Research map / Architectures and efficiency / Pruning and efficient tuning
Computation and Memory-Efficient Model Compression with Gradient Reweighting
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes a computation- and memory-efficient pruning method for LLMs using gradient reweighting, based only on the abstract's stated motivation.
Problem
Pruning large language models is computationally and memory expensive, and existing optimization-based pruning methods require substantial resources.
Approach
Uses gradient reweighting to make LLM pruning both computation- and memory-efficient relative to optimization-based pruning methods; specific mechanism not stated in the available abstract.
Closest papers by meaning
- Targeted Low-rank Refinement: Enhancing Sparse Language Models with Precision (ICML 2025 · similarity 0.94)
- Learning Pruning-Friendly Networks via Frank-Wolfe: One-Shot, Any-Sparsity, And No Retraining (ICLR 2022 · similarity 0.92)
- “Learning-Compression” Algorithms for Neural Net Pruning (CVPR 2018 · similarity 0.92)
- SPDY: Accurate Pruning with Speedup Guarantees (ICML 2022 · similarity 0.92)
- The Journey Matters: Average Parameter Count over Pre-training Unifies Sparse and Dense Scaling Laws (ICLR 2025 · similarity 0.91)
- Sparsest Models Elude Pruning: An Exposé of Pruning’s Current Capabilities (ICML 2024 · similarity 0.91)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.