Skip to content

Code for "UI-R1: Enhancing Efficient Action Prediction of GUI Agents by Reinforcement Learning"

active 2025-03-282026-03-05 (UTC)

Partial coverage11,473 / 12,470 hourly files (92%) · 2 absent upstream · 994 failed, retryable2025-03-092026-08-10 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
158
Pushes
26
Pull requests
0
Issues
18
Stars
65
Forks
6

Activity over time

Daily event counts in the loaded window

Line chart, 343 days from 2025-03-28 to 2026-03-05. Pushes: 26 total, peak 11 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 18 total, peak 2 in a day. Comments: 40 total, peak 4 in a day. Stars: 65 total, peak 6 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

ContributorContributionsPushesPRsComments
lll6gg5326024
YcZhangSing5001
caseclose5003
Tetetetetetetet3001
CTZhou-byte3002
YoloEliwa3003
cbigeyes2001
chengcc12322001
Quester-one2001
XianHYe1001
mengzchen1001
cockroach8641001
thongonary1000
sugarandgugu1000
bearnichi1000

Recent activity

Latest issues, pull requests and releases

  • Issue comment#24lll6gg2026-01-01 12:49
    Question about Screenspot-pro evaluation
  • Issue#24bearnichi2026-01-01 12:46
    Question about Screenspot-pro evaluation
  • Issue comment#24lll6gg2026-01-01 12:41
    Question about Screenspot-pro evaluation
  • Issue comment#21lll6gg2025-11-12 10:37
    关于UI-R1-E-3B的训练过程
  • Issue comment#21cockroach8642025-11-11 08:40
    关于UI-R1-E-3B的训练过程
  • Issue#23lll6gg2025-11-03 09:10
    Are there benchmark results for UI-R1-E-3B trained on 136 tasks?
  • Issue#14lll6gg2025-09-22 12:27
    Great job on this project!
  • Issue#22lll6gg2025-09-22 12:27
    做eval使用的Screenspot数据集说明
  • Issue#23thongonary2025-09-08 00:48
    Are there benchmark results for UI-R1-E-3B trained on 136 tasks?
  • Issue comment#22lll6gg2025-09-06 11:51
    做eval使用的Screenspot数据集说明
  • Issue#21caseclose2025-09-05 03:35
    关于UI-R1-E-3B的训练过程
  • Issue#20YcZhangSing2025-08-31 07:07
    Is it normal for the 'clip_ratio' is always 0.0?
  • Issue comment#20YcZhangSing2025-08-31 07:07
    Is it normal for the 'clip_ratio' is always 0.0?
  • Issue#20YcZhangSing2025-08-29 07:08
    Is it normal for the 'clip_ratio' is always 0.0?
  • Issue comment#18chengcc12322025-08-06 07:17
    ui-r1-3b-e training dataset
  • Issue comment#19lll6gg2025-08-05 06:40
    请问是否有安装pip包的具体版本号,在我的conda环境中老是有一些小问题,导致代码不能通畅的跑起来
  • Issue#19chengcc12322025-08-05 06:26
    请问是否有安装pip包的具体版本号,在我的conda环境中老是有一些小问题,导致代码不能通畅的跑起来
  • Issue comment#18lll6gg2025-07-16 03:28
    ui-r1-3b-e training dataset
  • Issue comment#17lll6gg2025-07-14 02:12
    未能复现论文精度
  • Issue comment#16XianHYe2025-07-07 14:10
    推理速度问题
  • Issue comment#16CTZhou-byte2025-06-04 04:51
    推理速度问题
  • Issue comment#16CTZhou-byte2025-06-04 04:47
    推理速度问题
  • Issue#16CTZhou-byte2025-06-04 04:38
    推理速度问题
  • Issue comment#15lll6gg2025-05-28 03:19
    About the reproduction of experimental results.
  • Issue comment#15lll6gg2025-05-26 13:57
    About the reproduction of experimental results.

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 65 stars here means stars gained during the window, not the repo's star count.