Wee Lee, Yang Zhou, Mohammed Dupty, Sicong Leng, Wei Lu, Sam Joyce
24 of 28 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 5 honoured the contract we drafted, 6 violated it and 0 have no contract verdict; 13 failures of our instrument; 4 no recorded run); 3 of them were also run on the host, not in the jail, by the peer-agreement lane that set their level, measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.
"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2311.15941.json · badge: /api/ran/2311.15941.svg
Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.
| Repository | Role | Ran |
|---|---|---|
| lengsicong/tell2design | canonical (classifier label) classifier basis: census |
12 ran · 3 no recorded run |
| lucidrains/imagen-pytorch | canonical (classifier label) classifier basis: census |
12 ran · 1 no recorded run |
| Function | Status | Where it lives |
|---|---|---|
| divisible_by | Ran ran, violated the contract we drafted |
lucidrains/imagen-pytorch/imagen_pytorch/imagen_pytorch.py code served (permissive licence) · get_code("856d86b39c6005b4") How it ranRan in Syntology's jail on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned bool, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. The comparison behind this sample's level is a different run: the peer-agreement lane ran it again on the host, not in the jail (report dated 2026-09-05T00:44:03Z). If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.
|
| identity | Ran ran, honoured the contract we drafted |
lucidrains/imagen-pytorch/imagen_pytorch/imagen_pytorch.py code served (permissive licence) · get_code("7f1040f5e3991d5e") How it ranRan in Syntology's jail on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned Tensor, ndim 2, dtype family float, shape (2, 4) as a later run recorded it. The image it ran in was not recorded. The comparison behind this sample's level is a different run: the peer-agreement lane ran it again on the host, not in the jail (report dated 2026-09-05T00:37:21Z). If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.
|
| log | Ran ran; our contract draft was wrong, not the code |
lucidrains/imagen-pytorch/imagen_pytorch/elucidated_imagen.py code served (permissive licence) · get_code("b5472673332de78e") How it ranRan in Syntology's jail on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned Tensor, ndim 2, dtype family float, shape (2, 4) as a later run recorded it. The image it ran in was not recorded. The comparison behind this sample's level is a different run: the peer-agreement lane ran it again on the host, not in the jail (report dated 2026-09-05T01:35:34Z). If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.
|
| ListOrTuple | Ran ran; our contract draft was wrong, not the code |
lucidrains/imagen-pytorch/imagen_pytorch/configs.py code served (permissive licence) · get_code("8f6d9d0f20f4a0fe") How it ranRan in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned _UnionGenericAlias. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.
|
| add_fp16_config_args | Ran ran; our contract draft was wrong, not the code |
lengsicong/tell2design/CogView/arguments.py pointer only (licence: NONE) · get_code("c1c8ca756efcd3a8") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, lengsicong/tell2design when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded. |
| add_training_args | Ran ran; our contract draft was wrong, not the code |
lengsicong/tell2design/CogView/arguments.py pointer only (licence: NONE) · get_code("b9f1927b5c7a63ff") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, lengsicong/tell2design when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded. |
| b_cubed | Ran ran, honoured the contract we drafted |
lengsicong/tell2design/T5/coreference_metrics.py pointer only (licence: NONE) · get_code("2d71e2917845b6ac") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, lengsicong/tell2design when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded. |
| calculate_activation_statistics | Ran ran; our contract draft was wrong, not the code |
lengsicong/tell2design/CogView/eval_utils/fid_score.py pointer only (licence: NONE) · get_code("177298ecedde13ed") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, lengsicong/tell2design when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded. |
| calculate_frechet_distance | Ran ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT) |
lengsicong/tell2design/CogView/eval_utils/fid_score.py pointer only (licence: NONE) · get_code("25ef415d07e43e6f") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, lengsicong/tell2design when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded. |
| cast_tuple | Ran ran, violated the contract we drafted |
lucidrains/imagen-pytorch/imagen_pytorch/trainer.py code served (permissive licence) · get_code("efcd80d66cfe5bcb") How it ranRan in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple, ndim 1, dtype family int; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.
