# THU-BPM/RLCSD

<https://repo.masters-masters.com/en/repos/THU-BPM/RLCSD>

[Home](https://repo.masters-masters.com/en) › [THU-BPM](https://repo.masters-masters.com/en/owners/THU-BPM) › [RLCSD](https://repo.masters-masters.com/en/repos/THU-BPM/RLCSD)

THU-BPM/RLCSD has 116 stars on GitHub. Its RepoMasters card: Prototype tier. Source code of paper "RLCSD: Reinforcement Learning with Contrastive On-Policy…

| Field | Value |
| --- | --- |
| Owner | [THU-BPM](https://repo.masters-masters.com/en/owners/THU-BPM) |
| Stars | 116 |
| Forks | 5 |
| Language | [Python](https://repo.masters-masters.com/en/languages/python) |
| License | MIT |
| Created | 2026 |
| Topics | large-language-models, llm, on-policy-distillation, opsd, reinforcement-learning, self-distillation, opd |
| Tier | [Prototype (100 to 249 ★)](https://repo.masters-masters.com/en/ranks/rush) |
| View on GitHub | [THU-BPM/RLCSD](https://github.com/THU-BPM/RLCSD) |

## Repository

Source code of paper "RLCSD: Reinforcement Learning with Contrastive On-Policy Self-Distillation"

The tier for repos with 100 to 249 ★. Published odds per card pulled: 70%. Rarity: Common.

## More repos by THU-BPM

- [THU-BPM/MarkLLM · ★ 1,089 · Python · Beta](https://repo.masters-masters.com/en/repos/THU-BPM/MarkLLM)
- [THU-BPM/MarkDiffusion · ★ 334 · Jupyter Notebook · Alpha](https://repo.masters-masters.com/en/repos/THU-BPM/MarkDiffusion)
- [THU-BPM/Omni-SafetyBench · ★ 116 · Python · Prototype](https://repo.masters-masters.com/en/repos/THU-BPM/Omni-SafetyBench)
- [THU-BPM/chatgpt-sql · ★ 106 · Python · Prototype](https://repo.masters-masters.com/en/repos/THU-BPM/chatgpt-sql)

## Nearby in Python

- [ukr8b3g-cmyk/MOSS-Image-Character-Catalog · ★ 116 · Python · Prototype](https://repo.masters-masters.com/en/repos/ukr8b3g-cmyk/MOSS-Image-Character-Catalog)
- [flemuh/radar-public-sector · ★ 116 · Python · Prototype](https://repo.masters-masters.com/en/repos/flemuh/radar-public-sector)
- [Sac-Y/match-cut · ★ 116 · Python · Prototype](https://repo.masters-masters.com/en/repos/Sac-Y/match-cut)
- [jezdez/django-mobileadmin · ★ 116 · Python · Prototype](https://repo.masters-masters.com/en/repos/jezdez/django-mobileadmin)
- [montylounge/django-sugar · ★ 116 · Python · Prototype](https://repo.masters-masters.com/en/repos/montylounge/django-sugar)
- [codysoyland/django-template-repl · ★ 116 · Python · Prototype](https://repo.masters-masters.com/en/repos/codysoyland/django-template-repl)

---
Data: GitHub · Illustration drawn by RepoMasters from the repo’s ID and its language color.