An entropy-based poisoning filter that mitigates task-agnostic backdoor attacks due to vulnerabilities in data and training mechanisms and injects multiple syntactic backdoors into the pre-training space through corpus poisoning, while preserving the PLM's pre-training capabilities.
Pengzhou Cheng, Wei Du, Zongru Wu et al.· North American Chapter of th...· 9 citations· ⚡3
MineExplorer benchmark for evaluating open-world exploration capabilities of MLLM agents in Minecraft is introduced, which first filter atomic tasks whose solutions rely heavily on Minecraft-specific knowledge to better reflect general open-world reasoning and compose atomic tasks into implicit multi-hop tasks.
Persuasion Duality is identified: reasoning enhances an agent's persuasive power while simultaneously increasing its resistance to persuasion, and a prompt-level adversarial argument detection method is proposed that consistently improves agent robustness.
This paper proposes UrbanGround, the first sandbox to make this question testable in a physically constrained replica of Hong Kong built from territory-wide 3D geospatial data, and hopes it will support broader study of how far current MLLM agents can explore reliably in complex, open-ended urban environments.
Tianjie Ju, Zheng Wu, Yue-Qing Sun et al.· 2 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