|
| cluster_pixel_values | Ran ran; our contract draft was wrong, not the code |
lengsicong/tell2design/CogView/calculate_iou.py pointer only (licence: NONE) · get_code("f48bf8f24cd43d0d") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, lengsicong/tell2design when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded. |
| convert_image_to | Ran ran; our contract draft was wrong, not the code |
lucidrains/imagen-pytorch/imagen_pytorch/data.py pointer only (licence: MIT); the stored copy get_code serves, from edshkim98/localdiffusion-hallucination, is pointer only (licence: NONE) · get_code("a47706b35198fab3") How it ranThe body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from edshkim98/localdiffusion-hallucination, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded. |
| default | Ran ran, violated the contract we drafted |
lucidrains/imagen-pytorch/imagen_pytorch/configs.py pointer only (licence: MIT); the stored copy get_code serves, from ThomasMrY/VCT, is pointer only (licence: NONE) · get_code("60fff7c3c400d7ff") How it ranThe body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from ThomasMrY/VCT, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded. |
| default | Ran ran, violated the contract we drafted |
lucidrains/imagen-pytorch/imagen_pytorch/t5.py code served (permissive licence) · get_code("915fbeb88e13d4a3") How it ranRan in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned str. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.
|
| exists | Ran ran, violated the contract we drafted |
lucidrains/imagen-pytorch/imagen_pytorch/configs.py pointer only (licence: MIT); the stored copy get_code serves, from ThomasMrY/VCT, is pointer only (licence: NONE) · get_code("aa5486a3650902d8") How it ranThe body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from ThomasMrY/VCT, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded. |
| f1 | Ran ran, honoured the contract we drafted |
lengsicong/tell2design/T5/coreference_metrics.py pointer only (licence: NONE); the stored copy get_code serves, from sapienzanlp/bookcoref, is pointer only (licence: NONE) · get_code("5dc251a1bb16c94f") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, lengsicong/tell2design when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded. |
| first | Ran ran, violated the contract we drafted |
lucidrains/imagen-pytorch/imagen_pytorch/imagen_video.py code served (permissive licence) · get_code("3072294c9b32cf4b") How it ranRan in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned int, ndim 0, dtype family int, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.
|
| generate_mask | Ran ran; our contract draft was wrong, not the code |
lengsicong/tell2design/CogView/calculate_iou.py pointer only (licence: NONE) · get_code("30f6580c44acf787") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, lengsicong/tell2design when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded. |
| generate_one_dim_mask | Ran ran, honoured the contract we drafted |
lengsicong/tell2design/CogView/calculate_iou.py pointer only (licence: NONE) · get_code("bb6a9d219a5135af") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, lengsicong/tell2design when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded. |
| get_activations | Ran ran; our contract draft was wrong, not the code |
lengsicong/tell2design/CogView/eval_utils/fid_score.py pointer only (licence: NONE) · get_code("eb21740d88a30ecb") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, lengsicong/tell2design when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded. |
| get_images_dataloader | Ran ran; our contract draft was wrong, not the code |
lucidrains/imagen-pytorch/imagen_pytorch/data.py code served (permissive licence) · get_code("f9f6d29329b5bf0d") How it ranRan in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned DataLoader. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.
|
| init_method_normal | Ran ran; our contract draft was wrong, not the code |
lengsicong/tell2design/CogView/model/gpt2_modeling.py pointer only (licence: NONE) · get_code("6bcca529f47d7b8e") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, lengsicong/tell2design when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded. |
| safeget | Ran ran; our contract draft was wrong, not the code |
lucidrains/imagen-pytorch/imagen_pytorch/utils.py code served (permissive licence) · get_code("42a39b682ff0811f") How it ranRan in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned str. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.
|
| to_python_float | Ran ran, honoured the contract we drafted |
lengsicong/tell2design/CogView/fp16/loss_scaler.py pointer only (licence: NONE) · get_code("6b5d363ab4dbf012") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, lengsicong/tell2design when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded. |
| add_model_config_args | Not yet run unverified (harvested, no recorded run) |
lengsicong/tell2design/CogView/arguments.py pointer only (licence: NONE) · get_code("655c169bb5832528") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, lengsicong/tell2design when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded. |
| evaluate_documents | Not yet run unverified (harvested, no recorded run) |
lengsicong/tell2design/T5/coreference_metrics.py pointer only (licence: NONE) · get_code("44ea1242eeeb38ac") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, lengsicong/tell2design when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded. |
| get_tokenizer | Not yet run unverified (harvested, no recorded run) |
lucidrains/imagen-pytorch/imagen_pytorch/t5.py code served (permissive licence) · get_code("4af30ae5e0b7d6ca") How it ranno invocation recorded. |
| inception_score | Not yet run unverified (harvested, no recorded run) |
lengsicong/tell2design/CogView/eval_utils/inception_score.py pointer only (licence: NONE) · get_code("4a633463b941a5da") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, lengsicong/tell2design when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded. |
Of 28 samples lifted from this paper's linked repositories, 28 carry a function identity and 0 do not. Of the 28 distinct functions with an identity, 22 are also present in other papers whose code we hold (22 with at least one paper dated earlier, 9 the same month, 12 later) and 6 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).
Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.
| Function | Also present in | Earliest-dated | Others named |
|---|---|---|---|
| exists | 486 other papers 247 dated earlier, 14 the same month, 219 later, 4 same year, order not determinable, 2 undated · 78 only as an assembly brick |
1603.08155 (2016-03) Perceptual Losses for Real-Time Style Transfer and Super-Resolution |
1611.07004 (2016-11) Image-to-Image Translation with Conditional Adversarial Networks 1804.04637 (2018-04) EMBER: An Open Dataset for Training Static PE Malware Machine Learning Models and 483 more not named here |
| default | 163 other papers 104 dated earlier, 2 the same month, 55 later, 1 same year, order not determinable, 1 undated · 27 only as an assembly brick |
1603.08155 (2016-03) Perceptual Losses for Real-Time Style Transfer and Super-Resolution |
1810.00825 (2018-10) Set Transformer: A Framework for Attention-based Permutation-Invariant Neural Networks 1907.01470 (2019-07) Augmenting Self-attention with Persistent Memory and 160 more not named here |
| default | 79 other papers 29 dated earlier, 1 the same month, 49 later · 15 only as an assembly brick |
1611.07004 (2016-11) Image-to-Image Translation with Conditional Adversarial Networks |
2006.11239 (2020-06) Denoising Diffusion Probabilistic Models 2010.02502 (2020-10) Denoising Diffusion Implicit Models and 76 more not named here |
| calculate_frechet_distance | 74 other papers 47 dated earlier, 1 the same month, 25 later, 1 same year, order not determinable |
1610.09585 (2016-10) Conditional Image Synthesis With Auxiliary Classifier GANs |
1706.08500 (2017-06) GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium 1807.11458 (2018-07) To learn image super-resolution, use a GAN to learn how to do image degradation first and 71 more not named here |
| identity | 54 other papers 22 dated earlier, 31 later, 1 same year, order not determinable · 11 only as an assembly brick |
1611.07004 (2016-11) Image-to-Image Translation with Conditional Adversarial Networks |
1907.01470 (2019-07) Augmenting Self-attention with Persistent Memory 2006.11239 (2020-06) Denoising Diffusion Probabilistic Models and 51 more not named here |
| log | 22 other papers 11 dated earlier, 1 the same month, 10 later · 9 only as an assembly brick |
1611.07004 (2016-11) Image-to-Image Translation with Conditional Adversarial Networks |
1907.05242 (2019-07) Large Memory Layers with Product Keys 2203.07852 (2022-03) Block-Recurrent Transformers and 19 more not named here |
| divisible_by | 17 other papers 8 dated earlier, 9 later · 5 only as an assembly brick |
2006.11239 (2020-06) Denoising Diffusion Probabilistic Models |
2112.05682 (2021-12) Self-attention Does Not Need $O(n^2)$ Memory 2203.07852 (2022-03) Block-Recurrent Transformers and 14 more not named here |
| f1 | 12 other papers 8 dated earlier, 1 the same month, 3 later |
1804.05392 (2018-04) Higher-order Coreference Resolution with Coarse-to-fine Inference |
1907.10529 (2019-07) SpanBERT: Improving Pre-training by Representing and Predicting Spans 2021.naacl-main.125 (2021 (year only)) Incorporating Syntax and Semantics in Coreference Resolution with Heterogeneous Graph Attention Network and 9 more not named here |
| to_python_float | 9 other papers 8 dated earlier, 1 later |
1904.00962 (2019-04) Large Batch Optimization for Deep Learning: Training BERT in 76 minutes |
1909.03329 (2019-09) LAMOL: LAnguage MOdeling for Lifelong Language Learning 2109.04332 (2021-09) PPT: Pre-trained Prompt Tuning for Few-shot Learning and 6 more not named here |
| inception_score | 6 other papers 5 dated earlier, 1 later |
1610.00291 (2016-10) Deep Feature Consistent Variational Autoencoder |
2306.04675 (2023-06) Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion models 2308.04417 (2023-08) DiffCR: A Fast Conditional Diffusion Framework for Cloud Removal from Optical Satellite Images and 3 more not named here |
