arXiv Machine Learning June 9, 2026 By Tom Devynck, Bilal Faye, Djamel Bouchaffra, Nadjib Lazaar, Hanane Azzag, Mustapha Lebbah

Energy-Regularized Spatial Masking: A Novel Approach to Enhancing Robustness and Interpretability in Vision Models

Read the original on arXiv Machine Learning →

arXiv:2604. 06893v3 Announce Type: replace-cross Abstract: Deep convolutional neural networks achieve remarkable performance by exhaustively processing dense spatial feature maps, yet this brute-force strategy introduces significant computational redundancy and encourages reliance on spurious background correlations.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

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 AI

Jul 10

When Structured Sparse Autoencoders Learn Consistent Concepts Across Modalities

arXiv:2607. 08605v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) have emerged as a promising technique for mechanistic interpretability by learning a set of sparse latent features in large models, each of which encodes a distinct concept.

By Weiduo Liao, Yunqiao Yang, Ying Wei

llms efficiency multimodal safety

arXiv Machine Learning

Aug 11

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

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.

By Parham Sazdar, Mostafa Tavassolipour, Reshad Hosseini

fine-tuning efficiency benchmarks safety

arXiv AI

Aug 11

Three Necessary Principles for Self-Supervised Visual Representation Learning

arXiv:2608. 08309v1 Announce Type: cross Abstract: We argue that learning visual representations without labels requires a training signal jointly complete across three non-overlapping objectives: semantic invariance across augmented views, patch-level spatial prediction, and representational non-degeneracy.

By Nikos Giakoumoglou, Paschalis Giakoumoglou, Tania Stathaki

safety

arXiv Machine Learning

Aug 5

SRAP: SVD-Refined Adversarial Perturbations for Imperceptible Face-Swap Defense

arXiv:2608. 03395v1 Announce Type: cross Abstract: Deepfake technologies pose increasing threats to facial privacy and identity security, motivating proactive defenses that protect facial images before misuse.

By Sungwon Cho, Kwanghyun Ko, Myungjoo Kang

safety

arXiv AI

Aug 12

Hybrid Token Compression for Vision-Language Models

arXiv:2512. 08240v2 Announce Type: replace-cross Abstract: Vision-language models (VLMs) rely on hundreds of visual tokens, leading to high computational and memory costs.

By Jusheng Zhang, Xiaoyang Guo, Tongyu Mo, Qinhan Lv, Wenhao Chai, Jian Wang, Keze Wang, Liang Lin

llms efficiency multimodal benchmarks

Related stories

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

When Structured Sparse Autoencoders Learn Consistent Concepts Across Modalities

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

Three Necessary Principles for Self-Supervised Visual Representation Learning

SRAP: SVD-Refined Adversarial Perturbations for Imperceptible Face-Swap Defense

Hybrid Token Compression for Vision-Language Models