Lovis Heindrich
YOU?
Author Swipe
View article: Optimal Gamification of Self-Directed Learning: A Computational Method and its Real-World Evaluation in an App for Learning English
Optimal Gamification of Self-Directed Learning: A Computational Method and its Real-World Evaluation in an App for Learning English Open
The rise of online learning has transformed education beyond the classroom setting. In online education, it is popular to motivate learners through gamified learning activities. One common approach to gamification involves awarding points …
View article: An Intelligent Tutor for Planning in Large Partially Observable Environments
An Intelligent Tutor for Planning in Large Partially Observable Environments Open
AI can not only outperform people in many planning tasks, but it can also teach them how to plan better. A recent and promising approach to improving human decision-making is to create intelligent tutors that utilize AI to discover and tea…
View article: Do Sparse Autoencoders Generalize? A Case Study of Answerability
Do Sparse Autoencoders Generalize? A Case Study of Answerability Open
Sparse autoencoders (SAEs) have emerged as a promising approach in language model interpretability, offering unsupervised extraction of sparse features. For interpretability methods to succeed, they must identify abstract features across d…
View article: Discovering the curriculum with AI: A proof-of-concept demonstration with an intelligent tutoring system for teaching project selection
Discovering the curriculum with AI: A proof-of-concept demonstration with an intelligent tutoring system for teaching project selection Open
The decisions of individuals and organizations are often suboptimal because fully rational decision-making is too demanding in the real world. Recent work suggests that some errors can be prevented by leveraging artificial intelligence to …
View article: Training Dynamics of Contextual N-Grams in Language Models
Training Dynamics of Contextual N-Grams in Language Models Open
Prior work has shown the existence of contextual neurons in language models, including a neuron that activates on German text. We show that this neuron exists within a broader contextual n-gram circuit: we find late layer neurons which rec…
View article: An intelligent tutor for planning in large partially observable environments
An intelligent tutor for planning in large partially observable environments Open
AI can not only outperform people in many planning tasks, but it can also teach them how to plan better. A recent and promising approach to improving human decision-making is to create intelligent tutors that utilize AI to discover and tea…
View article: Improving Human Decision-making by Discovering Efficient Strategies for Hierarchical Planning
Improving Human Decision-making by Discovering Efficient Strategies for Hierarchical Planning Open
To make good decisions in the real world, people need efficient planning strategies because their computational resources are limited. Knowing which planning strategies would work best for people in different situations would be very usefu…
View article: Improving Human Decision-Making by Discovering Efficient Strategies for Hierarchical Planning
Improving Human Decision-Making by Discovering Efficient Strategies for Hierarchical Planning Open
To make good decisions in the real world people need efficient planning strategies because their computational resources are limited. Knowing which planning strategies would work best for people in different situations would be very useful…