# rsi_today

- **Event:** [AIE Code Summit 2026 Hackathon](https://cerebralvalley.ai/e/aie-code-2026-hackathon)
- **When:** Sat, Nov 7 at 9:00 AM – 10:00 PM (PST)
- **Where:** San Francisco, CA
- **Team:** [Tom Tang](https://cerebralvalley.ai/u/yizetang), [Mia Jin](https://cerebralvalley.ai/u/miajin1), [Zack Guo](https://cerebralvalley.ai/u/ZackGuo)
- **GitHub:** https://github.com/ZiqiGuo98/svg-physics-rl
- **Demo video:** https://youtu.be/JkrF1tgln-0
- **Gallery:** https://cerebralvalley.ai/e/aie-code-2026-hackathon/hackathon/gallery
- **Page:** https://cerebralvalley.ai/e/aie-code-2026-hackathon/hackathon/gallery/37

We use RSI to automatically improve a language model's physics: builds the training environment, data, and checker-based reward, then fine tune a Qwen model with reinforcement learning to draw physically correct frame-by-frame scenes

## More from AIE Code Summit 2026 Hackathon

- [Bob](https://cerebralvalley.ai/e/aie-code-2026-hackathon/hackathon/gallery/34)
- [Colony](https://cerebralvalley.ai/e/aie-code-2026-hackathon/hackathon/gallery/35)
- [AgentGlass](https://cerebralvalley.ai/e/aie-code-2026-hackathon/hackathon/gallery/36)
- [Sisyphus](https://cerebralvalley.ai/e/aie-code-2026-hackathon/hackathon/gallery/38)
- [Museance](https://cerebralvalley.ai/e/aie-code-2026-hackathon/hackathon/gallery/39)
- [MERGE-GATE](https://cerebralvalley.ai/e/aie-code-2026-hackathon/hackathon/gallery/40)

---

Markdown version of https://cerebralvalley.ai/e/aie-code-2026-hackathon/hackathon/gallery/37. Site index for agents: https://cerebralvalley.ai/llms.txt · full text: https://cerebralvalley.ai/llms-full.txt