[NIPS2025] VideoChat-R1 & R1.5: Enhancing Spatio-Temporal Perception and Reasoning via Reinforcement Fine-Tuning
active 2025-04-10 → 2026-02-22 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 319 days from 2025-04-10 to 2026-02-22. Pushes: 13 total, peak 5 in a day. Pull requests: 1 total, peak 1 in a day. Issues: 24 total, peak 3 in a day. Comments: 21 total, peak 3 in a day. Stars: 115 total, peak 11 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 |
|---|---|---|---|---|
| leexinhao | 13 | 10 | 0 | 3 |
| Aurorana | 8 | 3 | 0 | 5 |
| JoshonSmith | 6 | 0 | 0 | 1 |
| mary-0830 | 2 | 0 | 0 | 2 |
| YoungjaeDev | 2 | 0 | 0 | 0 |
| falonss703 | 2 | 0 | 0 | 1 |
| sccbhxc | 2 | 0 | 0 | 1 |
| jinyoung0121 | 2 | 0 | 0 | 1 |
| xlchen0205 | 2 | 0 | 0 | 1 |
| c7785812 | 2 | 0 | 0 | 1 |
| mwxely | 1 | 0 | 0 | 0 |
| 2402227288 | 1 | 0 | 0 | 0 |
| BNU-IVC-YuanLIU | 1 | 0 | 0 | 0 |
| whc688 | 1 | 0 | 0 | 0 |
| NielsRogge | 1 | 0 | 0 | 0 |
| pspdada | 1 | 0 | 0 | 0 |
| Jayce1kk | 1 | 0 | 0 | 0 |
| Mario-Yan | 1 | 0 | 0 | 0 |
| jzhws | 1 | 0 | 0 | 0 |
| yyqqh098 | 1 | 0 | 0 | 1 |
Recent activity
Latest issues, pull requests and releases
- Issue#4924022272882025-12-23 06:592d grounding 代码问题
- Issue comment#46Aurorana2025-12-12 07:51为什么在大部分Video Benchmark上效果都不如InternVideo2.5 reported 的结果好呢
- Issue#46sotayang2025-11-26 12:09为什么在大部分Video Benchmark上效果都不如InternVideo2.5 reported 的结果好呢
- Issue comment#45yyqqh0982025-11-21 07:10No module named 'petrel_client'
- Issue comment#43chaohongguo2025-11-16 14:12Question about details of inference on QVhighlights
- Issue#43jinyoung01212025-10-26 17:14Question about details of inference on QVhighlights
- Issue comment#43jinyoung01212025-10-26 17:14Question about details of inference on QVhighlights
- Issue comment#38floppycracken2025-10-06 00:16Clarification on Iterative Perception (ITP) Usage During Training in VideoChat-R1.5
- Issue comment#38xlchen02052025-10-04 11:38Clarification on Iterative Perception (ITP) Usage During Training in VideoChat-R1.5
- Issue comment#38Aurorana2025-10-04 10:39Clarification on Iterative Perception (ITP) Usage During Training in VideoChat-R1.5
- Issue#38xlchen02052025-10-04 08:36Clarification on Iterative Perception (ITP) Usage During Training in VideoChat-R1.5
- Issue#33King-king4242025-09-01 05:43Direct GRPO with no cold start phase?
- Pull request#32Kerin6372025-08-18 16:12
- Issue comment#181171-jpg2025-08-08 04:35Inference is surprisingly slower than the normal Qwen/Qwen2.5-VL-7B-Instruct model
- Issue#31Mario-Yan2025-06-30 09:49Request for Release of SFT Data Used in Evaluation
- Issue comment#17chrisx5992025-06-28 10:21温度设置问题
- Issue#28JoshonSmith2025-06-16 05:57train script for video caption?
- Issue comment#3JoshonSmith2025-06-16 05:57Questions about the video caption task
- Issue#19JoshonSmith2025-06-16 05:56train code for video caption？
- Issue#26JoshonSmith2025-06-16 05:55train script for video caption?
- Issue comment#24sccbhxc2025-06-10 02:54The Result Reproduction on Charades-STA
- Issue comment#24leexinhao2025-06-09 14:53The Result Reproduction on Charades-STA
- Issue#26JoshonSmith2025-06-09 00:30train script for video caption?
- Issue#24sccbhxc2025-06-03 12:22The Result Reproduction on Charades-STA
- Issue#22whc6882025-05-30 08:06Question about time grounding
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 115 stars here means stars gained during the window, not the repo's star count.