arXiv Machine Learning
Jun 10
Compositional Generative Modeling from Decentralized Data
arXiv:2606. 10153v1 Announce Type: new Abstract: Learning the compositional nature of the physical world requires joint observation of interacting factors.
Decentralized Autoregressive Generation
arXiv:2601. 03184v3 Announce Type: replace-cross Abstract: The decentralization of autoregressive generation has attracted considerable attention in recent years as a solution to scaling bottlenecks.
Related stories
arXiv AI
Jun 16
Mosaic: Data-Free Knowledge Distillation via Mixture-of-Experts for Heterogeneous Distributed Environments
arXiv:2505. 19699v2 Announce Type: replace-cross Abstract: Federated Learning (FL) is a decentralized machine learning paradigm that enables clients to collaboratively train models while preserving data privacy.
arXiv AI
Jun 2
Heterogeneous Decentralized Diffusion Models
arXiv:2603. 06741v2 Announce Type: replace-cross Abstract: Training frontier-scale diffusion models often requires substantial computational resources concentrated in tightly-coupled clusters, limiting participation to well-resourced institutions.
arXiv Machine Learning
Aug 6
Stable GFlowNets with TV Monitoring and Probabilistic Guarantees
arXiv:2605. 01729v2 Announce Type: replace Abstract: Generative Flow Networks (GFlowNets) learn to sample states proportional to an unnormalized reward.
arXiv Machine Learning
Jun 16
Communication-Efficient Neural Tangent Kernels for Heterogeneous Decentralized Federated Learning
arXiv:2512. 12737v2 Announce Type: replace Abstract: Decentralized federated learning (DFL) enables collaborative model training without a central server, but converges slowly under statistical heterogeneity.
arXiv Machine Learning
Jun 2
Exploring and Exploiting Stability in Latent Flow Matching
arXiv:2605. 08398v2 Announce Type: replace Abstract: In this work, we show that Latent Flow-Matching (LFM) models are robust to different types of perturbations, including data reduction and model capacity shrinkage.
arXiv AI
Jul 9
Collaborative Synthetic Data Generation for Knowledge Transfer in Federated Learning
arXiv:2607. 07565v1 Announce Type: cross Abstract: One-shot federated learning (OSFL) addresses the communication overhead of federated learning by limiting training to a single round, but doing so without sacrificing model quality is non-trivial, particularly when client data distributions diverge.
arXiv AI
Jul 7
Decentralised Federated Learning over Temporal Networks: The Role of Heterogeneities
arXiv:2607. 03171v1 Announce Type: cross Abstract: Decentralised federated learning, based on peer-to-peer communication, is increasingly proposed for on-device training of machine learning models, promising a privacy-preserving, communication-efficient training process with no risk of single-point failure.
arXiv Machine Learning
Jun 3
DECA: Decentralizing Block-Wise Adam for Efficient LLM Full-Parameter Fine-Tuning on Non-IID Data
arXiv:2606. 03209v1 Announce Type: new Abstract: Fine-tuning large language models (LLMs) in privacy-sensitive and resource-constrained environments remains challenging.
Hugging Face Trending Papers
Jul 8
Collaborative Synthetic Data Generation for Knowledge Transfer in Federated Learning
One-shot federated learning (OSFL) addresses the communication overhead of federated learning by limiting training to a single round, but doing so without sacrificing model quality is non-trivial, particularly when client data distributions diverge. Recent work has addressed this challenge by aggregating client knowledge on the server through the construction of transferable synthetic datasets or distillates.
arXiv AI
Jun 16
Beyond Weights and Gradients: A Taxonomy of Federated Learning Messages
arXiv:2606. 16891v1 Announce Type: cross Abstract: Federated Learning is rapidly evolving beyond the exchange of traditional model weights and gradients, yet existing definitions fail to capture the full scope of modern payloads like synthetic data and federated analytics.
arXiv Machine Learning
Aug 3
Paris: A Decentralized Trained Open-Weight Diffusion Model
arXiv:2510. 03434v3 Announce Type: replace-cross Abstract: We present Paris, the first publicly released diffusion model pre-trained entirely through decentralized computation.