arXiv Machine Learning June 30, 2026 By Andy Li, Aiden Durrant, Milan Markovic, Georgios Leontidis

HiAP: A Multi-Granular Stochastic Auto-Pruning Framework for Vision Transformers

Read the original on arXiv Machine Learning →

arXiv:2603. 12222v2 Announce Type: replace-cross Abstract: Vision Transformers require significant computational resources and memory bandwidth, severely limiting their deployment on resource-constraint hardware.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv AI

Jun 3

PrimeSVT: An Automated Memory-aware Pruning Framework with Prioritized Compression Policy for Spiking Vision Transformers

arXiv:2606. 03428v1 Announce Type: cross Abstract: The large sizes of Spiking Vision Transformers (SViTs) still hinder their embedded implementation, highlighting the need for model compression.

By Rachmad Vidya Wicaksana Putra, Achyuta Muthuvelan, Alberto Marchisio, Muhammad Shafique

llms fine-tuning efficiency benchmarks

arXiv AI

Jun 3

PSViT: A Methodology for Structurally Pruning Spiking Vision Transformers

arXiv:2606. 03257v1 Announce Type: cross Abstract: Spiking Vision Transformer (SViT) models are promising low-power ViT models for solving vision-based tasks with state-of-the-art performance.

By Rachmad Vidya Wicaksana Putra, Achyuta Muthuvelan, Alberto Marchisio, Muhammad Shafique

llms computer-vision fine-tuning efficiency benchmarks

arXiv Machine Learning

Jul 31

WIDE: Boosting Adaptive LLM Inference via Token-level Dynamic Width Pruning

arXiv:2607. 28418v1 Announce Type: cross Abstract: Pruning is a promising approach for improving the efficiency of LLMs.

By Haozhe Hu, Hao Wu, Peiran Yin, Chao Han, Yunpu Ma, Xiaoyu Shen

llms nlp efficiency benchmarks

arXiv AI

Aug 7

APQF: Agentic Profiling-Guided Structured Pruning and Mixed-Precision Quantization with Adaptive Fine-Tuning

arXiv:2608. 05499v1 Announce Type: cross Abstract: Modern deep neural networks achieve strong performance, but their scale makes them costly and slow, especially on resource-constrained edge devices.

By Sadegh Jafari, Mohiuddin Bilwal, Fan Zhou, Brian Gelder, Ali Jannesari

llms agents fine-tuning efficiency

arXiv AI

Jun 9

RAPID: Layer-Wise Redundancy-Aware Pruning and Importance-Driven Token Merging for Efficient ViT

arXiv:2606. 08156v1 Announce Type: cross Abstract: Vision Transformers (ViTs) achieve strong performance but suffer from high computational costs due to quadratic self-attention complexity.

By Kyumin Choi, Ikbeom Jang

llms efficiency

arXiv Computer Vision

Sep 10

One Loop, Two Gains: Can Active Learning win the Lottery for Free?

arXiv:2609.10311v1 Announce Type: cross Abstract: The lottery ticket hypothesis posits the existence of winning tickets: sparse subnetworks that, when trained in isolation from their original initial...

By Benedikt Tscheschner, Eduardo Veas, Marc Masana

computer-vision fine-tuning efficiency

One email a morning, machine-written

Related stories

PrimeSVT: An Automated Memory-aware Pruning Framework with Prioritized Compression Policy for Spiking Vision Transformers

PSViT: A Methodology for Structurally Pruning Spiking Vision Transformers

WIDE: Boosting Adaptive LLM Inference via Token-level Dynamic Width Pruning

APQF: Agentic Profiling-Guided Structured Pruning and Mixed-Precision Quantization with Adaptive Fine-Tuning

RAPID: Layer-Wise Redundancy-Aware Pruning and Importance-Driven Token Merging for Efficient ViT

One Loop, Two Gains: Can Active Learning win the Lottery for Free?