paper-with-me

Graph Generation

1개 벤치마크 · 논문 831편 · 이 태스크의 논문 보기 →

Benchmarks

Toulouse Road Network

결과 6개

Most implemented

Papers

When Evidence Shapes Collaboration: Knowledge-Conditioned Topology Generation for Multi-Agent Systems

2026-08-28 · Yangxiao Jiang, Jiarun Fan, Mingcong Xu, Yanxi Guo 외 arxiv

Multi-Agent Systems (MAS) have recently moved from static workflows toward dynamically generated collaboration topologies. However, existing topology generation methods rely primarily on the parametric knowledge of large…

Graph Generation

Gromov-Monge Flow Matching for Equivariant Graph Generation

2026-08-27 · Moritz Piening, Christian Wald arxiv

Graphs are invariant under node permutations, motivating the use of permutation-equivariant architectures in generative models. In flow matching, however, symmetry may also enter the source--target coupling: once graph p…

Graph Generation

Diffusion Transformers for Roof Graph Synthesis and Reconstruction

2026-08-26 · Daniel Panangian, Ksenia Bittner arxiv

We present RoofDiT, a generative framework for 2D roof graph synthesis and reconstruction. Roofs are compactly described as planar graphs of junctions and structural edges, but existing methods often rely on fixed geomet…

Graph Generation

Reward-Guided Autoregressive Graph Generation for Efficient Multi-Agent Communication Topology Design

2026-08-20 · Poomphob Suwannapichat, Boonyarit Changaival, Caesar Wu, Pascal Bouvry arxiv

LLM-based Multi-Agent Systems (MAS) achieve strong performance on complex reasoning tasks by coordinating multiple agents, but at the cost of substantial token consumption. Recent work on automatic topology design, ARG-D…

Reinforcement LearningGraph Generation

GraphK: Variable-Size Graph Generation with Efficient Edge Construction

2026-08-19 · Resul Tugay, Eren Oluğ, Elif Ak, Sule Gunduz Oguducu arxiv

Graph generation models have advanced significantly with deep learning, yet they remain limited in scalability, flexibility, and ability to model underlying structures. We present GraphK, a novel encoder-sampler-decoder …

Computational EfficiencyGraph Generation

FRAGMENT: Factorized Graph Representations for Document Generation and Editing via Entity-Aware Transformations

2026-08-19 · Ayoub El Bouchtili, Guilhaume Leroy-Meline arxiv

Structured documents such as invoices, forms, reports, and scientific articles derive meaning from the interplay between spatial layout, textual content, and logical structure. Generative models operating at the pixel or…

Graph Generation

전체 831편 보기 →