Pruning（剪枝）是机器学习模型优化技术，通过移除冗余参数来减小模型大小、提高推理效率。随着大型语言模型(LLMs)的广泛应用，Pruning技术正成为平衡模型性能与资源消耗的关键手段。
Pruning
general · 首次出现 2026-05-22 · 最近出现 2026-10-23 · 累计提及 57
综述
相关报道
10 条在档- RLCP：用校准剪枝让序列推荐的动作集随会话动态伸缩arXiv cs.AI
- 当剪枝遇到可解释性：在LLMs中保持稀疏自动编码器鲁棒性arXiv cs.LG
- 公平性剪枝：通过差分激活定位GLU-MLP层中的人口统计偏见arXiv cs.LG
- Direct Pass@$k$ Optimization for Thought Pruning: Balancing Quality and Diversity in Test-Time ReasoningarXiv cs.AI
- Stochastic Pruning of the DPO Computation Graph: 1.4x Faster Training and Lower Peak MemoryarXiv cs.LG
- SliMOO: Interpretable Multi-Objective Evolutionary Search for LLM Depth PruningarXiv cs.LG
- TokenGate: Adapting LLMs for Fast and Memory-Efficient Prefill with Learned Token PruningarXiv cs.AI
- Are We Evaluating VLM Token Pruning Right? Looking Beyond Accuracy and Token CountarXiv cs.AI
- Two For The Price Of One: Curvature-Aware Pruning Preserves Influence Functions TooarXiv cs.LG
- Towards Automatically Pruning Logging Code with Coding Agents: How Far Are We?arXiv cs.AI