Nikolaos Pappas

Cross-Modal Content Optimization for Steering Web Agent Preferences

Capturing Gaze Shifts for Guidance: Cross-Modal Fusion Enhancement for VLM Hallucination Mitigation

Unraveling and Mitigating Safety Alignment Degradation of Vision-Language Models

DiverseAgentEntropy: Quantifying Black-Box LLM Uncertainty through Diverse Perspectives and Multi-Agent Interaction

Inference time LLM alignment in single and multidomain preference spectrum