Walnut Coding (the "Company"), a leading online coding platform for young learners, unveiled its latest generation of AI-powered coding hardware at the 2025 World Internet Conference in Wuzhen, China, ...
Overview: Reinforcement learning in 2025 is more practical than ever, with Python libraries evolving to support real-world simulations, robotics, and deci ...
Our code is based on open-r1, with our customized Trainer for mixed SFT+GRPO training. Some other updates focus on the white-box RL (reward function design) and post-completion training (replacement ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback