UniVG-R1: Reasoning Guided Universal Visual Grounding with Reinforcement Learning
active 2025-05-22 → 2026-01-30 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 254 days from 2025-05-22 to 2026-01-30. Pushes: 4 total, peak 3 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 14 total, peak 2 in a day. Comments: 12 total, peak 2 in a day. Stars: 82 total, peak 20 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 |
|---|---|---|---|---|
| SuleBai | 14 | 4 | 0 | 7 |
| kinredon | 2 | 0 | 0 | 0 |
| connorye | 2 | 0 | 0 | 0 |
| Zhao-Qihao | 2 | 0 | 0 | 1 |
| HkDzl | 1 | 0 | 0 | 0 |
| 5Jiahe | 1 | 0 | 0 | 0 |
| MrL-CV | 1 | 0 | 0 | 0 |
| fansticOne | 1 | 0 | 0 | 0 |
| harrylin-hyl | 1 | 0 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Issue#14harrylin-hyl2025-09-23 09:23多物体Grounding的情况
- Issue comment#12SuleBai2025-08-26 11:12Question about fairness of comparisons with baseline models
- Issue#13HkDzl2025-08-26 03:39如何把输出的bbox转换为和输入图像对其的大小和位置？
- Issue#11SuleBai2025-07-26 02:09作者你好，你们写论文时，是否有调研 MC-Bench 这篇论文？
- Issue comment#11SuleBai2025-07-22 15:30作者你好，你们写论文时，是否有调研 MC-Bench 这篇论文？
- Issue#11linhuixiao2025-07-22 11:52作者你好，你们写论文时，是否有调研 MC-Bench 这篇论文？
- Issue comment#10SuleBai2025-07-21 16:00Change the attention type obviously lower the eval output
- Issue comment#10FunTotal2025-07-21 06:25Change the attention type obviously lower the eval output
- Issue comment#10SuleBai2025-07-20 14:51Change the attention type obviously lower the eval output
- Issue comment#9Zhao-Qihao2025-07-09 02:45About GPU memory
- Issue#9Zhao-Qihao2025-07-09 02:44About GPU memory
- Issue#8connorye2025-07-04 08:26Question about some details in the paper
- Issue#8connorye2025-07-04 04:44Question about thesome details in the paper
- Issue#7fansticOne2025-06-17 02:32坐标是原始坐标吗
- Issue comment#6SuleBai2025-06-07 05:10Question about the evaluation results on MIG-Bench
- Issue#6kinredon2025-06-06 13:30Question about the evaluation results on MIG-Bench
- Issue#3SuleBai2025-06-02 09:42Cannot solve open-set object detection tasks?
- Issue comment#5SuleBai2025-06-02 09:36Stage 1 model checkpoint
- Issue comment#5SuleBai2025-06-02 09:16Stage 1 model checkpoint
- Issue#5kinredon2025-06-02 06:54Stage 1 model checkpoint
- Issue comment#4SuleBai2025-05-30 02:10Is it based on VLM-R1 for two stages of intensive fine-tuning on the specified dataset?
- Issue#3MrL-CV2025-05-29 08:00Cannot solve open-set object detection tasks?
- Issue comment#2SuleBai2025-05-28 02:48The CoT prompt for SFT data
- Issue#25Jiahe2025-05-27 15:11The CoT prompt for SFT data
- Issue comment#1SuleBai2025-05-26 03:41Release UniVG-R1 artifacts (model, dataset) on Hugging Face
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 82 stars here means stars gained during the window, not the repo's star count.