5 papers
How are linear representations learned? Exact solutions to the dynamics of abstraction
William W. Yang, Andrew M. Saxe, Peter E. Latham
In artificial and biological neural networks, concepts are often encoded as consistent linear directions in representation space. In deep learning, this idea is known as the linear…
CoMet: Context and Multiplicity Decomposition for Multimodal Uncertainty Estimation
Sanghyuk Chun, William Yang, Amaya Dharmasiri +1
Uncertainty estimation has been a long-standing challenge in AI models; it amounts to "knowing what you don't know," and metacognition is notoriously difficult even for humans (cf.…
Beyond Objects: Contextual Synthetic Data Generation for Fine-Grained Classification
William Yang, Xindi Wu, Zhiwei Deng +2
Text-to-image (T2I) models are increasingly used for synthetic dataset generation, but generating effective synthetic training data for classification remains challenging. Fine-tun…
Mitigating Extrinsic Gender Bias for Bangla Classification Tasks
Sajib Kumar Saha Joy, Arman Hassan Mahy, Meherin Sultana +4
In this study, we investigate extrinsic gender bias in Bangla pretrained language models, a largely underexplored area in low-resource languages. To assess this bias, we construct…
The Impact of Coreset Selection on Spurious Correlations and Group Robustness
Amaya Dharmasiri, William Yang, Polina Kirichenko +2
Coreset selection methods have shown promise in reducing the training data size while maintaining model performance for data-efficient machine learning. However, as many datasets s…