arXiv AI July 7, 2026 By Shuai Li, Qinglin Wang, Ping Luo, Jiahuan Wang, Hongyang Hu, Haotian Mo, Yigui Feng, Ziang Liu, Qisong Xiao, Jie Liu, Tao Sun

FedACT: Federated Adaptive Coordinate Trust Modulation for Robust Transformer Training under Data Heterogeneity

Read the original on arXiv AI →

arXiv:2607. 03763v1 Announce Type: cross Abstract: Federated Transformer training increasingly relies on local AdamW, whose adaptive updates can provide much stronger local progress than SGD-based training.

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

arXiv Machine Learning

Jul 7

Trajectory-Aware Information Matching for Multi-Step Gradient Inversion in Federated Learning

arXiv:2509. 22082v3 Announce Type: replace Abstract: Federated learning enables distributed information sharing and collaborative model training without exposing raw client data.

By Li Xia, Jing Yu, Zheng Liu, Sili Huang, Wei Tang, Xuan Liu

benchmarks safety

arXiv AI

Jun 15

How do Self-Supervised Remote Sensing Vision Models Transfer to Downstream Tasks?

arXiv:2606. 13896v1 Announce Type: cross Abstract: Self-supervised geospatial foundation models (GeoFMs) learn transferable representations from remote sensing data, but their downstream behavior is difficult to characterize.

By Julia Romero, Qin Lv, Morteza Karimzadeh

llms rag computer-vision fine-tuning multimodal benchmarks

arXiv AI

Jul 7

Fusion: A Framework for Unified Sequential Token AdaptatIon in VisiOn TraNsformers

arXiv:2607. 02612v1 Announce Type: cross Abstract: Vision Transformers achieve strong image classification accuracy but process all image regions with nearly the same computation, even when many regions are redundant or uninformative.

By Aravind Pradeep, Samira Nazari, Mahdi Taheri, Christian Herglotz

llms computer-vision efficiency benchmarks

arXiv AI

Aug 3

Evaluating Federated Pre-Training: On the Reliability of Downstream Fine-Tuning and Intrinsic Evaluation

arXiv:2607. 28658v1 Announce Type: cross Abstract: Federated pre-training offers a way to train foundation models on private or distributed data without centralizing the underlying datasets.

By Claudia Grosser, Maike Heuer, Denis Krompass, Thomas A. Runkler

llms fine-tuning benchmarks

arXiv AI

Jun 4

Adaptive Patching Is Harder Than It Looks For Time-Series Forecasting

arXiv:2606. 04074v1 Announce Type: cross Abstract: Adaptive patching is a recent and compelling proposal for time-series Transformers: allocate finer patches where the sequence looks locally informative.

By Federico Zucchi, Yi Xie, Chao Zhang, Keyuan Luo, Thomas Lampert, Ziyue Li

llms benchmarks safety

arXiv Machine Learning

Jul 24

Spectral Transformation for Layer-wise Global Rank Discovery in Federated LoRA for Vision Transformers

arXiv:2607. 21074v1 Announce Type: new Abstract: Fine-tuning Vision Transformers (ViTs) with low-rank adapters (LoRA) promises better communication efficiency under federated setup, yet existing aggregation strategies face fundamental limitations.

By Hariharan Ramesh, Jyotikrishna Dass

llms diffusion fine-tuning

Related stories

Trajectory-Aware Information Matching for Multi-Step Gradient Inversion in Federated Learning

How do Self-Supervised Remote Sensing Vision Models Transfer to Downstream Tasks?

Fusion: A Framework for Unified Sequential Token AdaptatIon in VisiOn TraNsformers

Evaluating Federated Pre-Training: On the Reliability of Downstream Fine-Tuning and Intrinsic Evaluation

Adaptive Patching Is Harder Than It Looks For Time-Series Forecasting

Spectral Transformation for Layer-wise Global Rank Discovery in Federated LoRA for Vision Transformers