AIHacker Newsabout 3 hours ago
ByteDance, Tsinghua Open-Source DAPO RL System
4 min read
ByteDance Seed and Tsinghua Air released DAPO, an open-source reinforcement learning system for large language models. It scores 50 points on AIME 2024 with Qwen2.5-32B, beating DeepSeek-R1-Zero-Qwen-32B using 50% fewer training steps.
Level
Hype check
Tap to vote and see what everyone thinks.
In this storyByteDance