architecture-agnostic
Architecture-agnostic refers to methods or techniques that are not tied to a specific model architecture, allowing them to be applicable across different types of neural networks or learning frameworks, enhancing their versatility.
- A High-Dimensional Statistical Method for Optimizing Transfer Quantities in Multi-Source Transfer Learning
- C-LoRA: Contextual Low-Rank Adaptation for Uncertainty Estimation in Large Language Models
- DeltaPhi: Physical States Residual Learning for Neural Operators in Data-Limited PDE Solving
- Energy Loss Functions for Physical Systems
- Scaling Data-Driven Probabilistic Robustness Analysis for Semantic Segmentation Neural Networks
- TRiCo: Triadic Game-Theoretic Co-Training for Robust Semi-Supervised Learning