重新审视大模型剪枝后微调的必要性，挑战复杂剪枝标准，提出更高效的压缩策略。
arXiv:2510.14444v3 Announce Type: replace Abstract: Post-training pruning can substantially reduce LLM inference costs, but it often degrades quality …
跨模型代理剪枝巧妙兼顾低延迟与高精度，解决长上下文LLM推理中KV缓存内存墙难题
arXiv:2605.16360v1 Announce Type: new Abstract: Efficient long-context inference in Large Language Models (LLMs) is severely constrained by the Key-Va…
揭秘MoE大模型预训练中剪枝与蒸馏技术，SlimQwen优化效率与性能。
arXiv:2605.08738v2 Announce Type: replace Abstract: Structured pruning and knowledge distillation (KD) are typical techniques for compressing large la…
提出LEAP可学习端到端自适应剪枝方法，在保持大语言模型性能的同时实现高效压缩
arXiv:2605.17289v1 Announce Type: new Abstract: Unstructured sparsity is now natively accelerated by recent GPU kernels and dataflow hardware, shiftin…
提出运行时自适应剪枝方法，让LLM推理内存动态调整，效率大增
arXiv:2505.17138v5 Announce Type: replace Abstract: Large language models (LLMs) excel at language understanding and generation, but their enormous co…
探究任务感知剪枝如何提升模型在分布外数据上的表现，揭示内在机制
arXiv:2605.14738v1 Announce Type: cross Abstract: Recent work has promoted task-aware layer pruning as a way to improve model performance on particula…
提出新型结构化剪枝方法，实现大模型高效压缩同时保持鲁棒性，适合模型优化研究者
arXiv:2605.18331v1 Announce Type: new Abstract: Large Language Models (LLMs) have experienced significant growth and development in recent years. Howe…
提出Ghosted Layers，无需训练即可恢复层剪枝后LLM的性能，通过激活对齐解决隐藏状态不匹配问题。
arXiv:2605.15491v1 Announce Type: cross Abstract: Layer pruning removes entire Transformer decoder blocks from large language models, but introduces a…
无需手动筛选视觉令牌，LRCP利用低秩可压缩性自动剪枝，大幅提升LVLMs推理效率，尤其适合高分辨率图像与长视频场景。
arXiv:2605.15621v1 Announce Type: new Abstract: Large vision-language models (LVLMs) achieve strong multimodal understanding, but their inference cost…