Tag: Qwen
NVIDIA RLP: RL Pretraining for AI Models
NVIDIA introduces RLP (Reinforcement Learning Pretraining), a novel method for training base models with RL to enhance reasoning and strategic decision-making.
mem-agent: AI Model with Persistent Memory
mem-agent: A 4B parameter AI model with persistent memory that rivals models 50x larger. Trained with reinforcement learning on Obsidian-like memory systems.
- « Previous
- 1
- 2
- 3