cd/entity/Multimodal large language models· home› entities› Multimodal large language models

grep -l @multimodal large language models /news/*.json | wc -l → 1

Multimodal large language models

mentions 1 type Person feed RSS

// recent coverage 1 mentions

04:00

2026-06-26

arxiv.org

large-language-models

Staying VIGILant: Mitigating Visual Laziness via Counterfactual Visual Alignment in MLLMs

Researchers propose VIGIL, a reinforcement-learning post-training framework that reduces hallucinations in multimodal large language models by maximizing mutual information between visual input and ge…

// co-occurs with top 4 entities

VIGIL 1 Large language models 1 Direct preference optimization 1 Reinforcement learning 1