← Search

Caiyong Piao

2 accepted papers

2026

Deep Residual Injection for Full-Spectrum Forensic Signal Perception in Multimodal Large Language Models

ICML 2026poster

Multimodal large language models (MLLMs) have been increasingly adopted in forensics for their robust semantic understanding. As AI-generated images become realistic, semantic-level inconsistencies alone are often insufficient for reliable detection. This motivates a critical question: *whether MLLM…

Cited by 0SourceScholar
2026

Towards Policy-Adaptive Image Guardrail: Benchmark and Method

CVPR 2026

Accurate rejection of sensitive or harmful visual content, i.e., harmful image guardrail, is critical in many application scenarios. This task must continuously adapt to the evolving safety policies and content across various domains and over time. However, traditional classifiers, confined to fixed

Cited by 0SourceScholar