Token readout choice confounds POPE VLM hallucination scores
A two-token yes/no logit lookup never matches LLaVA-1.5-7B outputs, shifting adversarial F1 by 6.13 points.
Stories per day · 30 days
2 RSS
3 stories, newest first · one card per story
Stories tagged #llava
Cross-modal triggers activate backdoors in multimodal LLMs
From a backdoor in one modality, the method builds a trigger in another without poisoning that modality during training.
NeuronEye: Query-Guided Visual Concept Activation for Vision-Language Reasoning
NeuronEye activates query-relevant visual concepts in frozen VLMs, lifting Qwen2.5-VL-7B CV-Bench by 3.1 points.