Search papers, labs, and topics across Lattice.
5
0
8
24
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.
Tool-calling LLM agents can be up to 52% safer if they complete a few regular tasks before engaging in safety-critical interactions.
Achieve interpretability in continual learning without sacrificing accuracy: CI-CBM outperforms existing interpretable methods by 36% while matching black-box model performance.
Ditch the blunt hammer of global activation steering: Steer2Edit surgically edits LLM behavior by pinpointing and tweaking the specific attention heads and MLP neurons responsible.
