Nov 2026
EQA-CL: a scene-disjoint benchmark for continual question answering from embodied observations
Wen-Tao Shang, Wen-Bo Hu, Miao Fan et al.
· Multimedia Systems · 0 citations
We have 2 of 14 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
This paper shows for the first time that visual token pruning enhances the robustness of Multimodal Large Language Models (MLLMs), mitigating vulnerabilities such as jailbreak attacks and hallucinations, and maintains strong results on general datasets like MME.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.