SoundStorm: Efficient Parallel Audio Generation
Scan and Snap: Understanding Training Dynamics and Token Composition in 1-layer Transformer
Role-Play with Large Language Models
EDM3: Event Detection as Multi-task Text Generation
PandaGPT: One Model To Instruction-Follow Them All
Betray Oneself: A Novel Audio DeepFake Detection Model via Mono-to-Stereo Conversion
Large Language Models as Tool Makers
Vector-Valued Variation Spaces and Width Bounds for DNNs: Insights on Weight Decay Regularization
Bi-fidelity Variational Auto-encoder for Uncertainty Quantification
Representation Transfer Learning via Multiple Pre-trained models for Linear Regression
Efficient Neural Music Generation
Language Model Tokenizers Introduce Unfairness Between Languages