1 citations · 2 across the 23 of their papers we have counts for
25 papers
How Narrative Wrapping Affects LLM Refusal: A Cross-Language Benchmark and Defense
Zhankai Ye, Yanning Wang, Yukai Jin +5
Safety-aligned language models often refuse a harmful request stated directly but answer the same request inside a role-play or narrative wrapper. We measure this vulnerability acr…
TempQ-Jail: Query-Constrained Candidate Ranking for Text-to-Video Jailbreak Attacks
Tianmeng Fang, Jiancheng Wang, Chen Wang +4
Existing text-to-video (T2V) jailbreak methods mainly seek more effective or stealthier attack candidates. In guarded T2V systems, however, video generation and security evaluation…
VFAD: Variational Semantic Prompting Meets Frequency-Adaptive Representation Learning for Zero-Shot Anomaly Detection
Peng Chen, Kaige Li, Wei Wang +5
Zero-shot anomaly detection (ZSAD) aims to detect and localize anomalies in unseen categories without access to target-specific training data. Although recent CLIP-based methods ha…
SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere
Chao Huang, Pengfei Wei, Penfei Wei +6
Video anomaly detection (VAD) aims to automatically identify events that deviate from normal patterns in untrimmed surveillance videos. Existing methods universally depend on large…
Multimodal Backdoor Attack on VLMs for Autonomous Driving via Graffiti and Cross-Lingual Triggers
Jiancheng Wang, Lidan Liang, Yong Wang +4
Visual language model (VLM) is rapidly being integrated into safety-critical systems such as autonomous driving, making it an important attack surface for potential backdoor attack…
A Patch-based Cross-view Regularized Framework for Backdoor Defense in Multimodal Large Language Models
Tianmeng Fang, Yong Wang, Zetai Kong +4
Multimodal large language models have become an important infrastructure for unified processing of visual and linguistic tasks. However, such models are highly susceptible to backd…
LongCat-Next: Lexicalizing Modalities as Discrete Tokens
Meituan LongCat Team, Bin Xiao, Chao Wang +86
The prevailing Next-Token Prediction (NTP) paradigm has driven the success of large language models through discrete autoregressive modeling. However, contemporary multimodal syste…
Stepping VLMs onto the Court: Benchmarking Spatial Intelligence in Sports
Yuchen Yang, Yuqing Shao, Duxiu Huang +11
Sports have long attracted broad attention as they push the limits of human physical and cognitive capabilities. Amid growing interest in spatial intelligence for vision-language m…
M3-AD: Reflection-aware Multi-modal, Multi-category, and Multi-dimensional Benchmark and Framework for Industrial Anomaly Detection
Chao Huang, Yanhui Li, Yunkang Cao +5
Although multimodal large language models (MLLMs) have advanced industrial anomaly detection toward a zero-shot paradigm, they still tend to produce high-confidence yet unreliable…
MPA: Multimodal Prototype Augmentation for Few-Shot Learning
Liwen Wu, Wei Wang, Lei Zhao +5
Recently, few-shot learning (FSL) has become a popular task that aims to recognize new classes from only a few labeled examples and has been widely applied in fields such as natura…
DLEBench: Evaluating Small-scale Object Editing Ability for Instruction-based Image Editing Model
Shibo Hong, Boxian Ai, Jun Kuang +5
Significant progress has been made in the field of Instruction-based Image Editing Models (IIEMs). However, while these models demonstrate plausible adherence to instructions and s…
SPDA-SAM: A Self-prompted Depth-Aware Segment Anything Model for Instance Segmentation
Yihan Shang, Wei Wang, Chao Huang +1
Recently, Segment Anything Model (SAM) has demonstrated strong generalizability in various instance segmentation tasks. However, its performance is severely dependent on the qualit…
Beyond Visual Safety: Jailbreaking Multimodal Large Language Models for Harmful Image Generation via Semantic-Agnostic Inputs
Mingyu Yu, Lana Liu, Zhehao Zhao +2
The rapid advancement of Multimodal Large Language Models (MLLMs) has introduced complex security challenges, particularly at the intersection of textual and visual safety. While e…
Advancing Adaptive Multi-Stage Video Anomaly Reasoning: A Benchmark Dataset and Method
Chao Huang, Benfeng Wang, Wei Wang +5
Recent progress in reasoning capabilities of Multimodal Large Language Models(MLLMs) has highlighted their potential for performing complex video understanding tasks. However, in t…
SuperOcc: Toward Cohesive Temporal Modeling for Superquadric-based 3D Occupancy Prediction
Zichen Yu, Quanli Liu, Wei Wang +2
3D occupancy prediction plays a pivotal role in the realm of autonomous driving, as it provides a comprehensive understanding of the driving environment. Most existing methods cons…
GeoMotionGPT: Geometry-Aligned Motion Understanding with Large Language Models
Zhankai Ye, Bofan Li, Yukai Jin +5
Discrete motion tokenization has recently enabled Large Language Models (LLMs) to serve as versatile backbones for motion understanding and motion-language reasoning. However, exis…
From Detection to Association: Learning Discriminative Object Embeddings for Multi-Object Tracking
Yuqing Shao, Yuchen Yang, Rui Yu +5
End-to-end multi-object tracking (MOT) methods have recently achieved remarkable progress by unifying detection and association within a single framework. Despite their strong dete…
Q-REAL: Towards Realism and Plausibility Evaluation for AI-Generated Content
Shushi Wang, Zicheng Zhang, Chunyi Li +7
Quality assessment of AI-generated content is crucial for evaluating model capability and guiding model optimization. However, most existing quality assessment datasets and models…
Did Models Learn Sufficiently? Attribution-Guided Training via Subset-Selected Counterfactual Augmentation
Yannan Chen, Ruoyu Chen, Wei Wang +6
Current visual models often make predictions based on a limited set of discriminative visual cues. As a result, they may become unreliable when the distribution shifts or when thes…
Noisy-Pair Robust Representation Alignment for Positive-Unlabeled Learning
Hengwei Zhao, Zhengzhong Tu, Zhuo Zheng +4
Positive-Unlabeled (PU) learning aims to train a binary classifier (positive vs. negative) where only limited positive data and abundant unlabeled data are available. While widely…
ComRAG: Retrieval-Augmented Generation with Dynamic Vector Stores for Real-time Community Question Answering in Industry
Qinwen Chen, Wenbiao Tao, Zhiwei Zhu +5
Community Question Answering (CQA) platforms can be deemed as important knowledge bases in community, but effectively leveraging historical interactions and domain knowledge in rea…
UltraAD: Fine-Grained Ultrasound Anomaly Classification via Few-Shot CLIP Adaptation
Yue Zhou, Yuan Bi, Wenjuan Tong +3
Precise anomaly detection in medical images is critical for clinical decision-making. While recent unsupervised or semi-supervised anomaly detection methods trained on large-scale…
AJF: Adaptive Jailbreak Framework Based on the Comprehension Ability of Black-Box Large Language Models
Mingyu Yu, Wei Wang, Yanjie Wei +3
Recent advancements in adversarial jailbreak attacks have exposed critical vulnerabilities in Large Language Models (LLMs), enabling the circumvention of alignment safeguards throu…
Measure Anything: Real-time, Multi-stage Vision-based Dimensional Measurement using Segment Anything
Yongkyu Lee, Shivam Kumar Panda, Wei Wang +1
We present Measure Anything, a comprehensive vision-based framework for dimensional measurement of objects with circular cross-sections, leveraging the Segment Anything Model (SAM)…