← Search

Mahdieh Baghshah

2 accepted papers

2026

HaloProbe: Bayesian Detection and Mitigation of Object Hallucinations in Vision-Language Models

ICML 2026poster

Large vision-language models can produce object hallucinations in image descriptions, highlighting the need for effective detection and mitigation strategies. Prior work commonly relies on the model's attention weights on visual tokens as a detection signal. We reveal that coarse-grained attention-b…

Cited by 0SourceScholar
2026

Uncovering Grounding IDs: How External Cues Shape Multi-Modal Binding

ICML 2026poster

Large vision–language models (LVLMs) perform well on multimodal tasks, but their ability to reason and precisely align visual and textual information still has room for improvement. In this study, we show that external visual cues, such as symbols or grid lines, help LVLMs form more accurate connect…

Cited by 0SourceScholar