群核科技开源空间理解模型SpatialLM,革新机器人3D空间理解与训练.
active 2025-03-17 → 2026-08-14 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 516 days from 2025-03-17 to 2026-08-14. Pushes: 14 total, peak 2 in a day. Pull requests: 9 total, peak 3 in a day. Issues: 144 total, peak 10 in a day. Comments: 229 total, peak 17 in a day. Stars: 3,529 total, peak 574 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 |
|---|---|---|---|---|
| SamMaoYS | 115 | 12 | 1 | 88 |
| bertjiazheng | 50 | 1 | 3 | 18 |
| chinmay0301ucsd | 7 | 0 | 0 | 6 |
| cyfcyfff | 7 | 0 | 0 | 4 |
| zhirui-gao | 6 | 0 | 0 | 3 |
| PaulLiuYZ | 6 | 0 | 0 | 2 |
| nnf994-xyh | 6 | 0 | 0 | 4 |
| 3i-cao | 6 | 0 | 0 | 2 |
| fanqbu | 5 | 0 | 0 | 3 |
| Fanie-Visagie | 5 | 0 | 0 | 1 |
| 2152505 | 5 | 0 | 0 | 4 |
| zzk6626 | 5 | 0 | 0 | 1 |
| Mr-Neurotic | 4 | 0 | 0 | 3 |
| RiccardoZuppetti | 4 | 0 | 0 | 2 |
| 808kalli | 4 | 0 | 0 | 2 |
| bkxmw | 4 | 0 | 0 | 2 |
| JakeCob | 3 | 0 | 0 | 1 |
| JeromeChen55 | 3 | 0 | 0 | 1 |
| hippoley | 3 | 0 | 0 | 3 |
| Eku127 | 3 | 0 | 0 | 1 |
Recent activity
Latest issues, pull requests and releases
- Issue#137echozpz2026-08-14 15:54请问不是真实尺度的点云，spatiallm能处理吗？
- Issue#125troyyang2026-04-25 06:23How do we train our own dataset?
- Issue comment#122SamMaoYS2026-02-11 14:08Model detect non-existent walls and furniture on aligned data
- Issue#122Syforeal2026-02-11 07:09Model detect non-existent walls and furniture on aligned data
- Issue comment#118Archer4922026-02-04 03:17OOM
- Issue comment#117SamMaoYS2026-01-20 15:13Which model for finetuning?
- Issue comment#118SamMaoYS2026-01-20 15:13OOM
- Issue#118Archer4922026-01-13 06:48OOM
- Issue comment#116SamMaoYS2026-01-03 06:41Sonata pre-training details
- Issue comment#115SamMaoYS2025-12-31 07:21输出结果都是相同的数据是什么原因？
- Issue#116delyan-boychev2025-12-15 23:37Sonata pre-training details
- Issue comment#114SamMaoYS2025-11-30 01:50相同的输入多次执行结果不一样，有办法保持一致吗？
- Issue#114qingfengmingyue2025-11-28 09:48相同的输入多次执行结果不一样，有办法保持一致吗？
- Issue#109SamMaoYS2025-11-19 11:01it only capable of generating layout data for cuboids?
- Issue comment#112lu-sir1882025-11-19 10:06SpatialLM-Test的结果
- Issue comment#110SamMaoYS2025-11-19 08:563D Object Detection finetune on ScanNet with annotations of 18 object categories
- Issue comment#100lu-sir1882025-11-13 08:21SpatialLM-Test的结果跑出来坐标框完全不对
- Issue comment#110frickyinn2025-11-13 03:143D Object Detection finetune on ScanNet with annotations of 18 object categories
- Issue comment#110bkxmw2025-11-07 09:093D Object Detection finetune on ScanNet with annotations of 18 object categories
- Issue#105SamMaoYS2025-11-04 11:32咨询训练数据集问题
- Issue comment#110SamMaoYS2025-11-04 11:313D Object Detection finetune on ScanNet with annotations of 18 object categories
- Issue comment#111SamMaoYS2025-11-04 11:18How to Reproduce Pre-Training Results
- Issue#111bkxmw2025-11-03 03:40How to Reproduce Pre-Training Results
- Issue comment#106bkxmw2025-10-31 08:49Difficulty reproducing zero-shot detection results with provided model
- Issue#1103i-cao2025-10-31 01:463D Object Detection finetune on ScanNet with annotations of 18 object categories
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 3,529 stars here means stars gained during the window, not the repo's star count.