Hugging Face Trending Papers July 20, 2026

CoCurve: Cross-Module Co-Pruning Curvature for Training-Free Structured LLM Pruning

Read the original on Hugging Face Trending Papers →

Structured pruning compresses large language models (LLMs) by removing whole computational units, such as attention heads and feed-forward (FFN) channel groups. Most training-free methods, however, rank these units independently, implicitly treating the loss from pruning a set as the sum of its individual losses.

Summary generated by The Flow from the publisher's feed. The full article lives at Hugging Face Trending Papers.

arXiv AI

Jul 21

CoCurve: Cross-Module Co-Pruning Curvature for Training-Free Structured LLM Pruning

arXiv:2607. 17568v1 Announce Type: cross Abstract: Structured pruning compresses large language models (LLMs) by removing whole computational units, such as attention heads and feed-forward (FFN) channel groups.

By Zhiren Gong, Zihao Zeng, Zijie Wang, Tiantong Wang, Chau Yuen, Wei Yang Bryan Lim

llms fine-tuning efficiency benchmarks

arXiv Machine Learning

Jun 18

Complementary Attention Head Pruning for Efficient Transformers

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

llms nlp efficiency benchmarks safety

arXiv Machine Learning

Jul 21

NIRVANA: Structured Pruning Reimagined for Large Language Model Compression

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

llms fine-tuning efficiency benchmarks

arXiv Machine Learning

Aug 4

GPrune-LLM: Generalization-Aware Structured Pruning for Large Language Models

arXiv:2603. 13418v2 Announce Type: replace Abstract: Structured pruning is widely applied to compress large language models (LLMs), but its performance depends heavily on how neuron importance is estimated.

By Xiaoyun Liu, Divya Saxena, Jiannong Cao, Yuqing Zhao, Yiying Dong, Penghui Ruan

llms efficiency safety

arXiv AI

Jul 28

TriSP: Tri-Signal Structured Pruning for Large Language Models

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

llms fine-tuning efficiency

arXiv Machine Learning

Aug 11

High-Layer Attention Pruning with Rescaling

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

llms efficiency

Related stories

CoCurve: Cross-Module Co-Pruning Curvature for Training-Free Structured LLM Pruning

Complementary Attention Head Pruning for Efficient Transformers

NIRVANA: Structured Pruning Reimagined for Large Language Model Compression

GPrune-LLM: Generalization-Aware Structured Pruning for Large Language Models

TriSP: Tri-Signal Structured Pruning for Large Language Models

High-Layer Attention Pruning with Rescaling