Supervised Fine Tuning on Curated Data is Reinforcement Learning

Was submitted as "DeepSeek won the best paper award at ACL 2025"

Here is the awards page:

Article URL: https://discourse.llvm.org/t/rfc-hardening-mode-for-the-compiler/87660

Comments URL:

Article URL: https://electrek.co/2025/07/30/peak-energy-us-first-grid-scale-sodium-ion-battery/

https://www.nytimes.com/2025/07/31/theater/robert-wilson-dea... (

Article URL: https://www.courthousenews.com/meta-violated-privacy-law-jury-says-in-menstrual-d

Article URL: https://www.science.org/content/article/contrarian-climate-assessme

Article URL: https://rickovercorpus.org/

Comments URL: https://news.ycombinator.com/item?id