Reg-DPO: SFT-Regularized Direct Preference Optimization with GT-Pair for Improving Video Generation
"DPO" 相关文章
ICCV 2025 | 港科、牛津大学发布AlignGuard，文图生成模型可规模化安全对齐框架
LLM Training Data Optimization: Fine-Tuning, RLHF & Red Teaming
LLM Training Data Optimization: Fine-Tuning, RLHF & Red Teaming
RLHF in 2024 with DPO and Hugging Face
Noteworthy AI Research Papers of 2024 (Part One)
Diversity First, Quality Later: A Two-Stage Assumption for Language Model Alignment
基于ERNIE-4.5-0.3B医疗领域大模型一站式分布式训练部署
Learning to Align Human Code Preferences
Unlearning of Knowledge Graph Embedding via Preference Optimization
Customize Amazon Nova in Amazon SageMaker AI using Direct Preference Optimization
英伟达大牛主讲！斯坦福吴恩达：大语言模型的后训练课程全网发布
AI产品经理必看的大模型微调劝退指南丨实战笔记
怎么通俗易懂地理解AI大模型微调？一篇大白话文章解释模型微调！
Pre-Training、Fine-Tuning、SFT、LoRA、RLHF之间有什么关系？
Fine-tune large language models with reinforcement learning from human or AI feedback
小长假AI进化营｜3天掌握大模型对齐核心技术
LLM自学成才变身「预言家」！预测未来能力大幅提升
以小博大，微软Phi-4正式发布~
LLM 就是内容创作者快速通向 O(n!) 表达之路 | 本质和形式系列-叙事结构@散沙
