KV-cache compression
OPERA: Alleviating Hallucination in Multi-Modal Large Language Models via Over-Trust Penalty and Retrospection-Allocation
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 OPERA as a baseline.
However, all above mentioned works introduce additional computational overhead, thus slows down model inference speed.
Recent methods in the same sub-problem, not yet superseded in the knowledge base — arXiv benchmark leaders, not vetted production recommendations.