热点
"后训练技术" 相关文章
Thinking About Thinking: Evaluating Reasoning in Post-Trained Language Models
cs.AI updates on arXiv.org 2025-10-21T04:23:24.000000Z
Thinking Sparks!: Emergent Attention Heads in Reasoning Models During Post Training
cs.AI updates on arXiv.org 2025-10-01T05:58:51.000000Z
微软Phi-4封神，14B小模型数学击败GPT-4o！合成数据占比40%，36页技术报告出炉
智源社区 2024-12-24T04:36:51.000000Z