arXiv Machine Learning July 7, 2026 By Filippo Biondi, Mirco Tribastone, Max Tschaikowski

Scaling Weisfeiler-Leman Expressiveness Analysis to Massive Graphs with GPUs

Read the original on arXiv Machine Learning →

arXiv:2607. 02603v1 Announce Type: cross Abstract: The stable coloring of the Weisfeiler-Leman (1-WL) test is a cornerstone of Graph Neural Networks because it provides an upper bound to the expressive power of message-passing architectures.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Jul 21

Taurus: Accelerating Out-of-Core Graph Neural Network Inference on Billion-Scale Graphs

arXiv:2607. 17374v1 Announce Type: cross Abstract: Graph Neural Network (GNN) inference on billion-scale graphs is challenging due to the large memory footprint of features and embeddings and high disk I/O costs in out-of-core settings.

By Pranjal Naman, Yogesh Simmhan

rag efficiency

arXiv Machine Learning

Jul 21

A Weisfeiler-Leman Characterization of Global-Attention Graph Transformers for Mixed-Integer Linear Programs

arXiv:2607. 17570v1 Announce Type: new Abstract: Graph foundation models (GFMs) with global attention are increasingly used to represent mixed-integer linear programs (MILPs), aiming to capture structure beyond the locality of standard graph neural networks.

By Md Abrar Jahin, Craig A. Knoblock, Jay Pujara

llms rag

arXiv Machine Learning

Sep 22

Reforge: Low-Latency Distributed GNN Serving with Selective Embedding Recomputation

arXiv:2501.08547v2 Announce Type: replace-cross Abstract: Graph Neural Networks (GNNs) have been widely adopted for their ability to compute expressive node representations in graph datasets. However...

By Geon-Woo Kim, Donghyun Kim, Jeongyoon Moon, Henry Liu, Tarannum Khan, Anand Iyer, Daehyeok Kim, Aditya Akella

rag benchmarks

arXiv Machine Learning

Jul 7

ParEVO: Synthesizing Code for Irregular Data: High-Performance Parallelism through Agentic Evolution

arXiv:2603. 02510v2 Announce Type: replace Abstract: The transition from sequential to parallel computing is essential for modern high-performance applications but is hindered by the steep learning curve of concurrent programming.

By Liu Yang, Zeyu Nie, Andrew Liu, Felix Zou, Deniz Altinb\"uken, Amir Yazdanbakhsh, Quanquan C. Liu

llms agents fine-tuning benchmarks

arXiv AI

Jun 4

CodegenBench: Can LLMs Write Efficient Code Across Architectures?

arXiv:2606. 04023v1 Announce Type: cross Abstract: While large language models (LLMs) have been extensively evaluated on code generation tasks for general-purpose programming and GPU-accelerated environments (e.

By Jie Li, Wenzhao Wu, Junqi Hu, Qinrui Zheng, Bowen Wu, Juepeng Zheng, Yutong Lu, Haohuan Fu

llms benchmarks

arXiv Machine Learning

Jul 1

GraphMend: Code Transformations for Fixing Graph Breaks in PyTorch 2

arXiv:2509. 16248v4 Announce Type: replace-cross Abstract: This paper presents GraphMend, a compiler technique that automatically fixes FX graph breaks in PyTorch 2 programs.

By Savini Kashmira, Jayanaka Dantanarayana, Thamirawaran Sathiyalogeswaran, Krisztian Flautner, Lingjia Tang, Jason Mars

One email a morning, machine-written

Related stories

Taurus: Accelerating Out-of-Core Graph Neural Network Inference on Billion-Scale Graphs

A Weisfeiler-Leman Characterization of Global-Attention Graph Transformers for Mixed-Integer Linear Programs

Reforge: Low-Latency Distributed GNN Serving with Selective Embedding Recomputation

ParEVO: Synthesizing Code for Irregular Data: High-Performance Parallelism through Agentic Evolution

CodegenBench: Can LLMs Write Efficient Code Across Architectures?

GraphMend: Code Transformations for Fixing Graph Breaks in PyTorch 2