proomt

Search

Search posts, papers, and topics

All posts

Hugging Face Daily PapersFedor Rodionov, Aleksandar Cvejic, Michael Birsak1 min readpaperadvanced

Architect-Ant: Editable Automatic Furnishing of Architectural Floor Plans

Read on arxiv.org

Summary

Architect-Ant is a framework for editable automatic furnishing of architectural floor plans, trained on AntPlan, a new dataset of 505 professional plans. It learns professional furnishing patterns and optimizes layouts using geometric and functional constraints, resulting in realistic designs with low violation rates.

  • Introduces AntPlan, a curated dataset of 505 real professional architectural floor plans with dense furniture annotations.
  • Architect-Ant learns professional furnishing patterns through supervised fine-tuning on the AntPlan dataset.
  • Optimizes layouts using GRPO with a Layout Rule Score (LRS) that aggregates geometric and functional constraints.
  • Generates editable, coordinate-based layouts that closely reflect real-world residential furnishing patterns.

This work is relevant for architects, interior designers, and real estate professionals looking to automate and enhance the realism of floor plan furnishing processes.

8/10
machine learningarchitecturecomputer visionaigenerative aidesign

Related reading

  1. ANTMAN: Adaptive Need Tracking for Multi-Agent Navigation in Large Information Spaces

    ANTMAN is an adaptive coordination framework that tracks unresolved information needs via a Need Graph, allowing agents to route work and recover locally as evidence accumulates. Experiments show it scales to 16× larger contexts with only 1.23× coordination overhead, far less than static partition baselines, while keeping answer quality high.

    Hugging Face Daily Papersarxiv.org1 minpaper

  3. Designer-RSI: Evolving Procedural Memory from User Traffic for Agentic Graphic Design

    The paper introduces Designer‑RSI, a continual‑adaptation system that couples a frozen design‑software‑controlling LLM with an external procedural memory of natural‑language design skills. Over five adaptation rounds on real user briefs, the memory grows from 76 to 139 procedures and lifts execution success from 72.7% to 99.3%, showing that skill accumulation and selective replay can dramatically…

    Hugging Face Daily Papersarxiv.org1 minpaper

  5. Recursive self-improvement of AI research agents

    The paper introduces AIDE², an AI research agent that rewrites its own code, benchmarks each version, and adopts the best performing changes—a process they call recursive self‑improvement. In an 8‑day autonomous run it produced seven improvements that beat a strong human‑engineered baseline on four unseen benchmarks and reduced reward‑hacking from 55 % to 32 %.

    Hugging Face Daily Papersarxiv.org2 minpaperHN31