training cost
The resources (time, computational power, energy) expended during the model training process, which can significantly influence the feasibility of deploying large models.
- $\boldsymbol{\lambda}$-Orthogonality Regularization for Compatible Representation Learning
- Data Mixture Optimization: A Multi-fidelity Multi-scale Bayesian Framework
- NaViL: Rethinking Scaling Properties of Native Multimodal Large Language Models under Data Constraints
- NegoCollab: A Common Representation Negotiation Approach for Heterogeneous Collaborative Perception