arXiv Machine Learning August 11, 2026 By Parham Sazdar, Mostafa Tavassolipour, Reshad Hosseini

Domain-Aware Pruning: Sparsity and Domain Generalization via Regularized Probabilistic Masking

Read the original on arXiv Machine Learning →

arXiv:2608. 08624v1 Announce Type: new Abstract: Domain generalization (DG) and neural network pruning are conventionally treated as distinct objectives, targeting out-of-distribution (OOD) robustness and model efficiency, respectively.

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 Machine Learning

Sep 1

MOONSHOT : A Framework for Multi-Objective Pruning of Vision and Large Language Models

arXiv:2604.13287v2 Announce Type: replace Abstract: Weight pruning is a common technique for compressing large neural networks. We focus on the challenging post-training one-shot setting, where a pre...

By Gabriel Afriat, Xiang Meng, Shibal Ibrahim, Hussein Hazimeh, Rahul Mazumder

llms efficiency benchmarks

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

arXiv Machine Learning

Aug 27

When Pruning Meets Interpretability: Preserving Sparse Autoencoder Robustness in LLMs

Sparse autoencoders (SAEs) are commonly used to interpret large language models, but their reliability after pruning is unclear. This study shows that pruning’s effect on an SAE is governed by perturbation energy, a covariance-weighted norm, and that magnitude pruning distorts the representation space by ignoring activation geometry. Activation-aware pruning methods such as Wanda and SparseGPT better preserve SAE behavior, and the authors find that middle layers are especially vulnerable, leading them to propose a layer‑wise sparsity allocation that reduces perplexity for a given sparsity level.

By Suchit Gupte, Xueru Zhang, Mohammad Mahdi Khalili

llms efficiency safety

arXiv Machine Learning

Aug 10

Prune Once: Retraining-Free Task-Agnostic Pruning for Vision-Language Models

arXiv:2608. 06901v1 Announce Type: cross Abstract: Vision-language models (VLMs) have achieved remarkable generalization across diverse multimodal tasks through large-scale pre-training, yet their rapidly increasing computational and memory requirements pose significant challenges for deployment in constrained environments.

By Minseok Kang, Hyunwoo Kim, Chanyoung Kim, Minwoo Kim, Jaekoo Lee, Dahuin Jung

llms efficiency multimodal

arXiv Machine Learning

Aug 10

The Sparsity Whisperer

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

llms efficiency multimodal

arXiv Computation and Language

Sep 15

Pruning as Regularization: Sensitivity-Aware One-Shot Pruning in ASR

arXiv:2511.08092v2 Announce Type: replace-cross Abstract: We challenge the conventional view of neural network pruning as solely a compression technique, demonstrating that one-shot magnitude pruning...

By Julian Irigoyen, Arthur S\"ohler, Andreas S{\o}eborg Kirkedal

fine-tuning efficiency multimodal

One email a morning, machine-written

Related stories

MOONSHOT : A Framework for Multi-Objective Pruning of Vision and Large Language Models

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

When Pruning Meets Interpretability: Preserving Sparse Autoencoder Robustness in LLMs

Prune Once: Retraining-Free Task-Agnostic Pruning for Vision-Language Models

The Sparsity Whisperer

Pruning as Regularization: Sensitivity-Aware One-Shot Pruning in ASR