arXiv Machine Learning June 2, 2026 By Dang Nguyen Hong, Nhi Ngoc-Yen Nguyen, Huy-Hieu Pham

MIC: Maximizing Informational Capacity in Adaptive Representations via Isotropic Subspace Alignment

Read the original on arXiv Machine Learning →

arXiv:2605. 29987v2 Announce Type: replace Abstract: Although multi-scales representation learning enables elastic-dimension embeddings, nested subspaces often suffer from dimensional redundancy and spectral collapse.

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 Computer Vision

Sep 10

Isotropic Embedding Perturbations for Robust Vision Language Encoders

arXiv:2609.10292v1 Announce Type: new Abstract: Data augmentation is fundamental to training modern deep vision and multimodal models. While individual methods, such as RandAug, CutMix, Mixup, RandEr...

By Hyesong Choi, Daeun Kim, Song Park, Taekyung Kim, Byeongho Heo, Sangdoo Yun, Dongbo Min, Dongyoon Han

llms rag diffusion multimodal safety

Hugging Face Trending Papers

Sep 9

Isotropic Embedding Perturbations for Robust Vision Language Encoders

Data augmentation is fundamental to training modern deep vision and multimodal models. While individual methods, such as RandAug, CutMix, Mixup, RandErase, and DropPath, offer strong regularization ef...

llms rag diffusion multimodal safety

arXiv AI

Sep 23

Understanding Hyperspherical Geometry of ECAPA-TDNN Embedding and Its Impact on Zero-Shot Voice Conversion

arXiv:2609.24688v1 Announce Type: cross Abstract: Angular-margin speaker encoders are widely used in voice conversion, yet the geometry of their classifier prototypes remains poorly understood. We an...

By Mathilde Abrassart, Nicolas Obin, Axel Roebel

rag

arXiv AI

Jun 8

Modality Gap-Driven Subspace Alignment Training Paradigm For Multimodal Large Language Models

arXiv:2602. 07026v3 Announce Type: replace-cross Abstract: Despite the success of multimodal contrastive learning in aligning visual and linguistic representations, a persistent geometric anomaly, the Modality Gap, remains: embeddings of distinct modalities expressing identical semantics occupy systematically offset regions.

By Xiaomin Yu, Yi Xin, Yuhui Zhang, Wenjie Zhang, Chonghan Liu, Hanzhen Zhao, Chen Liu, Xiaoxing Hu, Ziyue Qiao, Hao Tang, Xiaobin Hu, Chengwei Qin, Hui Xiong, Yu Qiao, Shuicheng Yan

llms rag fine-tuning multimodal safety

arXiv Machine Learning

Jul 23

IConE: Batch Independent Collapse Prevention for Self-Supervised Representation Learning

arXiv:2603. 15263v2 Announce Type: replace-cross Abstract: Self-supervised learning (SSL) has revolutionized representation learning, with Joint-Embedding Architectures (JEAs) emerging as an effective approach for capturing semantic features.

By Konstantinos Almpanakis, Anna Kreshuk

rag

arXiv Machine Learning

Sep 1

Diverse via bounded Agreement: Geometric Regularization for Multimodal Fusion

arXiv:2601.21670v4 Announce Type: replace-cross Abstract: Multimodal fusion is often treated as an optimization-balancing problem, where training signals are adjusted to prevent one modality from dom...

By Zixuan Xia, Hao Wang, Pengcheng Weng, Yanyu Qian, Yangxin Xu, William Dan, Fei Wang

rag multimodal benchmarks safety

One email a morning, machine-written

Related stories

Isotropic Embedding Perturbations for Robust Vision Language Encoders

Isotropic Embedding Perturbations for Robust Vision Language Encoders

Understanding Hyperspherical Geometry of ECAPA-TDNN Embedding and Its Impact on Zero-Shot Voice Conversion

Modality Gap-Driven Subspace Alignment Training Paradigm For Multimodal Large Language Models

IConE: Batch Independent Collapse Prevention for Self-Supervised Representation Learning

Diverse via bounded Agreement: Geometric Regularization for Multimodal Fusion