Browse State-of-the-Art › Text-to-Image Generation

Text-to-Image Generation

546 papers with code · 17 benchmarks · 25 datasets archive 2025-07-28

Computer VisionNatural Language Processing

The development of the brain's blood supply in an embryo involves a complex process with several stages. Initially, there is a network of connections between the carotid and basilar artery systems that usually disappear during development. However, in some cases, these connections remain, leading to variations in the adult cerebral circulation. Around the 24th day of embryonic life (at the 3 mm embryonic stage), the internal carotid arteries (ICA) emerge. They are formed from a combination of the 3rd branchial arch arteries and the distal segments of the paired dorsal aortae. The ICA initially provides all the blood needed by the developing brain. As the brain grows, particularly the occipital region, brainstem, and cerebellum, the blood supply from the ICA becomes insufficient, prompting the development of the posterior circulation. At this stage (4-5 mm embryonic stage), the posterior circulation, specifically the hindbrain, is supplied by two longitudinal neural arteries. These arteries receive blood from several temporary connections (anastomoses) with the ICA, including: Trigeminal artery (TA), Otic artery (OA), Hypoglossal artery (HA), Proatlantal artery (ProA). These carotid-vertebrobasilar anastomoses act as temporary bridges, providing blood flow to the developing posterior circulation until the vertebral arteries (VA) and the basilar artery (BA) are fully formed.6

The BA forms between the 5-8 mm stage by the fusion of the longitudinal neural arteries. As the posterior communicating artery develops and connects with the distal BA, the TA, OA, and HA typically regress. Unlike the TA, OA, and HA, the ProA persists until the VA are fully developed. A segment of the ProA becomes incorporated into the V3 segment of the VA and the distal portions of the occipital artery. The VA develop between the 7-12 mm stage from transverse connections between cervical intersegmental arteries, starting with the ProA and progressing downwards to the 6th intersegmental artery. This 6th intersegmental artery eventually forms the origin of the adult VA from the subclavian artery. 7-8

Persistence of the HA into adulthood, the focus of this discussion, is a rare occurrence. It is the second most common persistent carotid-vertebrobasilar anastomosis, following the persistent trigeminal artery. The failure of the HA to regress during embryological development leads to PPHA. This condition can impact the normal blood flow dynamics in the brain and, in certain cases, can be associated with cerebrovascular issues like aneurysms or ischemic events.

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

17 leaderboard tables shown for this task, 17 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted. 10 shown of 17 until expanded.

Syntology 35 newer papers were judged to report on this task's benchmarks so far (Claude Sonnet 4.5, reading their tables: a model's judgement, not a result; 0 placed): COCO (Common Objects in Context) (9 judged, 0 placed), GenEval (22 judged, 0 placed), DPG (4 judged, 0 placed), MS-COCO (3 judged, 0 placed), T2I-CompBench (5 judged, 0 placed). Drawn from 8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read).

DatasetBest model (first row in archive order)PaperCodeSyntologyCompare
COCO (Common Objects in Context) (69 rows) RAT-Diffusion Data Extrapolation for Text-to-image Generation on Small Datasets code — Compare
CUB (20 rows) RAT-Diffusion Data Extrapolation for Text-to-image Generation on Small Datasets code — Compare
GenEval (20 rows) SD3.5-Medium+Flow-GRPO Flow-GRPO: Training Flow Matching Models via Online RL code Syntology official (archive's flag): 5 ran · 5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified Compare
Multi-Modal-CelebA-HQ (10 rows) Swinv2-Imagen Swinv2-Imagen: Hierarchical Vision Transformer Diffusion Models... — — Compare
DrawBench (8 rows) LCM (Curriculum DPO) Curriculum Direct Preference Optimization for Diffusion and... code Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified Compare
Oxford 102 Flowers (8 rows) RAT-Diffusion Data Extrapolation for Text-to-image Generation on Small Datasets code — Compare
Conceptual Captions (5 rows) Contextual RQ-Transformer Draft-and-Revise: Effective Image Generation with Contextual RQ-Transformer — — Compare
COCO (3 rows) Parti Finetuned Scaling Autoregressive Models for Content-Rich Text-to-Image Generation code Syntology 8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 2 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified Compare
LHQC (3 rows) NUWA-Infinity NUWA-Infinity: Autoregressive over Autoregressive Generation for... code — Compare
DPG (2 rows) Lumina-Image 2.0 Lumina-Image 2.0: A Unified and Efficient Image Generative Framework code Syntology official (archive's flag): 15 ran · 15 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 6 where Syntology's instrument failed) · 1 unverified Compare
GeNeVA (CoDraw) (2 rows) LatteGAN LatteGAN: Visually Guided Language Attention for Multi-Turn... code — Compare
GeNeVA (i-CLEVR) (2 rows) LatteGAN LatteGAN: Visually Guided Language Attention for Multi-Turn... code — Compare
LAION COCO (2 rows) Parti Finetuned Scaling Autoregressive Models for Content-Rich Text-to-Image Generation code Syntology 8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 2 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified Compare
MS-COCO (2 rows) AttnGAN AttnGAN: Fine-Grained Text to Image Generation with Attentional... code Syntology 3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified Compare
T2I-CompBench (2 rows) Emu3 Emu3: Next-Token Prediction is All You Need code Syntology 6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified Compare
Colors (1 row) BiLSTMS on color generation Generation Of Colors using Bidirectional Long Short Term Memory Networks code — Compare
Flickr-8k (1 row) SSC+SKD Language-Oriented Communication with Semantic Coding and Knowledge... — — Compare

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. Each line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

25 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

7 subtasks in the archive's task tree.

Parent tasks archive 2025-07-28

Papers archive 2025-07-28

archive papers tagged: 1,085 · with a code link: 546 · where Syntology ran a sample: 246 (207 with a run with no instrument failure, 39 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (246 of 1,085 tagged: 207 with a run with no instrument failure, 39 where every run was a failure of Syntology's instrument)

Page 1 of 11: papers 1 to 100 of 1,085, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.

Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.

Syntology lines on 79 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.

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