arXiv AI June 17, 2026 By Pungponhavoan Tep, Marc Bernacki

Physics-Informed Attention Mechanism and Generalization Capability of Deep Learning-Based Grain Growth Evolution Prediction

arXiv:2606. 17235v1 Announce Type: cross Abstract: Machine Learning (ML) models for grain growth prediction are typically trained on idealized synthetic data, yet practical applications require generalization to conditions outside the training distribution.

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

fine-tuning

arXiv Machine Learning

2d ago

SPEAR: Structure Property Explainability with Attention Regularization

arXiv:2608. 13826v1 Announce Type: cross Abstract: Machine learning is increasingly used to learn structure property relationships from spectroscopic and diffraction data, yet its adoption in materials discovery is often limited by poor interpretability of model predictions.

By Aditya Raghavan, Utkarsh Pratiush, Dalton A. Pearl, Jade Holliman Jr, Katharine Page, Philip D Rack, Sergei V Kalinin

benchmarks safety

arXiv Machine Learning

Jun 9

AttentionCap: Transformer Based Capacitance Matrix Learning Toward Full-Chip Extraction

arXiv:2606. 08161v1 Announce Type: new Abstract: As capacitance extraction accuracy of rule-based pattern matching becomes difficult to sustain at advanced nodes, a growing trend emerges to develop deep-learning-based 2D capacitance models.

By Jiechen Huang, Hector R. Rodriguez, Dingcheng Yang, Zuochang Ye, Yibo Lin, Wenjian Yu

llms rag fine-tuning efficiency

arXiv AI

Jun 2

DLLM-JEPA: Joint Embedding Predictive Architectures for Masked Diffusion Language Models

arXiv:2606. 00091v1 Announce Type: cross Abstract: Joint Embedding Predictive Architectures (JEPAs) have reshaped self-supervised representation learning in vision.

By Sangdae Nam

llms rag diffusion fine-tuning benchmarks

arXiv Machine Learning

Aug 6

Towards Physics of Multimodal Pretraining: Knowledge Flow, Modality Synergy, Early Unification, and Recipes

arXiv:2608. 05000v1 Announce Type: cross Abstract: Vision offers a critical axis for advancing foundation models, driving a shift towards natively unified multimodal pretraining.

By Junlin Han, Shengbang Tong, David Fan, Minghao Chen, Philip Torr, Filippos Kokkinos, Mike Lewis

nlp multimodal safety

arXiv AI

1d ago

Focusing by Contrastive Attention: Enhancing VLMs' Visual Reasoning

arXiv:2509. 06461v3 Announce Type: replace-cross Abstract: Vision-Language Models (VLMs) have demonstrated remarkable success across diverse visual tasks, yet their performance degrades in complex visual environments.

By Yuyao Ge, Shenghua Liu, Yiwei Wang, Lingrui Mei, Baolong Bi, Xuanshan Zhou, Jiayu Yao, Jiafeng Guo, Xueqi Cheng

llms computer-vision multimodal

arXiv AI

Jul 22

A Controlled Study of Attention-Only Transformers

arXiv:2607. 18363v1 Announce Type: cross Abstract: Feed-forward networks hold two thirds of a transformer's non-embedding parameters, yet the architecture has not received a necessity test that controls parameters, compute, and depth at once.

By Henry Ndubuaku, Karen Mosoyan, Jakub Mroz, Noah Cylich, Satyajit Kumar, Parkirat Sandhu, Roman Shemet, Justin H Lee

llms rag

Related stories

SPEAR: Structure Property Explainability with Attention Regularization

AttentionCap: Transformer Based Capacitance Matrix Learning Toward Full-Chip Extraction

DLLM-JEPA: Joint Embedding Predictive Architectures for Masked Diffusion Language Models

Towards Physics of Multimodal Pretraining: Knowledge Flow, Modality Synergy, Early Unification, and Recipes

Focusing by Contrastive Attention: Enhancing VLMs' Visual Reasoning

A Controlled Study of Attention-Only Transformers