Search papers, labs, and topics across Lattice.
University of Waterloo, Department of Machine Learning, Mohamed, Zayed University of Artificial Intelligence
3
1
7
7
Multimodal unlearning could revolutionize how we handle sensitive data in AI, enabling targeted removal without sacrificing model performance.
Stance detection can be revolutionized by leveraging cloze-style MLM and prototypical learning, achieving high performance even in low-resource contexts.
A task-specific, lightweight transformer can outperform state-of-the-art reasoning LLMs and commercial tools in C code vulnerability detection, at a fraction of the inference cost.
