Showing 2026Show all
2 papers · 1 filter
cs.AI2026
Offline-Online Curriculum RL for Multimodal Reasoning
Wendi Deng, Hang Du, Guoshun Nan +11
Multimodal large language models exhibit capabilities on reasoning tasks, yet often produce flawed intermediate steps while yielding correct final answers. This behavior undermines…
cs.CV2026
Covert Visual Prompt Injection against Commercial Multimodal Large Language Models
Meiwen Ding, Song Xia, Chenqi Kong +1
Although multimodal large language models (MLLMs) are increasingly deployed in real-world applications, their instruction-following behavior leaves them vulnerable to prompt inject…