Code for NeurIPS 2024 paper "Regularizing Hidden States Enables Learning Generalizable Reward Model for LLMs" (under preparation)
active 2024-10-16 → 2026-01-05 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 447 days from 2024-10-16 to 2026-01-05. Pushes: 47 total, peak 13 in a day. Pull requests: 1 total, peak 1 in a day. Issues: 11 total, peak 2 in a day. Comments: 27 total, peak 6 in a day. Stars: 39 total, peak 4 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 |
|---|---|---|---|---|
| YangRui2015 | 42 | 27 | 0 | 14 |
| ruomengd | 21 | 20 | 0 | 1 |
| zzwjames | 7 | 0 | 0 | 4 |
| Joe-Hall-Lee | 5 | 0 | 0 | 2 |
| 1sir3 | 3 | 0 | 0 | 3 |
| Huangzisu | 3 | 0 | 0 | 1 |
| BIRlz | 2 | 0 | 0 | 2 |
| Weiww-Xu | 1 | 0 | 0 | 0 |
| glgjss960 | 1 | 0 | 0 | 0 |
| brchristian | 1 | 0 | 1 | 0 |
Recent activity
Latest issues, pull requests and releases
- Pull request#11brchristian2025-09-03 21:44
- Issue#9Weiww-Xu2025-06-30 10:04Question about indexing logic for chosen/rejected pairs
- Issue comment#81sir32025-06-06 23:35Addressing the Performance Gap: LoRA-Fine-Tuned GRM Evaluation on reward-bench
- Issue comment#81sir32025-06-06 23:33Addressing the Performance Gap: LoRA-Fine-Tuned GRM Evaluation on reward-bench
- Issue comment#81sir32025-06-05 17:26Addressing the Performance Gap: LoRA-Fine-Tuned GRM Evaluation on reward-bench
- Issue comment#8YangRui20152025-06-05 17:17Addressing the Performance Gap: LoRA-Fine-Tuned GRM Evaluation on reward-bench
- Issue comment#7YangRui20152025-05-08 22:35Training details for released GRM series
- Issue#4zzwjames2025-04-07 04:59do you have code to reproduce the results of reward overoptimization for PPO
- Issue comment#4zzwjames2025-04-07 04:59do you have code to reproduce the results of reward overoptimization for PPO
- Issue comment#4YangRui20152025-04-06 04:03do you have code to reproduce the results of reward overoptimization for PPO
- Issue comment#4zzwjames2025-04-05 23:39do you have code to reproduce the results of reward overoptimization for PPO
- Issue comment#6YangRui20152025-03-27 17:01Duplicate bos token
- Issue comment#6Huangzisu2025-03-27 16:55Duplicate bos token
- Issue#6Huangzisu2025-03-27 16:55Duplicate bos token
- Issue#6Huangzisu2025-03-27 09:24Duplicate bos token
- Issue comment#5Joe-Hall-Lee2025-03-14 10:12RuntimeError: size mismatch
- Issue#5Joe-Hall-Lee2025-03-14 10:12RuntimeError: size mismatch
- Issue comment#5YangRui20152025-03-13 15:16RuntimeError: size mismatch
- Issue comment#4YangRui20152025-03-01 06:59do you have code to reproduce the results of reward overoptimization for PPO
- Issue#4zzwjames2025-02-28 23:39do you have code to reproduce the results of reward overoptimization for PPO
- Issue#2YangRui20152025-02-24 02:28evaluation of full finetuned model
- Issue comment#2BIRlz2025-02-24 02:27evaluation of full finetuned model
- Issue comment#3YangRui20152025-02-20 15:33peft_name in scripts/eval_bt_rm.sh
- Issue#3glgjss9602025-02-20 15:02peft_name in scripts/eval_bt_rm.sh
- Issue comment#2ruomengd2025-02-20 07:57evaluation of full finetuned model
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 39 stars here means stars gained during the window, not the repo's star count.