[NeurIPS2024] Repo for the paper `ControlMLLM: Training-Free Visual Prompt Learning for Multimodal Large Language Models'
active 2024-06-05 → 2026-04-02 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 667 days from 2024-06-05 to 2026-04-02. Pushes: 93 total, peak 27 in a day. Pull requests: 4 total, peak 2 in a day. Issues: 38 total, peak 5 in a day. Comments: 50 total, peak 5 in a day. Stars: 178 total, peak 7 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 |
|---|---|---|---|---|
| mrwu-mac | 127 | 90 | 4 | 24 |
| ranck626 | 6 | 0 | 0 | 3 |
| guangqian-guo | 6 | 0 | 0 | 3 |
| spark-tom | 4 | 0 | 0 | 2 |
| KaKa-101 | 4 | 0 | 0 | 2 |
| JJumSSu | 4 | 0 | 0 | 2 |
| zhd61 | 4 | 0 | 0 | 2 |
| Wu-Guo-Xiang | 3 | 0 | 0 | 0 |
| qq1332427275 | 3 | 0 | 0 | 2 |
| zengxingchen | 3 | 0 | 0 | 1 |
| C3236455482 | 3 | 3 | 0 | 0 |
| saharzal | 2 | 0 | 0 | 1 |
| codepassionor | 2 | 0 | 0 | 1 |
| Kevin3777 | 2 | 0 | 0 | 1 |
| freya9933 | 2 | 0 | 0 | 2 |
| xuchenkai1 | 1 | 0 | 0 | 0 |
| sterzhang | 1 | 0 | 0 | 1 |
| Hhankyangg | 1 | 0 | 0 | 1 |
| qizipeng | 1 | 0 | 0 | 0 |
| W-QY | 1 | 0 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Issue#26saharzal2025-07-18 07:53image mask alignment?
- Issue comment#28mrwu-mac2025-07-17 03:58What changes have been made in the transformers library?
- Pull request#29mrwu-mac2025-07-17 03:50
- Pull request#29mrwu-mac2025-07-17 03:50
- Issue#28yyc66312025-07-16 02:44What changes have been made in the transformers library?
- Issue#7mrwu-mac2025-07-12 04:29requirements on adding new models
- Issue#18mrwu-mac2025-07-12 04:29ValueError: `.to` is not supported for `4-bit` or `8-bit` bitsandbytes models. Please use the model as it is, since the model has already been set to the correct devices and casted to the correct `dtype`
- Issue#17mrwu-mac2025-07-12 04:29get_local.cache['LlamaSdpaAttention.forward'] is empty([])
- Issue#12mrwu-mac2025-07-12 04:28Query about the selection of H, W
- Issue#15mrwu-mac2025-07-12 04:28Questions about implementation on qwen2 model
- Pull request#27mrwu-mac2025-07-10 04:44
- Issue comment#26saharzal2025-07-09 15:58image mask alignment?
- Issue comment#25guangqian-guo2025-07-07 13:59The ROC results in the code are inconsistent with those in article
- Issue comment#24freya99332025-07-01 17:26The results of reproduction.
- Issue comment#24freya99332025-07-01 17:26The results of reproduction.
- Issue comment#24guangqian-guo2025-06-28 07:21The results of reproduction.
- Issue#24guangqian-guo2025-06-28 01:39The results of reproduction.
- Issue#23guangqian-guo2025-06-28 01:32About the environment.
- Issue comment#23guangqian-guo2025-06-27 03:44About the environment.
- Issue comment#23mrwu-mac2025-06-27 02:55About the environment.
- Issue#23guangqian-guo2025-06-27 02:49About the environment.
- Issue comment#18kill20131102025-06-26 09:38ValueError: `.to` is not supported for `4-bit` or `8-bit` bitsandbytes models. Please use the model as it is, since the model has already been set to the correct devices and casted to the correct `dtype`
- Issue#22W-QY2025-06-25 01:34Is it possible to provide a modified version of the transformer suitable for Qwen2.5VL?
- Pull request#20mrwu-mac2025-05-29 00:58
- Issue#18wzhroll2025-05-06 08:48ValueError: `.to` is not supported for `4-bit` or `8-bit` bitsandbytes models. Please use the model as it is, since the model has already been set to the correct devices and casted to the correct `dtype`
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 178 stars here means stars gained during the window, not the repo's star count.