arXiv Machine Learning June 15, 2026 By Yash Tomar, Aryav Das

PostDeg: Placement Beats Parameterization in LayerNorm GNNs

Read the original on arXiv Machine Learning →

arXiv:2606. 14022v1 Announce Type: new Abstract: LayerNorm-based GNNs routinely erase the topology signals (degree, centrality, $k$-core) that node-selection policies should depend on, but the literature has not located where in the residual block the erasure happens.

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

arXiv Machine Learning

Aug 11

Placing Degree Scales After LayerNorm

arXiv:2606. 14022v3 Announce Type: replace Abstract: Graph neural networks (GNNs) are widely used to learn node-selection policies on graphs, and most stack graph attention (GAT) blocks with LayerNorm.

By Yash Vardhan Tomar, Aryav Das

arXiv AI

Jul 21

Exact Network Surgery: Functional Invariance and Gradient Plasticity in Reactive Computational Graphs

arXiv:2607. 16568v1 Announce Type: new Abstract: Function-preserving network growth techniques such as Net2Net and progressive stacking expand a model's capacity without destroying its learned function, but existing formulations either tolerate numerical perturbations or require a full rebuild of the training program.

By Abdallah Khemais (ISITCOM, University of Sousse)

arXiv Machine Learning

Jul 10

Uncertainty-gated selection for block-sparse attention

arXiv:2607. 07724v1 Announce Type: new Abstract: Block-sparse attention scales long-context language models by replacing the O(N^2) softmax with a per-query top-k selection over key blocks.

By Thomas Rossi

llms

arXiv Machine Learning

Jun 8

Reversible Foundations: Training a 120B Sparse MoE through State-Preserving Scaling

arXiv:2606. 07404v1 Announce Type: new Abstract: This paper reports on training a hundred-billion-parameter sparse mixture of experts on a single eight-GPU node, end to end.

By Rohan Shravan

llms nlp efficiency

arXiv AI

Jun 15

When the Tool Decides: LLM Agents Defer Blindly to Graph Neural Network Tools, and Stronger Backbones Defer More

arXiv:2606. 14476v1 Announce Type: new Abstract: A growing line of work equips large language model (LLM) agents with graph neural networks (GNNs) as callable tools, assuming the agent exercises judgment over when and how much to rely on such a tool.

By Zhongyuan Wang, Pratyusha Vemuri

llms agents

arXiv Machine Learning

Jun 25

Pre-Warm: Input-Conditioned Weight Initialization for Convolutional Neural Networks

arXiv:2606. 25256v1 Announce Type: cross Abstract: We introduce Pre-Warm, a simple yet effective zero-training-cost method for data-conditioned initialization of the first convolutional layer.

By Rowan Martnishn

benchmarks

Related stories

Placing Degree Scales After LayerNorm

Exact Network Surgery: Functional Invariance and Gradient Plasticity in Reactive Computational Graphs

Uncertainty-gated selection for block-sparse attention

Reversible Foundations: Training a 120B Sparse MoE through State-Preserving Scaling

When the Tool Decides: LLM Agents Defer Blindly to Graph Neural Network Tools, and Stronger Backbones Defer More

Pre-Warm: Input-Conditioned Weight Initialization for Convolutional Neural Networks