Search papers, labs, and topics across Lattice.
Concordia University, Laval University
3
0
9
16
CCBR empowers users to shape their recommendations through text-driven interactions, outperforming traditional models while maintaining high interpretability.
Even advanced LLMs struggle to prevent privacy breaches in multi-user settings, exposing critical data spillage risks that current benchmarks overlook.
Ditch the text: WavSLM shows you can train a competitive speech language model using only distilled WavLM representations, unlocking a simpler, single-stream generative pretraining paradigm for speech.
