Latest Search
Quote
| Back Zoom + Zoom - | ||||
|
Xiaohongshu Open-Sources Large Model Reinforcement Learning Training Engine 'Relax'
Recommend 2 Positive 0 Negative 0 |
||||
|
||||
|
The AI platform team of Xiaohongshu open-sourced Relax, a large-model reinforcement learning training engine designed for full-modality and agentic scenarios. Relax reportedly supports unified processing and flexible integration of inputs including images, audio and video. By combining modality-aware parallelism with end-to-end asynchronous pipelines, it enhances multimodal training efficiency and scalability. Auto-translated by AI AASTOCKS Financial News |
||||
Copied to Clipboard
 |
||||
