grounding diagnostics 1object hallucination 1selective correction 1verifier-guided decoding 1vision-language models 1
From the 1 of 1 linked paper with an AI index.
Showing cs.CVShow all
2 papers · 1 filter
cs.CV2026
AdaptiveEmbed: Sample-Adaptive Multi-Vector Representation for Multimodal Retrieval
Xinze Liu, Lei Yang, Dayan Wu +7
Multi-vector representations have emerged as an effective paradigm for multimodal retrieval, representing each sample with multiple complementary embeddings to capture fine-grained…
cs.CV2026
Hallucinations Leave a Grounding Signature:Verifier-Guided Decoding for Selective Object Correction
Lei Yang, Xinze Liu, Dayan Wu +7
The paper introduces a method to detect and correct hallucinated objects in large vision‑language models by identifying a hidden grounding pattern and using a lightweight verifier…