MANSION: Multi-floor lANguage-to-3D Scene generatIOn for loNg-horizon tasks | Signal Canvas | ScienceToStartup

← Back to Paper

MANSION: Multi-floor lANguage-to-3D Scene generatIOn for loNg-horizon tasks

Stale68d agoVerification pending / evidence receipt incomplete

Export Brief Open in Build Loop Connect with Author

Viability

0.0/10

Compared to this week’s papers

Verification pending

Use This Via API or MCP

Use Signal Canvas as the narrative proof surface

Signal Canvas is the citation-first public layer for turning one paper into a structured commercialization narrative. Use it to hand off into REST, MCP, Build Loop, and launch-pack execution without losing source lineage.

Signal Canvas API Paper Proof Page Open Build Loop Launch Pack Example

Use This Via API or MCP

Use this Signal Canvas via API or MCP

Route this paper proof surface into REST, MCP, or developer workflows while preserving the same evidence receipt and related-resource context.

Signal Canvas guide REST guide MCP guide

Page Freshness

Signal Canvas proof surface

Canonical route: /signal-canvas/mansion-multi-floor-language-to-3d-scene-generation-for-long-horizon-tasks

stale

Proof freshness: stale
Proof status: unverified
Display score: 8/10
Last proof check: 2026-04-02
Score updated: 2026-04-02
Score fresh until: 2026-05-02
References: 0
Source count: 0
Coverage: 17%

This page is showing the last landed evidence receipt and score bundle because the latest proof data is outside the freshness window.

Agent Handoff

MANSION: Multi-floor lANguage-to-3D Scene generatIOn for loNg-horizon tasks

Canonical ID mansion-multi-floor-language-to-3d-scene-generation-for-long-horizon-tasks | Route /signal-canvas/mansion-multi-floor-language-to-3d-scene-generation-for-long-horizon-tasks

REST example

curl https://sciencetostartup.com/api/v1/agent-handoff/signal-canvas/mansion-multi-floor-language-to-3d-scene-generation-for-long-horizon-tasks

MCP example

{
  "tool": "search_signal_canvas",
  "arguments": {
    "mode": "paper",
    "paper_ref": "mansion-multi-floor-language-to-3d-scene-generation-for-long-horizon-tasks",
    "query_text": "Summarize MANSION: Multi-floor lANguage-to-3D Scene generatIOn for loNg-horizon tasks"
  }
}

source_context

{
  "surface": "signal_canvas",
  "mode": "paper",
  "query": "MANSION: Multi-floor lANguage-to-3D Scene generatIOn for loNg-horizon tasks",
  "normalized_query": "2603.11554",
  "route": "/signal-canvas/mansion-multi-floor-language-to-3d-scene-generation-for-long-horizon-tasks",
  "paper_ref": "mansion-multi-floor-language-to-3d-scene-generation-for-long-horizon-tasks",
  "topic_slug": null,
  "benchmark_ref": null,
  "dataset_ref": null
}

Paper mode· single-doc scopescope: mansion-multi-floor-language-to-3d-scene-generation-for-long-horizon-tasks

Preparing verified analysis

GitHub Code Pulse

No public code linked for this paper yet.

Claim map

Strong 8Mixed 0Weak 0

Evidencepartial
We introduce MANSION, the first language-driven framework for generating building-scale, multi-floor 3D environments.
Implicationpartial
Explicitly stated in the abstract with definitive language
Verificationpartial
partial
Evidencepartial
existing embodied benchmarks are largely confined to single-floor in-house environments, failing to reflect the complexity of real-world tasks.
Implicationpartial
Directly stated in the abstract as a limitation of current approaches
Verificationpartial
partial
Evidencepartial
MANSION generates realistic, navigable whole-building structures with diverse, human-friendly scenes
Implicationpartial
Directly stated in abstract with descriptive claims about capabilities
Verificationpartial
partial
Evidencepartial
enabling the development and evaluation of cross-floor long-horizon tasks.
Implicationpartial
Directly stated in abstract as a key capability of the framework
Verificationpartial
partial
Evidencepartial
we release MansionWorld, a dataset of over 1,000 diverse buildings ranging from hospitals to offices
Implicationpartial
Explicit numeric claim with specific examples provided
Verificationpartial
partial
Evidencepartial
Benchmarking reveals that state-of-the-art agents degrade sharply in our settings
Implicationpartial
Directly stated in abstract but without specific performance metrics
Verificationpartial
partial
Evidencepartial
alongside a Task-Semantic Scene Editing Agent that customizes these environments using open-vocabulary commands to meet specific user needs.
Implicationpartial
Directly stated in abstract with specific technical description
Verificationpartial
partial
Evidencepartial
Being aware of vertical structural constraints, MANSION generates realistic, navigable whole-building structures
Implicationpartial
Implied from description but not explicitly stated as a technical feature
Verificationpartial
partial