prasannamayil.bsky.social
PhD student in ML at MPI-IS. Prev Apple. Interested in robustness at scale and reasoning.
👤 Joined on 18 January 2025
Followers
Following
Total Posts
@prasannamayil.bsky.socialCuratedThoughts: Data Curation for RL Datasets 🚀 Since DeepSeek-R1 introduced reasoning-based RL, datasets like Open-R1 & OpenThoughts emerged for fine-tuning & GRPO. Our deep dive found major flaws — 25% of OpenThoughts needed elimination by data curation. Here's why 👇🧵
Show Post