KV-cache compression
Woodpecker: Hallucination Correction for Multimodal Large Language Models
Cited as a baseline — critiqued by newer work, not yet beaten on a benchmark here
1 papers critique it · 0 beat it on benchmarks
Verbatim critique sentences, each from a paper that cites WoodPecker as a baseline.
WoodPecker~yin2024woodpecker introduces an additional visual model to monitor and ask the original model to regenerate hallucinated contents
Recent methods in the same sub-problem, not yet superseded in the knowledge base — arXiv benchmark leaders, not vetted production recommendations.