6 citations · 9 across the 14 of their papers we have counts for
15 papers
Steering LLM Viewpoints through Fabricated Evidence Injection
Xi Yang, Chang Liu, Zhenglin Huang +4
As chatbots increasingly influence daily decision-making, their potential to produce misleading responses poses substantial risks to users. This paper investigates a critical cogni…
A Deterministic Agentic Workflow for HS Tariff Classification: Multi-Dimensional Rule Reasoning with Interpretable Decisions
Yu Zhang, Dongjiang Zhuang, Qu Zhou +4
Harmonized System (HS) tariff classification is a high-stakes, expert-level task in which a free-form product description must be mapped to a specific six- or eight-digit code unde…
Safe Multi-Agent Behavior Must Be Maintained, Not Merely Asserted: Constraint Drift in LLM-Based Multi-Agent Systems
Tianxiao Li, Yixing Ma, Haiquan Wen +4
Modern LLM based agents are no longer passive text generators. They read repositories, call tools, browse the web, execute code, maintain memory, communicate with other agents, and…
Omni-Fake: Benchmarking Unified Multimodal Social Media Deepfake Detection
Tianxiao Li, Zhenglin Huang, Haiquan Wen +10
Multimodal deepfakes are proliferating on social media and threaten authenticity, information integrity, and digital forensics. Existing benchmarks are constrained by their single-…
Where Do Prompt Perturbations Break Generation? A Segment-Level View of Robustness in LoRA-Tuned Language Models
Zhuoyun Li, Boxuan Wang, Jinwei Hu +6
Large language models are sensitive to minor prompt perturbations, yet existing robustness methods usually enforce consistency at the whole-sequence level. This holistic view can h…
Rethinking Cross-Generator Image Forgery Detection through DINOv3
Zhenglin Huang, Jason Li, Haiquan Wen +7
As generative models become increasingly diverse and powerful, cross-generator detection has emerged as a new challenge. Existing detection methods often memorize artifacts of spec…
Spatial-DISE: A Unified Benchmark for Evaluating Spatial Reasoning in Vision-Language Models
Xinmiao Huang, Qisong He, Zhenglin Huang +5
Spatial reasoning ability is crucial for Vision Language Models (VLMs) to support real-world applications in diverse domains including robotics, augmented reality, and autonomous n…
RAIDX: A Retrieval-Augmented Generation and GRPO Reinforcement Learning Framework for Explainable Deepfake Detection
Tianxiao Li, Zhenglin Huang, Haiquan Wen +4
The rapid advancement of AI-generation models has enabled the creation of hyperrealistic imagery, posing ethical risks through widespread misinformation. Current deepfake detection…
BusterX++: Towards Unified Cross-Modal AI-Generated Content Detection and Explanation with MLLM
Haiquan Wen, Tianxiao Li, Zhenglin Huang +2
The rapid advancement of generative AI has substantially improved image and video synthesis, amplifying the risk of multimodal visual misinformation. Recent MLLMs have shown promis…
Towards Explainable Bilingual Multimodal Misinformation Detection and Localization
Yiwei He, Zhenglin Huang, Haiquan Wen +5
The increasing realism of multimodal content has made misinformation more subtle and harder to detect, especially in news media where images are frequently paired with bilingual (e…
So-Fake: Benchmarking and Explaining Social Media Image Forgery Detection
Zhenglin Huang, Xiangtai Li, Xi Yang +6
Recent advances in AI-powered generative models have enabled the creation of increasingly realistic synthetic images, posing significant risks to information integrity and public t…
BusterX: MLLM-Powered AI-Generated Video Forgery Detection and Explanation
Haiquan Wen, Yiwei He, Zhenglin Huang +7
As generative video models become increasingly realistic, detecting AI-generated videos requires systems that offer both accuracy and interpretability. However, applying Multimodal…
FALCON: Fine-grained Activation Manipulation by Contrastive Orthogonal Unalignment for Large Language Model
Jinwei Hu, Zhenglin Huang, Xiangyu Yin +4
Large language models have been widely applied, but can inadvertently encode sensitive or harmful information, raising significant safety concerns. Machine unlearning has emerged t…
SIDA: Social Media Image Deepfake Detection, Localization and Explanation with Large Multimodal Model
Zhenglin Huang, Jinwei Hu, Xiangtai Li +6
The rapid advancement of generative models in creating highly realistic images poses substantial risks for misinformation dissemination. For instance, a synthetic image, when share…
IPMix: Label-Preserving Data Augmentation Method for Training Robust Classifiers
Zhenglin Huang, Xiaoan Bao, Na Zhang +4
Data augmentation has been proven effective for training high-accuracy convolutional neural network classifiers by preventing overfitting. However, building deep neural networks in…