pith. sign in

Beyond size: How gradients shape pruning decisions in large language models

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

fields

cs.LG 2

years

2025 2

verdicts

UNVERDICTED 2

representative citing papers

RAP: Runtime Adaptive Pruning for LLM Inference

cs.LG · 2025-05-22 · unverdicted · novelty 5.0

RAP is a reinforcement learning framework for runtime-adaptive pruning of LLMs that jointly optimizes model weights and KV-cache usage under varying memory budgets.

citing papers explorer

Showing 2 of 2 citing papers.