This paper proposes an improved structured pruning method for large language models (LLMs) that addresses key challenges in adapting Adaptive Feature Retention (AFR), an unstructured pruning technique, to structured pruning. When applying AFR to structured pruning, three major problems arise: distribution mismatch between heterogeneous pruning scores, loss of sign information indicating optimization direction consistency, and influence of outliers.
arXiv:2510. 00192v3 Announce Type: replace Abstract: Low-rank adaptation (LoRA) has become a widely used paradigm for parameter-efficient fine-tuning of large language models, yet its representational capacity often lags behind full fine-tuning.
By Xin Yu, Cong Xie, Xunmei Liu, Tiantian Fan, Lingzhou Xue, Zhi Zhang
arXiv:2606. 19150v1 Announce Type: new Abstract: The remarkable success of Transformer-based models in natural language processing stems from architectural scaling, which leads to a large number of parameters and hinders deployment in resource-constrained environments.
By Yaniv Livertovsky, Shahar Somin, Gonen Singer
arXiv:2507. 01900v3 Announce Type: replace-cross Abstract: Pruning is a highly effective approach for compressing large language models (LLMs), significantly reducing inference latency.
By Songtao Liu, Peng Liu
arXiv:2607. 22587v1 Announce Type: new Abstract: Large language models (LLMs) achieve strong performance across diverse tasks but their deployment is constrained by the memory and compute cost of their parameters.
By Manel Kara laoua, Soumia Bouyahiaoui, Aicha Boutorh
arXiv:2509. 14230v2 Announce Type: replace Abstract: While structured pruning presents a highly effective pathway for accelerating Large Language Model (LLM) inference, existing methods frequently suffer from significant performance degradation and demand computationally retraining to recover capabilities.
By Mengting Ai, Tianxin Wei, Sirui Chen, Jingrui He
arXiv:2608. 06630v1 Announce Type: new Abstract: Pruning reduces the inference cost of large language models, but existing criteria primarily preserve large activations or reconstruct layer outputs.
By Linghao Kong, Inimai Subramanian, Micah Adler, Dan Alistarh, Dan Gutfreund, Nir Shavit
Sparsely activated Mixture-of-Experts (MoE) language models contain substantial structured redundancy among routed experts, but pruning them without downstream calibration data remains challenging. Existing expert-pruning methods typically rely on a single aggregated importance score, which can bias the retained set toward experts favored by dominant calibration patterns.
arXiv:2606. 01544v1 Announce Type: new Abstract: Deploying Large Language Models (LLMs) in practice incurs substantial memory and computational costs.
By Cheonjun Park
arXiv:2607. 01710v1 Announce Type: new Abstract: Sparsely activated Mixture-of-Experts (MoE) language models contain substantial structured redundancy among routed experts, but pruning them without downstream calibration data remains challenging.
By Yongqin Zeng, Sicheng Pan, Jiale Wang, Hai-tao Zheng, Hong-Gee Kim, Chunxia Ma, XiuTeng Zhou
Deploying Large Language Models (LLMs) in practice incurs substantial memory and computational costs. Post-training pruning (PTP) is an effective approach to reducing these costs by removing weights without additional training.
arXiv:2605. 14738v3 Announce Type: replace-cross Abstract: Recent work has promoted task-aware layer pruning as a way to improve model performance on particular tasks, as shown by TALE.
By Krish Sharma, Omar Naim, Soumadeep Saha, Vinija Jain, Aman Chadha, Nicholas Asher