Paul X. McCarthy
paulxmccarthy.bsky.social
CEO, Professor, Author of Online Gravity. Co-founder of Oxford's "Science of Startups." Uncovering latent knowledge to fuel innovation. @LeagueofScholars @UNSW @UTS
👤 Joined on 19 November 2024
98
Followers
82
Following
1
Total Posts
📜 Kullanıcı Geçmişi
- 19 Kas 2024, 11:46
🎉 Bluesky'e katıldı - İlk kullanıcı adı:
@paulxmccarthy.bsky.social
🚫 Blokladığı Kullanıcılar
❤️ Beğendiği Gönderiler
Reinforcement Learning with Verifiable Rewards (RLVR) across diverse, less-structured domains (e.g., medicine, chemistry, psychology, economics, and education), where well-structured reference answers are rare. Paper: www.alphaxiv.org/abs/2503.23829 Model: huggingface.co/virtuoussy/Q...
Show PostOpen-Reasoner-Zero (ORZ), an open-source initiative scaling Reinforcement Learning on base models! 🌊 Updated Paper & Superior Results 🔭 Easy-to-use Training Scripts 📚 Expanded Curated Datasets 🤗 New Hugging Face Models
Show Post
Deepseek-R1, we employed techniques including supervised fine-tuning (SFT), direct preference optimization (DPO), and reinforcement learning (RL) to enhance their financial capabilities. The fine-tuned models demonstrated substantial performance gains [2/3 of https://arxiv.org/abs/2504.13125v1]
Show Post
(Plz repost) I’ve been receiving some good news lately and will be hiring at all levels to expand the lab. Please get in contact if you are interested in reinforcement learning, neural plasticity, neural circuit dynamics, and/or hearing rehabilitation. pierre.apostolides @ umich .edu Tyvm
Show Post