← Search

Songping Wang

2 accepted papers

2026

Exposing and Defending the Achilles' Heel of Video Mixture-of-Experts

ICLR 2026poster

Mixture-of-Experts (MoE) has demonstrated strong performance in video understanding tasks, yet its adversarial robustness remains underexplored. Existing attack methods often treat MoE as a unified architecture, overlooking the independent and collaborative weaknesses of key components such as route…

Cited by 0SourcecodeScholar
2026

RunawayEvil: Jailbreaking the Image-to-Video Generative Models

CVPR 2026

Image-to-Video (I2V) generation represents a frontier in content creation, where models synthesize dynamic visual sequences by jointly reasoning from both image and text prompts. This multimodal grounding enables diverse controllability over video attributes. However, it is precisely this capability

Cited by 0SourcecodeScholar