Research map / Image generation / GANs
GANs for text generation
Train discrete text generators adversarially with feature matching and imitation objectives.
21 accepted papers at ICML, NeurIPS, ICLR, CVPR and AAAI (2017–2022) · an approach in GANs, keyword cluster “gans · mode · samples”
State History Tried Preprints Export
Where it stands
Not enough benchmark data Fewer than four papers report the same benchmark, so there is no record to follow.
How this is decided
A benchmark is tracked when at least four papers of this approach report their own method on the same dataset and metric in at least two different years. Its record is the best number reported up to 2024 compared with the best reported in 2025–26: still improving means at least 1% better, flat means at most 0.2% better with at least two papers from 2025–26 trying. Numbers on a different scale from the rest (a fraction among percentages) and far outliers are left out. Results come from different papers with different setups, so they are signals, not head-to-head comparisons. The share of papers is counted at ICML, NeurIPS, ICLR, CVPR and AAAI.
How it got here
Most cited paper of each year
- 2017 · Adversarial Feature Matching for Text Generation (ICML 2017 · 243 citations)
- 2018 · Long Text Generation via Adversarial Training with Leaked Information (AAAI 2018 · 421 citations)
- 2019 · RelGAN: Relational Generative Adversarial Networks for Text Generation (ICLR 2019 · 143 citations)
- 2020 · Language GANs Falling Short (ICLR 2020 · 87 citations)
- 2021 · StrokeGAN: Reducing Mode Collapse in Chinese Font Generation via Stroke Encoding (AAAI 2021 · 67 citations)
- 2022 · Generative Cooperative Networks for Natural Language Generation (ICML 2022 · 4 citations)
Earliest papers here
- Adversarial Feature Matching for Text Generation (ICML 2017 · 243 citations)
- Adversarial Ranking for Language Generation (NeurIPS 2017)
- Long Text Generation via Adversarial Training with Leaked Information (AAAI 2018 · 421 citations)
What has been tried
20 papers here report 217 measured changes (a component added, removed or swapped, compared with a baseline): helped 75%, no clear effect 9%, hurt 13%, mixed 3%. Papers mostly publish changes that helped, so "helped" is over-represented.
Recent preprints
Loading recent arXiv preprints…
Use it
Download BibTeX of 20 key papersOpen the topic in the interactive map
Get alerts. Describe your idea in scime atlas and save it (free scime account): you get a weekly email when new preprints land close to it.
Related approaches
Same keyword cluster
- Stabilized GAN training (144 papers)
- GAN latent optimization and evaluation (52 papers)
- Generative adversarial network theory (62 papers)
Elsewhere in the topic
- Large-scale GAN latent analysis (108 papers)
- GAN-based image manipulation (90 papers)
- Conditional GANs (25 papers)
- GAN vocoders and audio synthesis (13 papers)
Benchmark numbers, ablations and baseline numbers are extracted by AI from each paper's full text and can be wrong; the paper is the authority. Data: results index of 2026-11-02, citation counts from OpenAlex (2026-10-09).