Tech QeRL: NVFP4-Quantized Reinforcement Learning (RL) Brings 32B LLM Training to a Single H100—While Improving Exploration
Tech xAI launches Grok-4-Fast: Unified Reasoning and Non-Reasoning Model with 2M-Token Context and Trained End-to-End with Tool-Use Reinforcement Learning (RL)
Artificial Intelligence DeepSeek-RL 2025: Ensuring Safe Reinforcement Learning with Robust Constraints
Tech RL^V: Unifying Reasoning and Verification in Language Models through Value-Free Reinforcement Learning
