Ashton Anderson

Chessformer: A Unified Architecture for Chess Modeling

ChessQA: Evaluating Large Language Models for Chess Understanding

Identifying and Reducing "Generative Collisions" in Black-Box Large Language Models

Level Up: Defining and Exploiting Transitional Problems for Curriculum Learning

SEAM: Semantically Equivalent Across Modalities Benchmark for Vision-Language Models

Learning to Imitate with Less: Efficient Individual Behavior Modeling in Chess

Understanding Skill Adaptation in Transformers Using Sparse Autoencoders: Chess as a Model System