Cong, Lanshan Zhang et autres

The rapid proliferation of IoT-enabled cameras has driven increasing demand for low-latency, intelligent video understanding in real-world applications such as smart cities and industrial automation. While Multimodal Large Language Models (MLLMs) offer unprecedented capabilities in semantic reasoning and natural language-based video comprehension, …

cn (code pays fourni par la source)

ClueTracer: Question-to-Vision Clue Tracing for Training-Free Hallucination Suppression in Multimodal Reasoning

Gongli Xi, Kun Wang, Zeming Gao, Huahui Yi et autres

Large multimodal reasoning models solve challenging visual problems via explicit long-chain inference: they gather visual clues from images and decode clues into textual tokens. Yet this capability also increases hallucinations, where the model generates content that is not supported by the input …

Lrbomchz/CoPHo: CoPHo

Gongli Xi

CoPHo release

cn (code pays fourni par la source)

Lrbomchz/CoPHo: CoPHo

Gongli Xi

CoPHo release

cn (code pays fourni par la source)

CoPHo: Classifier-guided Conditional Topology Generation with Persistent Homology

Gongli Xi, Ye Tian, Mengyu Yang, Zhenyu Zhao et autres

The structure of topology underpins much of the research on performance and robustness, yet available topology data are typically scarce, necessitating the generation of synthetic graphs with desired properties for testing or release. Prior diffusion-based approaches either embed conditions into the diffusion …

SaFeR-VLM: Toward Safety-aware Fine-grained Reasoning in Multimodal Models

Huahui Yi, Kun Wang, Qiaoyang Li, Miao Yu et autres

Multimodal Large Reasoning Models (MLRMs) demonstrate impressive cross-modal reasoning but often amplify safety risks under adversarial or unsafe prompts, a phenomenon we call the \textit{Reasoning Tax}. Existing defenses mainly act at the output level and do not constrain the reasoning process, leaving …

Go To Anywhere: A Multi-Armed Bandit Based Offloading Attack in Edge Computing

Jiahui Hu, Ye Tian, Zeming Gao, Gongli Xi et autres

Task scheduling is a critical component in edge computing. Many advanced scheduling strategies select the most suitable execution node based on user-reported resource requirements, thereby enhancing user experience. However, the reliance on user-reported resource demands presents a potential vulnerability, as malicious users …

cn (code pays fourni par la source)