6 papers
Governing Execution Risk in Agentic AI Systems: A Trajectory-Guided Framework for Red Teaming
Zhihao Zhu, Yi Yang
AI agents are increasingly embedded in organizational workflows, where they interact with external information sources and invoke digital tools to perform operational tasks. As org…
Revealing Training Data Exposure in Vision Language Large Models via Parameter Gradients
Zhihao Zhu, Hongyi Tang, Yi Yang +1
Vision-Language Large Models (VLLMs) trained on massive crawled corpora raise pressing copyright and data-provenance concerns. These concerns are particularly acute in healthcare,…
DistractMIA: Black-Box Membership Inference on Vision-Language Models via Semantic Distraction
Hongyi Tang, Zhihao Zhu, Yi Yang
Vision-language models (VLMs) are trained on large-scale image-text corpora that may contain private, copyrighted, or otherwise sensitive data, motivating membership inference as a…
Perception Without Engagement: Dissecting the Causal Discovery Deficit in LMMs
Jiafeng Liang, Zhihao Zhu, Zihan Zhang +7
Although Large Multimodal Models (LMMs) have achieved strong performance on general video understanding, their susceptibility to textual prior shortcuts during causal discovery has…
Analyzing Reasoning Consistency in Large Multimodal Models under Cross-Modal Conflicts
Zhihao Zhu, Jiafeng Liang, Shixin Jiang +5
Large Multimodal Models (LMMs) have demonstrated impressive capabilities in video reasoning via Chain-of-Thought (CoT). However, the robustness of their reasoning chains remains qu…
AI Meets Brain: Memory Systems from Cognitive Neuroscience to Autonomous Agents
Jiafeng Liang, Hao Li, Chang Li +12
Memory serves as the pivotal nexus bridging past and future, providing both humans and AI systems with invaluable concepts and experience to navigate complex tasks. Recent research…