| first | 5 other papers 4 dated earlier, 1 later |
2204.06125 (2022-04) Hierarchical Text-Conditional Image Generation with CLIP Latents |
2303.11916 (2023-03) CompoDiff: Versatile Composed Image Retrieval With Latent Diffusion 2308.08157 (2023-08) Learning to Generate Semantic Layouts for Higher Text-Image Correspondence in Text-to-Image Synthesis and 2 more not named here |
| evaluate_documents | 4 other papers 3 dated earlier, 1 the same month |
1804.05392 (2018-04) Higher-order Coreference Resolution with Coarse-to-fine Inference |
2205.10475 (2022-05) DEEPSTRUCT: Pretraining of Language Models for Structure Prediction 2310.13774 (2023-10) Seq2seq is All You Need for Coreference Resolution and 1 more not named here |
| b_cubed | 3 other papers 2 dated earlier, 1 the same month |
2205.10475 (2022-05) DEEPSTRUCT: Pretraining of Language Models for Structure Prediction |
2310.13774 (2023-10) Seq2seq is All You Need for Coreference Resolution 2311.03748 (2023-11) Unified Low-Resource Sequence Labeling by Sample-Aware Dynamic Sparse Finetuning |
| calculate_activation_statistics | 3 other papers 2 dated earlier, 1 the same month |
1904.01310 (2019-04) DM-GAN: Dynamic Memory Generative Adversarial Networks for Text-to-Image Synthesis |
2202.04053 (2022-02) DALL-Eval: Probing the Reasoning Skills and Social Biases of Text-to-Image Generation Models 2311.06322 (2023-11) Post-training Quantization for Text-to-Image Diffusion Models with Progressive Calibration and Activation Relaxing |
| convert_image_to | 3 other papers 2 dated earlier, 1 later |
2305.16037 (2023-05) GenerateCT: Text-Conditional Generation of 3D Chest CT Volumes |
2308.08157 (2023-08) Learning to Generate Semantic Layouts for Higher Text-Image Correspondence in Text-to-Image Synthesis 2404.05980 (2024-04) Tackling Structural Hallucination in Image Translation with Local Diffusion |
| ListOrTuple | 2 other papers 2 dated earlier |
2305.16037 (2023-05) GenerateCT: Text-Conditional Generation of 3D Chest CT Volumes |
2308.08157 (2023-08) Learning to Generate Semantic Layouts for Higher Text-Image Correspondence in Text-to-Image Synthesis |
| cast_tuple | 2 other papers 2 dated earlier |
2305.16037 (2023-05) GenerateCT: Text-Conditional Generation of 3D Chest CT Volumes |
2308.08157 (2023-08) Learning to Generate Semantic Layouts for Higher Text-Image Correspondence in Text-to-Image Synthesis |
| get_activations | 2 other papers 2 dated earlier |
1904.01310 (2019-04) DM-GAN: Dynamic Memory Generative Adversarial Networks for Text-to-Image Synthesis |
2202.04053 (2022-02) DALL-Eval: Probing the Reasoning Skills and Social Biases of Text-to-Image Generation Models |
| get_images_dataloader | 2 other papers 2 dated earlier |
2305.16037 (2023-05) GenerateCT: Text-Conditional Generation of 3D Chest CT Volumes |
2308.08157 (2023-08) Learning to Generate Semantic Layouts for Higher Text-Image Correspondence in Text-to-Image Synthesis |
| get_tokenizer | 2 other papers 2 dated earlier |
2305.16037 (2023-05) GenerateCT: Text-Conditional Generation of 3D Chest CT Volumes |
2308.08157 (2023-08) Learning to Generate Semantic Layouts for Higher Text-Image Correspondence in Text-to-Image Synthesis |
Shown: the 20 functions present in the most other papers. 2 more shared functions are not listed here.
Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
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, 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 1 .
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2311.15941")
get_code_for_paper("2311.15941")
have("2311.15941")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2311.15941.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2311.15941)
Connect an agent — have() is free.