14
2025/11
NeurIPS 2025 满分论文：LLM 强化学习的上限已被基座锁死了
论文标题：Does Reinforcement Learning Really Incentivize Reasoning Capacity in LL
...
小红书推出 RedOne 2.0：SNS 领域大模型后训练实践指南
论文标题：RedOne 2.0: Rethinking Domain-specific LLM Post-Training in Social Netw
...