Výsledky vyhledávání

Report

Teleporter Theory: A General and Simple Approach for Modeling Cross-World Counterfactual Causality

Autor: Li, Jiangmeng, Qin, Bin, Ji, Qirui, Li, Yi, Qiang, Wenwen, Cao, Jianwen, Xu, Fanjiang

Leveraging the development of structural causal model (SCM), researchers can establish graphical models for exploring the causal mechanisms behind machine learning techniques. As the complexity of machine learning applications rises, single-world int

Externí odkaz: http://arxiv.org/abs/2406.11501

Zobrazit plný text záznamu

Report

Revisiting Spurious Correlation in Domain Generalization

Autor: Qin, Bin, Li, Jiangmeng, Li, Yi, Wu, Xuesong, Wang, Yupeng, Qiang, Wenwen, Cao, Jianwen

Without loss of generality, existing machine learning techniques may learn spurious correlation dependent on the domain, which exacerbates the generalization of models in out-of-distribution (OOD) scenarios. To address this issue, recent works build

Externí odkaz: http://arxiv.org/abs/2406.11517

Zobrazit plný text záznamu

Report

Relay Decoding: Concatenating Large Language Models for Machine Translation

Autor: Fu, Chengpeng, Feng, Xiaocheng, Huang, Yichong, Huo, Wenshuai, Li, Baohang, Wang, Hui, Qin, Bin, Liu, Ting

Leveraging large language models for machine translation has demonstrated promising results. However, it does require the large language models to possess the capability of handling both the source and target languages in machine translation. When it

Externí odkaz: http://arxiv.org/abs/2405.02933

Zobrazit plný text záznamu