Shuo Wang

GuardAlign: Test-time Safety Alignment in Multimodal Large Language Models

Leveraging MLLMs for Zero-Shot Action Recognition: Concise, Discriminative and anti-Hallucination Prompting

Look Carefully: Adaptive Visual Reinforcements in Multimodal Large Language Models for Hallucination Mitigation

SignAligner: Harmonizing Complementary Pose Modalities for Coherent Sign Language Generation

SeViCES: Unifying Semantic-Visual Evidence Consensus for Long Video Understanding

DAMA: Data- and Model-aware Alignment of Multi-modal LLMs

Enhancing CLIP Robustness via Cross-Modality Alignment