autoregressive modeling
Autoregressive modeling is a statistical approach where future values are predicted based on past observations in a sequence, commonly used in time series analysis and natural language processing tasks for generating coherent outputs.
- Efficient Speech Language Modeling via Energy Distance in Continuous Latent Space
- FlexVAR: Flexible Visual Autoregressive Modeling without Residual Prediction
- Generative Pre-trained Autoregressive Diffusion Transformer
- SAMPO: Scale-wise Autoregression with Motion Prompt for Generative World Models
- Show-o2: Improved Native Unified Multimodal Models
- vHector and HeisenVec: Scalable Vector Graphics Generation Through Large Language Models