[NeurIPS 2025 Spotlight] VisualQuality-R1 is the first open-sourced NR-IQA model can accurately describe and rate the image quality.
active 2025-05-11 → 2026-07-03 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 419 days from 2025-05-11 to 2026-07-03. Pushes: 17 total, peak 4 in a day. Pull requests: 2 total, peak 1 in a day. Issues: 6 total, peak 2 in a day. Comments: 14 total, peak 2 in a day. Stars: 86 total, peak 9 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 |
|---|---|---|---|---|
| TianheWu | 27 | 17 | 1 | 8 |
| xxxzzz200 | 2 | 0 | 0 | 1 |
| xiangliustc | 2 | 0 | 0 | 2 |
| zhiyu-z | 1 | 0 | 0 | 0 |
| codefanw | 1 | 0 | 0 | 1 |
| akk-123 | 1 | 0 | 0 | 0 |
| liuxuexun | 1 | 0 | 0 | 0 |
| whycantfindaname | 1 | 0 | 0 | 1 |
| fengzehui0422 | 1 | 0 | 0 | 1 |
| saitejatangudu | 1 | 0 | 0 | 0 |
| NielsRogge | 1 | 0 | 1 | 0 |
Recent activity
Latest issues, pull requests and releases
- Issue comment#15TianheWu2026-06-01 03:24Question about reproducing the Super-Resolution / SRIQA-Bench results in Table 2
- Issue comment#9codefanw2026-04-03 10:37I have successed in running the code with 4 a800 80g
- Issue comment#9TianheWu2025-11-26 06:34I have successed in running the code with 4 a800 80g
- Issue comment#8xxxzzz2002025-11-25 12:16Question about the parameter B in the paper
- Issue comment#7xiangliustc2025-11-23 14:33OOM Errors on Single-Node A800 (80GB) Even with DeepSpeed Zero-3 Offload – Seeking Optimal Hyperparameters
- Issue comment#7TianheWu2025-11-19 07:15OOM Errors on Single-Node A800 (80GB) Even with DeepSpeed Zero-3 Offload – Seeking Optimal Hyperparameters
- Issue comment#7xiangliustc2025-11-19 07:10OOM Errors on Single-Node A800 (80GB) Even with DeepSpeed Zero-3 Offload – Seeking Optimal Hyperparameters
- Issue#8xxxzzz2002025-11-17 02:33Question about the parameter B in the paper
- Issue comment#3whycantfindaname2025-10-21 06:51Process synchronization in the Accuracy Reward Method
- Issue comment#7fengzehui04222025-09-27 14:45OOM Errors on Single-Node A800 (80GB) Even with DeepSpeed Zero-3 Offload – Seeking Optimal Hyperparameters
- Issue comment#6TianheWu2025-08-27 04:07mos数据怎么制备
- Issue#6TianheWu2025-08-27 04:07mos数据怎么制备
- Issue#6akk-1232025-08-27 02:06mos数据怎么制备
- Pull request#5TianheWu2025-08-08 06:26
- Issue comment#4TianheWu2025-07-05 15:08What is the difference between VisualQuality-R1-7B and VisualQuality-R1-7B-preview?
- Issue#4zhiyu-z2025-07-03 08:10What is the difference between VisualQuality-R1-7B and VisualQuality-R1-7B-preview?
- Issue comment#3TianheWu2025-06-15 09:21Process synchronization in the Accuracy Reward Method
- Issue#3saitejatangudu2025-06-13 17:52Process synchronization in the Accuracy Reward Method
- Issue comment#1TianheWu2025-06-05 12:35Code release
- Pull request#2NielsRogge2025-05-29 09:04
- Issue comment#1TianheWu2025-05-28 11:22Code release
- Issue#1liuxuexun2025-05-28 05:38Code release
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 86 stars here means stars gained during the window, not the repo's star count.