Getting Motif-ated: Controllable AI Compositions from Injected Motif Prompts
cs.LG, cs.AI, cs.MM, cs.SD, eess.AS
Submitted: 2026-09-26
Updated: 2026-09-26
Comments: NeurIPS 2026, Creative AI Track
Code: https://github.com/cpyang123/motigen
Project page: https://motigen-site.github.io
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Classifier-Free Diffusion Guidance
- CTRL: A Conditional Transformer Language Model for Controllable Generation
- MuseCoco: Generating Symbolic Music from Text
- MuPT: A Generative Symbolic Music Pretrained Transformer
- Steering Language Models With Activation Engineering
- NotaGen: Advancing Musicality in Symbolic Music Generation with Large Language Model Training Paradigms
- TunesFormer: Forming Irish Tunes with Control Codes by Bar Patching
- ChatMusician: Understanding and Generating Music Intrinsically with LLM
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks