#graph-optimization News & Analysis

3 articles tagged with #graph-optimization. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.

3 articles

AIBullisharXiv – CS AI · May 297/10

🧠

PassNet: Scaling Large Language Models for Graph Compiler Pass Generation

PassNet introduces the first large-scale ecosystem for using large language models to generate compiler passes—structured graph transformations that optimize tensor compiler performance. The framework includes 18K computational graphs and 200 curated benchmark tasks, revealing that while LLMs lag frontier models by 37% on average, they achieve up to 3x speedups on individual workloads, indicating consistency rather than capability is the limiting factor.

AIBullisharXiv – CS AI · Jun 16/10

🧠

D$^3$: Dynamic Directional Graph-Constrained Data Scheduling for LLM Training

Researchers introduce D³, a novel data scheduling framework for LLM training that models interactions between training samples as a dynamic directional graph to optimize training order. The approach outperforms existing data scheduling methods while maintaining computational efficiency through an approximation algorithm.

AINeutralarXiv – CS AI · Mar 24/106

🧠

Optimization of Edge Directions and Weights for Mixed Guidance Graphs in Lifelong Multi-Agent Path Finding

Researchers propose Mixed Guidance Graph Optimization (MGGO) to improve multi-agent pathfinding systems by optimizing both edge directions and weights in guidance graphs. The paper introduces two MGGO methods, including one using Quality Diversity algorithms with neural networks, to provide stricter guidance for agent movement in lifelong scenarios.