Search papers, labs, and topics across Lattice.
3
0
5
AHR achieves state-of-the-art performance in text classification with a fraction of the parameters, revolutionizing how LLMs can adapt to limited data.
Achieving over 51% accuracy improvement, MM-CBM redefines interpretability in multimodal deep learning by aligning image and text features with natural concepts.
Achieve interpretability in continual learning without sacrificing accuracy: CI-CBM outperforms existing interpretable methods by 36% while matching black-box model performance.
