# tongjingqi/AI-Can-Learn-Scientific-Taste

<https://repo.masters-masters.com/en/repos/tongjingqi/AI-Can-Learn-Scientific-Taste>

[Home](https://repo.masters-masters.com/en) › [tongjingqi](https://repo.masters-masters.com/en/owners/tongjingqi) › [AI-Can-Learn-Scientific-Taste](https://repo.masters-masters.com/en/repos/tongjingqi/AI-Can-Learn-Scientific-Taste)

tongjingqi/AI-Can-Learn-Scientific-Taste has 436 stars on GitHub. Its RepoMasters card: Alpha tier. We propose Reinforcement Learning from Community Feedback…

| Field | Value |
| --- | --- |
| Owner | [tongjingqi](https://repo.masters-masters.com/en/owners/tongjingqi) |
| Stars | 436 |
| Forks | 12 |
| Language | No language |
| License | Apache-2.0 |
| Created | 2026 |
| Topics | agent, ai-scientists, rl, ai-innovator |
| Tier | [Alpha (250 to 699 ★)](https://repo.masters-masters.com/en/ranks/b_movie) |
| View on GitHub | [tongjingqi/AI-Can-Learn-Scientific-Taste](https://github.com/tongjingqi/AI-Can-Learn-Scientific-Taste) |

## Repository

We propose Reinforcement Learning from Community Feedback (RLCF), a training paradigm that uses large-scale community signals as supervision, and formulate scientific taste learning as a preference modeling and alignment problem.

The tier for repos with 250 to 699 ★. Published odds per card pulled: 20%. Rarity: Uncommon.

## More repos by tongjingqi

- [tongjingqi/Thinking-with-Video · ★ 320 · Python · Alpha](https://repo.masters-masters.com/en/repos/tongjingqi/Thinking-with-Video)
- [tongjingqi/Game-RL · ★ 162 · Python · Prototype](https://repo.masters-masters.com/en/repos/tongjingqi/Game-RL)

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