Papers › Tell2Design: A Dataset for Language-Guided Floor Plan Generation

Tell2Design: A Dataset for Language-Guided Floor Plan Generation

27 Nov 2023arXiv:2311.15941archive 2025-07-28

Sicong Leng, Yang Zhou, Mohammed Haroon Dupty, Wee Sun Lee, Sam Conrad Joyce, Wei Lu

We consider the task of generating designs directly from natural language descriptions, and consider floor plan generation as the initial research area. Language conditional generative models have recently been very successful in generating high-quality artistic images. However, designs must satisfy different constraints that are not present in generating artistic images, particularly spatial and relational constraints. We make multiple contributions to initiate research on this task. First, we introduce a novel dataset, \textit{Tell2Design} (T2D), which contains more than $80k$ floor plan designs associated with natural language instructions. Second, we propose a Sequence-to-Sequence model that can serve as a strong baseline for future research. Third, we benchmark this task with several text-conditional image generation models. We conclude by conducting human evaluations on the generated samples and providing an analysis of human performance. We hope our contributions will propel the research on language-guided design generation forward.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2311.15941")

Code

Syntology Ran 23 of 28 code samples harvested from 2 repositories linked to this paper; 5 have no recorded run. Of those that ran: 1 ran · honoured contract; 5 ran · violated contract; 4 ran · our draft was wrong; 1 ran · fixture could not drive it; 12 ran with no contract checked.

By repository: official repository: 28 samples from 2 repositories, 23 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

lucidrains/imagen-pytorch officialmentioned in papermentioned on GitHubpytorchMIT report
lengsicong/tell2design officialmentioned in paperjax report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

28 samples harvested; 23 ran; 1 honoured the contract we drafted; 5 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · honoured contract
5ran · violated contract
4ran · our draft was wrong
1ran · fixture could not drive it
12ran
5unverified

Licence: 15 of the 28 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; each sample names its own and says which. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

divisible_by lucidrains/imagen-pytorch/imagen_pytorch/imagen_pytorch.py official repository ran · violated contract fingerprinted MIT (permissive) · 856d86b39c6005b4 · report
identity lucidrains/imagen-pytorch/imagen_pytorch/imagen_pytorch.py official repository ran · honoured contract MIT (permissive) · 7f1040f5e3991d5e · report
log lucidrains/imagen-pytorch/imagen_pytorch/elucidated_imagen.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · b5472673332de78e · report
ListOrTuple lucidrains/imagen-pytorch/imagen_pytorch/configs.py official repository ran MIT (permissive) · 8f6d9d0f20f4a0fe · report
add_fp16_config_args lengsicong/tell2design/CogView/arguments.py official repository ran no licence file found · pointer only · c1c8ca756efcd3a8 · report
add_training_args lengsicong/tell2design/CogView/arguments.py official repository ran no licence file found · pointer only · b9f1927b5c7a63ff · report
b_cubed lengsicong/tell2design/T5/coreference_metrics.py official repository ran no licence file found · pointer only · 2d71e2917845b6ac · report
calculate_activation_statistics lengsicong/tell2design/CogView/eval_utils/fid_score.py official repository ran · our draft was wrong no licence file found · pointer only · 177298ecedde13ed · report
calculate_frechet_distance lengsicong/tell2design/CogView/eval_utils/fid_score.py official repository ran · fixture could not drive it no licence file found · pointer only · 25ef415d07e43e6f · report
cast_tuple lucidrains/imagen-pytorch/imagen_pytorch/trainer.py official repository ran fingerprinted MIT (permissive) · efcd80d66cfe5bcb · report
cluster_pixel_values lengsicong/tell2design/CogView/calculate_iou.py official repository ran no licence file found · pointer only · f48bf8f24cd43d0d · report
convert_image_to lucidrains/imagen-pytorch/imagen_pytorch/data.py official repository ran MIT (permissive) · a47706b35198fab3 · report
default lucidrains/imagen-pytorch/imagen_pytorch/configs.py official repository ran · violated contract fingerprinted MIT (permissive) · 60fff7c3c400d7ff · report
default lucidrains/imagen-pytorch/imagen_pytorch/t5.py official repository ran · violated contract MIT (permissive) · 915fbeb88e13d4a3 · report
exists lucidrains/imagen-pytorch/imagen_pytorch/configs.py official repository ran · violated contract MIT (permissive) · aa5486a3650902d8 · report
first lucidrains/imagen-pytorch/imagen_pytorch/imagen_video.py official repository ran · violated contract MIT (permissive) · 3072294c9b32cf4b · report
generate_mask lengsicong/tell2design/CogView/calculate_iou.py official repository ran no licence file found · pointer only · 30f6580c44acf787 · report
generate_one_dim_mask lengsicong/tell2design/CogView/calculate_iou.py official repository ran no licence file found · pointer only · bb6a9d219a5135af · report
get_activations lengsicong/tell2design/CogView/eval_utils/fid_score.py official repository ran · our draft was wrong no licence file found · pointer only · eb21740d88a30ecb · report
get_images_dataloader lucidrains/imagen-pytorch/imagen_pytorch/data.py official repository ran MIT (permissive) · f9f6d29329b5bf0d · report
init_method_normal lengsicong/tell2design/CogView/model/gpt2_modeling.py official repository ran · our draft was wrong no licence file found · pointer only · 6bcca529f47d7b8e · report
safeget lucidrains/imagen-pytorch/imagen_pytorch/utils.py official repository ran MIT (permissive) · 42a39b682ff0811f · report
to_python_float lengsicong/tell2design/CogView/fp16/loss_scaler.py official repository ran no licence file found · pointer only · 6b5d363ab4dbf012 · report
add_model_config_args lengsicong/tell2design/CogView/arguments.py official repository unverified no licence file found · pointer only · 655c169bb5832528 · report
evaluate_documents lengsicong/tell2design/T5/coreference_metrics.py official repository unverified no licence file found · pointer only · 44ea1242eeeb38ac · report
f1 lengsicong/tell2design/T5/coreference_metrics.py official repository unverified no licence file found · pointer only · 5dc251a1bb16c94f · report
get_tokenizer lucidrains/imagen-pytorch/imagen_pytorch/t5.py official repository unverified MIT (permissive) · 4af30ae5e0b7d6ca · report
inception_score lengsicong/tell2design/CogView/eval_utils/inception_score.py official repository unverified no licence file found · pointer only · 4a633463b941a5da · report

Tasks

Conditional Image GenerationImage Generation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections