LAMIC: Layout-Aware Multi-Image Composition via Scalability of Multimodal Diffusion Transformer

Source

  • Person key: alfredyao
  • Source kind: paper
  • Canonical URL: https://arxiv.org/abs/2508.00477
  • License: NOASSERTION
  • Public handling: public-metadata-summary-hash-link-only
  • Semantic hash: 367944518de20b4bb94f209fd11b11b51f47388f30faa4f128156a819b3e2260
  • First seen: 2026-05-16
  • Last changed: 2026-05-16
  • Identity guard: Do not confuse with yao-shunyu-ysymyth, the OpenAI language-agents researcher at ysymyth.github.io.

Classification

Summary

In controllable image synthesis, generating coherent and consistent images from multiple references with spatial layout awareness remains an open challenge. We present LAMIC, a Layout-Aware Multi-Image Composition framework that, for the first time, extends single-reference diffusion models to multi-reference scenarios in a training-free manner. Built upon the MMDiT model, LAMIC introduces two plug-and-play attention mechanisms: 1) Group Isolation Attention (GIA) to enhance entity disentanglement; and 2) Region-Mod…

What This Teaches

How learning, planning, and feedback loops shape agent behavior and model capability.

Public Handling Notes

  • EXTRACTED: Metadata and links are from public sources.
  • INFERRED: Unclear-license full text, PDFs, and source code should not be mirrored into public wiki pages.
  • AMBIGUOUS: Items discovered by keyword search are still separated by source identity and category heuristics.