3 papers
cs.CV2026
RemoteShield: Enable Robust Multimodal Large Language Models for Earth Observation
Rui Min, Liang Yao, Shiyu Miao +5
A robust Multimodal Large Language Model (MLLM) for Earth Observation should maintain consistent interpretation and reasoning under realistic input variations. However, current Rem…
cs.AI2026
OOD-MMSafe: Advancing MLLM Safety from Harmful Intent to Hidden Consequences
Ming Wen, Kun Yang, Jingyu Zhang +4
While safety alignment for Multimodal Large Language Models (MLLMs) has gained significant attention, current paradigms primarily target malicious intent or situational violations.…
cs.CL2025
PEO: Improving Bi-Factorial Preference Alignment with Post-Training Policy Extrapolation
Yuxuan Liu
The alignment of large language models with human values presents a critical challenge, particularly when balancing conflicting objectives like helpfulness and harmlessness. Existi…