iGEN
Visit IGEN World Explore IGEN Expo
EXPLORE UPGRADE PLANS
BREAKING
Robot Learning Reveals Emergent 'Self' Subnetwork in Continual Learning Studies New Book on Optimal Transport Offers Machine Learning Practitioners a Unified Framework Lightweight Distillation of SAM 3 and DINOv3 for Edge-Deployable Livestock Monitoring Varanasi to Host 2-Day Wheat Products Promotion Society CEO's Conclave from July 9 Uncertainty Quality of VGGT: Analysis on DTU Benchmark Dataset Reveals Effective Confidence Threshold for 3D Reconstruction New Diffusion Model Learns Permutation Distributions with Softer, More Tractable Trajectories RidgeCut: Reinforcement Learning Framework Optimizes Logistics Network Partitioning with Rings and Wedges SDS-LoRA: New Low-Rank Adaptation Method Fixes Gradient Distortion in Large Model Fine-Tuning NeuronFabric Architecture Cuts Memory for On-Chip Transformer Training, Promises Efficient Edge AI Kharif Pulses Sowing Off to a Weak Start: Acreage Down 43% as of June 12 Robot Learning Reveals Emergent 'Self' Subnetwork in Continual Learning Studies New Book on Optimal Transport Offers Machine Learning Practitioners a Unified Framework Lightweight Distillation of SAM 3 and DINOv3 for Edge-Deployable Livestock Monitoring Varanasi to Host 2-Day Wheat Products Promotion Society CEO's Conclave from July 9 Uncertainty Quality of VGGT: Analysis on DTU Benchmark Dataset Reveals Effective Confidence Threshold for 3D Reconstruction New Diffusion Model Learns Permutation Distributions with Softer, More Tractable Trajectories RidgeCut: Reinforcement Learning Framework Optimizes Logistics Network Partitioning with Rings and Wedges SDS-LoRA: New Low-Rank Adaptation Method Fixes Gradient Distortion in Large Model Fine-Tuning NeuronFabric Architecture Cuts Memory for On-Chip Transformer Training, Promises Efficient Edge AI Kharif Pulses Sowing Off to a Weak Start: Acreage Down 43% as of June 12
Home ›› Topics ›› gradients

Topic

gradients

2 stories
Beyond Weights and Gradients: New Taxonomy Classifies Federated Learning Messages into Three Categories Technology
Artificial Intelligence #federated learning#machine learning

Beyond Weights and Gradients: New Taxonomy Classifies Federated Learning Messages into Three Categories

A research paper by Guerrero, Vargas, Wang, Doan, and Nagels introduces a formal mathematical definition of a federated message and a taxonomy organizing exchanges into three categories: model structures, statistical summaries, and data-conditioned representations. The authors review 202 publications, noting a shift since 2021 toward diverse messaging paradigms beyond traditional weights and gradients, and evaluate trade-offs in computational demands, communication costs, and privacy risks.

Jun 16, 2026 1 source
ReGrad: A New AI Paradigm for Continual Learning Without Catastrophic Forgetting Technology
Artificial Intelligence #machine learning#continual learning

ReGrad: A New AI Paradigm for Continual Learning Without Catastrophic Forgetting

A new paper introduces ReGrad (Retrievable Gradients), a paradigm for continual post-training that pre-computes document-specific gradients, stores them in a Gradient Bank, and retrieves query-relevant gradients at inference time for temporary weight adaptation. The method uses bi-level meta-learning to reshape gradients into generalizable signals, outperforming CPT and RAG baselines in experiments.

Jun 16, 2026 1 source