4 papers
The Ghost in the Keys: A Disklavier Demo for Human-AI Musical Co-Creativity
Louis Bradshaw, Alexander Spangher, Stella Biderman +1
While generative models for music composition are increasingly capable, their adoption by musicians is hindered by text-prompting, an asynchronous workflow disconnected from the em…
Scaling Self-Supervised Representation Learning for Symbolic Piano Performance
Louis Bradshaw, Honglu Fan, Alexander Spangher +2
We study the capabilities of generative autoregressive transformer models trained on large amounts of symbolic solo-piano transcriptions. After first pretraining on approximately 6…
LLM Circuit Analyses Are Consistent Across Training and Scale
Curt Tigges, Michael Hanna, Qinan Yu +1
Most currently deployed large language models (LLMs) undergo continuous training or additional finetuning. By contrast, most research into LLMs' internal mechanisms focuses on mode…
Grokking Group Multiplication with Cosets
Dashiell Stander, Qinan Yu, Honglu Fan +1
The complex and unpredictable nature of deep neural networks prevents their safe use in many high-stakes applications. There have been many techniques developed to interpret deep n…