热点
"后训练方法" 相关文章
Human-in-the-loop Online Rejection Sampling for Robotic Manipulation
cs.AI updates on arXiv.org 2025-10-31T04:07:52.000000Z
推理效率狂飙60倍：DiDi-Instruct让扩散大模型16步超越千步GPT
机器之心 2025-10-27T07:15:35.000000Z
Reconstruction Alignment Improves Unified Multimodal Models
cs.AI updates on arXiv.org 2025-09-19T05:06:02.000000Z
A post-training approach to AI regulation with Model Specs
Interconnects 2024-10-22T06:07:43.000000Z
Post-Training有多重要？AI2研究员长文详解前沿模型的后训练秘籍
智源社区 2024-08-20T06:07:37.000000Z