EffiVLM-Bench is a benchmark study showing token compression is task- and model-dependent, KV cache methods are more loyal, and parameter compression preserves accuracy better at typical ratios.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
EffiVLM-BENCH: A Comprehensive Benchmark for Evaluating Training-Free Acceleration in Large Vision-Language Models
EffiVLM-Bench is a benchmark study showing token compression is task- and model-dependent, KV cache methods are more loyal, and parameter compression preserves accuracy better at typical ratios.