Assistant Professor, Peking University
4 papers at NeurIPS 2025
An effective parameter-efficient model merging method for multimodal large language models from the perspective of direction robustness in low-rank space
We introduce MMOral, the first large-scale multimodal instruction dataset and benchmark tailored for panoramic X-ray interpretation. MMOral-Bench is a comprehensive evaluation suite covering five key diagnostic dimensions in dentistry.
We propose Spatial Adversarial Alignment (SAA), which leverages a witness model to fine-tune the surrogate model via spatial-aware and adversarial-aware alignment to generate highly transferable adversarial examples.
