DeepSeek trained its flagship V3 model for about $5.6 million, a fraction of the $50 million to $100 million OpenAI spent on GPT-4, and the Chinese lab operating under U.S. chip export controls has co…
Oyster-II, a new reinforcement learning-based framework for large language model safety, outperforms its predecessor and competitors like Qwen3-14B while balancing safety and utility. The model addres…
Researchers propose Oyster-II, a reinforcement learning framework for constructive safety alignment in large language models, addressing limitations of refusal-based strategies and supervised fine-tun…
Alibaba's Qwen team released Qwen-AgentWorld, a language world model that simulates environment responses to agent actions, outperforming GPT-5.4 and Claude Opus 4.8 on the AgentWorldBench across seve…