AdaMerging: Adaptive Model Merging for Multi-Task Learning. ICLR, 2024.
active 2023-10-09 → 2026-07-15 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 1011 days from 2023-10-09 to 2026-07-15. Pushes: 9 total, peak 4 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 18 total, peak 2 in a day. Comments: 24 total, peak 4 in a day. Stars: 96 total, peak 3 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 |
|---|---|---|---|---|
| EnnengYang | 19 | 9 | 0 | 10 |
| KIM-JAKE | 6 | 0 | 0 | 5 |
| monody1 | 5 | 0 | 0 | 4 |
| KexuanShi | 5 | 0 | 0 | 1 |
| yifei-he | 3 | 0 | 0 | 1 |
| FarisXiong | 3 | 0 | 0 | 1 |
| sasgkhgw | 2 | 0 | 0 | 0 |
| lejelly | 2 | 0 | 0 | 1 |
| DongHwanJang | 2 | 0 | 0 | 0 |
| Polly-LYP | 1 | 0 | 0 | 0 |
| sorobedio | 1 | 0 | 0 | 0 |
| kasurashan | 1 | 0 | 0 | 1 |
| aryajalali | 1 | 0 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Issue#12KexuanShi2025-03-19 06:08Cannot Reproduce results of Ties-Merging in ViT-B-32 by the provided codes.
- Issue#12KexuanShi2025-03-18 13:07Cannot Reproduce results of Ties-Merging in ViT-B-32 by the provided codes.
- Issue comment#11KexuanShi2025-03-17 08:14Can not reproduce the Stanford Cars result in ViT-B-16
- Issue#11KexuanShi2025-03-17 08:14Can not reproduce the Stanford Cars result in ViT-B-16
- Issue comment#11EnnengYang2025-03-17 08:11Can not reproduce the Stanford Cars result in ViT-B-16
- Issue#11KexuanShi2025-03-17 06:42Can not reproduce the Stanford Cars result in ViT-B-16
- Issue comment#10EnnengYang2025-03-16 12:29ModuleNotFoundError: No module named 'open_clip.transformer'
- Issue#10Polly-LYP2025-03-16 04:20ModuleNotFoundError: No module named 'open_clip.transformer'
- Issue comment#9EnnengYang2025-03-09 02:30Cannot Load Models - Missing VisualTransformer in open_clip
- Issue#9aryajalali2025-03-09 00:53Cannot Load Models - Missing VisualTransformer in open_clip
- Issue comment#8lejelly2025-02-17 08:26[Question] Concerns about gradient propagation through .cuda() operations in CPU→GPU transfers
- Issue comment#8EnnengYang2025-02-12 06:52[Question] Concerns about gradient propagation through .cuda() operations in CPU→GPU transfers
- Issue#8lejelly2025-02-10 03:51[Question] About gradient propagation with .cpu() in parameter merging
- Issue#6FarisXiong2024-11-19 10:28Reproduce EuroSAT Results with ViT-L-14 and ViT-B-32 Models
- Issue comment#7KIM-JAKE2024-09-06 06:50Memory management in training process
- Issue comment#7KIM-JAKE2024-09-06 06:46Memory management in training process
- Issue comment#7EnnengYang2024-09-06 06:44Memory management in training process
- Issue comment#7kasurashan2024-09-06 06:31Memory management in training process
- Issue comment#7EnnengYang2024-09-04 04:22Memory management in training process
- Issue comment#7KIM-JAKE2024-09-03 15:19Memory management in training process
- Issue comment#6FarisXiong2024-09-02 03:03Reproduce EuroSAT Results with ViT-L-14 and ViT-B-32 Models
- Issue comment#7KIM-JAKE2024-08-31 13:37Memory management in training process
- Issue comment#7EnnengYang2024-08-31 12:53Memory management in training process
- Issue comment#7KIM-JAKE2024-08-31 02:47Memory management in training process
- Issue comment#7EnnengYang2024-08-30 12:19Memory management in training process
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 96 stars here means stars gained during the window, not the repo's star count.