Hugging Face Trending Papers June 25, 2026

Cascaded Multi-Granularity Pruning for On-Device LLM Inference in Industrial IoT

Read the original on Hugging Face Trending Papers →

Deploying large language models (LLMs) on Industrial Internet of Things (IIoT) edge devices demands extreme compression, yet existing structured pruning methods collapse at high compression ratios due to one-shot importance estimation, and their cross-architecture behavior remains unpredictable. This article presents a cascaded multi-granularity pruning framework that removes layers, attention heads, and feed-forward channels in coarse-to-fine order, with lightweight low-rank recovery between stages to re-estimate component importance.

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

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 AI

Jul 28

Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization

arXiv:2607. 22583v1 Announce Type: new Abstract: Large Language Models (LLMs) have achieved widespread adoption because of their strong reasoning and query-response capabilities.

By Muhammad Junaid Ali, Smail Niar, El-Ghazali Talbi

llms efficiency

arXiv AI

Jun 2

From Layers to Submodules: Rethinking Granularity in Replacement-Based LLM Compression

arXiv:2606. 02559v1 Announce Type: cross Abstract: Post-training compression of Large Language Models (LLMs) removes entire architectural components, either deleting them or replacing them with fitted modules.

By Elia Cunegatti, Marcus Vukojevic, Erik Nielsen, Giovanni Iacca

llms efficiency

arXiv AI

Jun 18

Attribution-Guided and Coverage-Maximized Pruning for Structural MoE Compression

arXiv:2606. 18304v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) models scale compute efficiently, yet remain expensive to deploy due to their substantial memory footprint and inference overhead.

By Yifu Ding, Jiacheng Wang, Ge Yang, Yongcheng Jing, Jinyang Guo, Xianglong Liu, Dacheng Tao

efficiency benchmarks

arXiv AI

Jun 24

Lightweight Transformer Models for On-Device Fault Detection: A Benchmark Study on Resource-Constrained Deployment

arXiv:2606. 24173v1 Announce Type: cross Abstract: On-device fault detection enables real-time diagnostics without cloud dependency, but deploying machine learning models on resource-constrained hardware demands careful tradeoffs between accuracy, latency, and model size.

By Disha Patel

llms efficiency benchmarks

arXiv Machine Learning

Jul 14

Prune, Update and Trim: Robust Structured Pruning for Large Language Models

arXiv:2605. 18331v2 Announce Type: replace Abstract: Large Language Models (LLMs) have experienced significant growth and development in recent years.

By Diego Coello de Portugal Mecke, Tom Hanika, Lars Schmidth-Thieme

llms efficiency benchmarks

Related stories

TriSP: Tri-Signal Structured Pruning for Large Language Models

Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization

From Layers to Submodules: Rethinking Granularity in Replacement-Based LLM Compression

Attribution-Guided and Coverage-Maximized Pruning for Structural MoE Compression

Lightweight Transformer Models for On-Device Fault Detection: A Benchmark Study on Resource-Constrained Deployment

Prune, Update and Trim: Robust Structured Pruning for Large Language Models