#Samples

7 статей
arXiv Computer Vision
arXiv Computer Vision

Beyond Discrete Samples: High Information Density Replay for Efficient Lifelong Person

arXiv:2508.01587v4 Тип объявления: замена Абстракта: Повторная идентификация человека на протяжении всей жизни (LReID) обычно сопротивляется катастрофическому забвению, воспроизводя исторические образ...

arXiv Computer Vision
2
Читать
arXiv NLP
arXiv NLP

Обсуждение In-Context Samples for Machine-Translation

arXiv:2608.27036v1 Анонс Тип: новый Абстракт: Модели большого языка (LLM) могут быть обучены для выполнения цепочек рассуждений с целью повышения надежности их ответов. В этой работе мы исследуем, как...

arXiv NLP
1
Читать
arXiv Computer Vision
arXiv Computer Vision

Uncertainty Identifies Difficult Samples Across Methods: A Multi-Task Study on a Heterogeneous Skin Lesion Dataset

arXiv:2608.14768v1 Announce Type: new Abstract: Skin lesion classifiers can be confidently wrong on the cases that matter most, so knowing when a prediction should not be trusted is clinically as usef...

arXiv Computer Vision
arXiv Statistics
arXiv Statistics

How Many Samples Are Needed to Determine Causal Direction? Sharp Minimax Bounds for Bivariate LiNGAM

arXiv:2608.15840v1 Announce Type: new Abstract: We study how many observations are needed to determine the causal direction between two linearly related variables. Classical LiNGAM theory shows that i...

arXiv Statistics
arXiv Machine Learning
arXiv Machine Learning

Geometric Filtering of LLM-Generated Samples for Few-Shot Text Classification

arXiv:2608.13866v1 Announce Type: new Abstract: Large language models (LLMs) can generate synthetic training data for text classification, but the quality of generated samples is heterogeneous: some f...

arXiv Machine Learning