training objective
- Generative Model Inversion Through the Lens of the Manifold Hypothesis
- Global Minimizers of $\ell^p$-Regularized Objectives Yield the Sparsest ReLU Neural Networks
- Model-Guided Dual-Role Alignment for High-Fidelity Open-Domain Video-to-Audio Generation
- No Experts, No Problem: Avoidance Learning from Bad Demonstrations
- Why Do Some Language Models Fake Alignment While Others Don't?