6 papers
Learn from Whoever Is Right: Answer-Verified Multi-Teacher Distillation for Multi-Domain LLMs
Xixiang He, Xingming Li, Baiqi Wu +4
Modern large language models (LLMs) rely on reinforcement learning to build strong capabilities in individual domains, but integrating those capabilities into a single deployable m…
Multi2AV-Safety: Benchmarking Safety in Multimodal-to-Audio-Video Generation
Kaichao Jiang, Changtao Miao, Baiqi Wu +9
Audio-video generation is rapidly moving from prompt-driven synthesis toward multimodal conditioning, where text, images, audio, and video can jointly shape the generated output. T…
Order within Chaos: Capturing Intrinsic Energy Anomalies for AI-Manipulated Image Forgery Localization
Yiming Wang, Baiqi Wu, Qingming Li +3
Recent advancements in generative AI have led to image editing models capable of producing realistic forgeries that evade traditional image forgery localization methods, as these a…
StemBind: When MLLMs Get Lost Between Rules and Instances in Abstract Visual Reasoning
Xixiang He, Baiqi Wu, Xingming Li +4
Multimodal large language models (MLLMs) often know the rule but pick the wrong answer: on abstract visual reasoning (AVR) tasks, a model can describe what it sees and name the und…
TASAR: Transfer-based Attack on Skeletal Action Recognition
Yunfeng Diao, Baiqi Wu, Ruixuan Zhang +5
Skeletal sequence data, as a widely employed representation of human actions, are crucial in Human Activity Recognition (HAR). Recently, adversarial attacks have been proposed in t…
Boosting Adversarial Transferability for Skeleton-based Action Recognition via Exploring the Model Posterior Space
Yunfeng Diao, Baiqi Wu, Ruixuan Zhang +3
Skeletal motion plays a pivotal role in human activity recognition (HAR). Recently, attack methods have been proposed to identify the universal vulnerability of skeleton-based HAR(…