Xinfeng Li

3

Papers

85

Total Citations

Papers (3)

MMAR: A Challenging Benchmark for Deep Reasoning in Speech, Audio, Music, and Their Mix

NeurIPS 2025arXiv

Heuristic-Induced Multimodal Risk Distribution Jailbreak Attack for Multimodal Large Language Models

Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment