ReCo, a lightweight DPO-trained linear head that re-injects pooled image embeddings at every step, reduces hallucination on five benchmarks across three VLMs and combines with existing mitigation methods.
Visual instruction tun- ing
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
ReCo: Reminder Composition Mitigates Hallucinations in Vision-Language Models
ReCo, a lightweight DPO-trained linear head that re-injects pooled image embeddings at every step, reduces hallucination on five benchmarks across three VLMs and combines with existing mitigation methods.