Episode Details
Back to Episodes
Architectural and Inferential Inductive Biases For Exchangeable Sequence Modeling
Published 1 year, 5 months ago
Description
- Autoregressive models effectively model exchangeable sequences and uncertainty from missing data
- The paper critiques single-step generation's limitations in uncertainty distinction
- It advocates for multi-step autoregressive generation for better decision-making performance
- New architectural innovations are necessary for improved exchangeable sequence modeling