[ICLR'23] DiffuSeq: Sequence to Sequence Text Generation with Diffusion Models
active 2023-08-22 → 2026-05-13 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 996 days from 2023-08-22 to 2026-05-13. Pushes: 1 total, peak 1 in a day. Pull requests: 2 total, peak 2 in a day. Issues: 41 total, peak 3 in a day. Comments: 69 total, peak 5 in a day. Stars: 268 total, peak 5 in a day.
- Pushes
- Pull requests
- Issues
- Comments
- Stars
Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.
Top contributors
Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity
| Contributor | Contributions | Pushes | PRs | Comments |
|---|---|---|---|---|
| summmeer | 19 | 1 | 0 | 18 |
| xiaotingxuan | 11 | 0 | 0 | 7 |
| chiral-carbon | 9 | 0 | 2 | 5 |
| zzbuzzard | 6 | 0 | 0 | 4 |
| CCCCCCCCCdut | 5 | 0 | 0 | 2 |
| zkzhou-2 | 5 | 0 | 0 | 4 |
| BIT-MJY | 4 | 0 | 0 | 2 |
| siebeniris | 3 | 0 | 0 | 1 |
| swave-demo | 3 | 0 | 0 | 3 |
| orxh | 3 | 0 | 0 | 1 |
| Humble2967738843 | 3 | 0 | 0 | 1 |
| MirDoch | 3 | 0 | 0 | 1 |
| skepsun | 3 | 0 | 0 | 1 |
| decode12 | 3 | 0 | 0 | 2 |
| kimyong95 | 2 | 0 | 0 | 2 |
| Neochris | 2 | 0 | 0 | 0 |
| LikeStarting | 2 | 0 | 0 | 1 |
| kingkingofall | 2 | 0 | 0 | 0 |
| chenshao107 | 2 | 0 | 0 | 2 |
| bansky-cl | 1 | 0 | 0 | 1 |
Recent activity
Latest issues, pull requests and releases
- Issue#87redwyd2025-03-20 09:52Loss Function Problem
- Issue comment#86summmeer2025-01-18 06:44Confusion about the 'warmup-decay' of the noise schedule
- Issue comment#57xiaotingxuan2024-12-28 11:31NaN probabilities for step_sample
- Issue comment#57cecilialeo772024-12-28 09:18NaN probabilities for step_sample
- Issue#86Sometimesrains2024-11-13 04:03Confusion about the 'warmup-decay' of the noise schedule
- Issue comment#61ziyanfeng6862024-11-11 09:58diffuseq-v2: TypeError: load_state_dict() takes 1 positional argument but 3 were given
- Issue comment#62antoine-tran2024-09-10 15:33DiffuSeq-v2 checkpoint release
- Issue comment#66Christina07172024-08-06 01:59Try to train the model with another dataset, but get so many [UNK] token.
- Issue comment#85summmeer2024-08-05 10:27Text simplification dataset
- Issue comment#84summmeer2024-08-05 10:24questions on source data
- Issue comment#82X-fxx2024-07-19 02:01'grad_norm' is NaN
- Issue#85MeshchaninovViacheslav2024-07-01 14:10Text simplification dataset
- Issue#84louisefz2024-06-14 14:26questions on source data
- Issue comment#79summmeer2024-06-07 06:02DDPM
- Issue comment#79BIT-MJY2024-06-07 00:49DDPM
- Issue comment#62yanghu8192024-06-05 10:09DiffuSeq-v2 checkpoint release
- Issue comment#50swave-demo2024-06-04 02:50Taken <Pad> as a regular token could make model only learn the <Pad> information?
- Issue comment#50summmeer2024-06-03 13:02Taken <Pad> as a regular token could make model only learn the <Pad> information?
- Issue comment#50swave-demo2024-06-03 09:39Taken <Pad> as a regular token could make model only learn the <Pad> information?
- Issue comment#25swave-demo2024-06-03 09:34Some questions about different losses
- Issue comment#82LikeStarting2024-06-02 05:06'grad_norm' is NaN
- Issue comment#83orxh2024-05-30 11:04Understanding tT_loss
- Issue#83orxh2024-05-30 11:04Understanding tT_loss
- Issue comment#83summmeer2024-05-30 07:56Understanding tT_loss
- Issue#83orxh2024-05-18 23:37Understanding tT_loss
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 268 stars here means stars gained during the window, not the repo's star count.