热点
"数据混合" 相关文章
Scaling Reinforcement Learning Beyond Math: Researchers from NVIDIA AI and CMU Propose Nemotron-CrossThink for Multi-Domain Reasoning with Verifiable Reward Modeling
MarkTechPost@AI 2025-05-05T05:35:46.000000Z
NVIDIA Introduces CLIMB: A Framework for Iterative Data Mixture Optimization in Language Model Pretraining
MarkTechPost@AI 2025-04-19T21:15:38.000000Z
Meta斯坦福全新多模态Apollo，60分钟视频轻松理解，7B性能超越30B
36kr-科技 2024-12-20T04:30:49.000000Z
大模型「强崩溃」！Meta新作：合成数据有「剧毒」，1%即成LLM杀手
智源社区 2024-10-14T05:08:52.000000Z