A TPE-guided search over layer-wise pruning ratios and KV cache bit-widths compresses LLaVA-1.5 7B/13B with small accuracy loss, outperforming Wanda and SparseGPT on most tested benchmarks.
Automated knowl- edge distillation via monte carlo tree search,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Enhancing Large Multimodal Models with Adaptive Sparsity and KV Cache Compression
A TPE-guided search over layer-wise pruning ratios and KV cache bit-widths compresses LLaVA-1.5 7B/13B with small accuracy loss, outperforming Wanda and SparseGPT on most tested benchmarks.