large-scale models
Large-scale models refer to AI systems with extensive parameters and data requirements, often requiring significant computational resources and designed to handle complex tasks across diverse domains.
- Asymmetric Duos: Sidekicks Improve Uncertainty
- Domain-Specific Pruning of Large Mixture-of-Experts Models with Few-shot Demonstrations
- Fast Data Attribution for Text-to-Image Models
- Fourier Analysis Network
- How Many Tokens Do 3D Point Cloud Transformer Architectures Really Need?
- RespoDiff: Dual-Module Bottleneck Transformation for Responsible & Faithful T2I Generation
- Robust SuperAlignment: Weak-to-Strong Robustness Generalization for Vision-Language Models
- Self-Supervised Learning of Motion Concepts by Optimizing Counterfactuals
- Uncertainty Quantification for Physics-Informed Neural Networks with Extended Fiducial Inference