design principles
Fundamental guidelines and best practices that inform the development of AI systems, ensuring attributes like reliability, interpretability, and ethical considerations are integrated from the outset.
- Don’t call it privacy-preserving or human-centric pose estimation if you don’t measure privacy
- Dynamical Properties of Tokens in Self-Attention and Effects of Positional Encoding
- How to build a consistency model: Learning flow maps via self-distillation
- ML4CFD Competition: Results and Retrospective Analysis
- On Transferring Transferability: Towards a Theory for Size Generalization