DiffusionDriveV2: Reinforcement Learning-Constrained Truncated Diffusion Modeling in End-to-End Autonomous Driving
active 2025-12-09 → 2026-06-11 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 185 days from 2025-12-09 to 2026-06-11. Pushes: 2 total, peak 1 in a day. Pull requests: 1 total, peak 1 in a day. Issues: 17 total, peak 2 in a day. Comments: 15 total, peak 3 in a day. Stars: 97 total, peak 12 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 |
|---|---|---|---|---|
| Doctor-James | 14 | 2 | 0 | 11 |
| mxCynic | 3 | 0 | 1 | 1 |
| TensorsSun | 2 | 0 | 0 | 1 |
| chuanye-Wang | 2 | 0 | 0 | 0 |
| charriry | 1 | 0 | 0 | 0 |
| TikaToka | 1 | 0 | 0 | 0 |
| 311850 | 1 | 0 | 0 | 0 |
| psm-2 | 1 | 0 | 0 | 0 |
| BHC1205 | 1 | 0 | 0 | 0 |
| dsamvoel | 1 | 0 | 0 | 0 |
| xiaoyang-coder | 1 | 0 | 0 | 0 |
| Liangyu-Sun | 1 | 0 | 0 | 0 |
| CurryChen77 | 1 | 0 | 0 | 1 |
| YWCandGHY | 1 | 0 | 0 | 0 |
| Percivalzixie | 1 | 0 | 0 | 0 |
| lanbo-xiao | 1 | 0 | 0 | 1 |
| DanqiZhao21 | 1 | 0 | 0 | 0 |
| Tongjiaxun | 1 | 0 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Issue#38charriry2026-04-30 05:41Has anyone tried this algorithm in practical applications and could share its latency or throughput numbers?
- Issue#29dsamvoel2026-02-08 08:01Training loss mismatch warning
- Issue#27chuanye-Wang2026-01-29 05:28How to visualize the model prediction
- Issue#26chuanye-Wang2026-01-29 04:57How to visualize
- Issue comment#25Doctor-James2026-01-28 11:13a problem with ddp strategy
- Issue#24xiaoyang-coder2026-01-22 06:16v1和v2，decoder diffusion次数不一样。
- Issue comment#24Doctor-James2026-01-22 02:38v1和v2，decoder diffusion次数不一样。
- Issue comment#23CurryChen772026-01-16 05:41Bench2Drive Evaluation Plans for DiffusionDriveV2
- Issue comment#19Doctor-James2026-01-16 02:40About adding noise to anchor trajectories
- Issue#22Tongjiaxun2026-01-15 03:35为什么训练轨迹rl的时候需要diffusion两次？
- Issue comment#20mxCynic2026-01-15 02:45我可以在V2的项目里直接运行V1的训练脚本吗？
- Pull request#21mxCynic2026-01-15 02:42
- Issue#20mxCynic2026-01-13 09:41我可以在V2的项目里直接运行V1的训练脚本吗？
- Issue#17BHC12052026-01-08 08:14The issue of multiplicative noise addition
- Issue comment#18Doctor-James2026-01-08 08:03运行 mode selector提示模型权重文件和代码定义的模型结构不一致
- Issue comment#18Doctor-James2026-01-08 07:29运行 mode selector提示模型权重文件和代码定义的模型结构不一致
- Issue comment#18Doctor-James2026-01-08 05:37运行 mode selector提示模型权重文件和代码定义的模型结构不一致
- Issue#18Percivalzixie2026-01-08 03:16运行 mode selector提示模型权重文件和代码定义的模型结构不一致
- Issue#163118502026-01-03 16:06The problem about running the official evaluation script
- Issue#12DanqiZhao212026-01-01 01:12which line should be commented out
- Issue comment#15TensorsSun2025-12-31 04:44The problem about training log file
- Issue#14TensorsSun2025-12-29 11:01The cache dataset about diffusiondrive V1 and V2
- Issue comment#12Doctor-James2025-12-29 02:18which line should be commented out
- Issue#13psm-22025-12-27 17:15More Examples
- Issue#10TikaToka2025-12-24 08:13Error when training the model
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 97 stars here means stars gained during the window, not the repo's star count.