Our team: MohammadHossein Rezaei (@mhrezaeics), Robert Vacareanu (@robert_nlp), Zihao Wang (@wzihao12), Clinton Wang (@clintonjwang), Yunzhong He (@_yunzhong), Feyza Akyürek (@afeyzaakyurek) Paper: arxiv.org/pdf/2510.07284
Unfortunately, I had to miss out on attending in person in Vienna, but glad to see the recognition. We need more research on understanding data and posttraining of LLMs. Always a pleasure working with @alan and @JunmoKang
🎉 Excited to see that our paper on cost-efficient data annotation for LLMs won an SAC Highlight Award! 🔗 Check out @mohit_rag18's work here: aclanthology.org/2025.acl-long.…
🤔 How do we train LLMs on real-world tasks where it’s hard to define a single verifiable answer? Our work at @scale_AI introduces Rubrics as Rewards (RaR) — a framework for on-policy post-training that uses structured, checklist-style rubrics as interpretable reward signals. 🧵
United States الاتجاهات
- 1. Chiefs 103K posts
- 2. Branch 30.4K posts
- 3. Mahomes 31.4K posts
- 4. #TNABoundForGlory 51.4K posts
- 5. #LoveCabin N/A
- 6. LaPorta 10.2K posts
- 7. Goff 13.4K posts
- 8. Bryce Miller 4,264 posts
- 9. Kelce 15.9K posts
- 10. #OnePride 6,310 posts
- 11. #LaGranjaVIP 49.5K posts
- 12. Dan Campbell 3,477 posts
- 13. #DETvsKC 4,844 posts
- 14. Butker 8,375 posts
- 15. Mariners 48.7K posts
- 16. Rod Wave N/A
- 17. Gibbs 5,516 posts
- 18. Baker 54.2K posts
- 19. Pacheco 4,914 posts
- 20. Mike Santana 4,051 posts
Something went wrong.
Something went wrong.