爱可可 AI 前沿推介(7.29)

文章预览

LG - 机器学习 CV - 计算机视觉 CL - 计算与语言 RO - 机器人 1、[LG] LoRA-Pro：Are Low-Rank Adapters Properly Optimized? 2、[CL] RAG-QA Arena：Evaluating Domain Robustness for Long-form Retrieval Augmented Question Answering 3、[LG] Strategy and Skill Learning for Physics-based Table Tennis Animation 4、[IR] NV-Retriever：Improving text embedding models with effective hard-negative mining 5、[LG] Transformers on Markov Data：Constant Depth Suffices 摘要：低秩Adapter是否做了足够的优化、长式检索增强问答域鲁棒性评估、面向物理乒乓动画的策略与技能学习、通过有效的硬负样本挖掘改进文本嵌入模型、马尔可夫数据上的Transformer 1、[LG] LoRA-Pro: Are Low-Rank Adapters Properly Optimized? Z Wang, J Liang [University of Science and Technology of China & Chinese Academy of Sciences] LoRA-Pro：低秩Adapter是否做了足够的优化？ 要点: 提出一种称为LoRA-Pro的方法，目的是缩小LoRA和 ………………………………