systematic study
- An Analysis of Concept Bottleneck Models: Measuring, Understanding, and Mitigating the Impact of Noisy Annotations
- Artificial Hivemind: The Open-Ended Homogeneity of Language Models (and Beyond)
- Comprehensive Assessment and Analysis for NSFW Content Erasure in Text-to-Image Diffusion models
- Revisiting Semi-Supervised Learning in the Era of Foundation Models
- Superposition Yields Robust Neural Scaling