Search papers, labs, and topics across Lattice.
3
0
8
Margin loss fine-tuning of ECAPA-TDNNs slashes the error rate in spoken language identification by over 50%, highlighting the power of discriminative representation learning.
Stop passively waiting for retrieval cues – ProactAgent proactively asks for information from its memory and skills, leading to significant gains in lifelong learning performance.
Forget black box sentiment analysis: ABSA-R1 uses RL to make LLMs explain *why* they feel a certain way, boosting both accuracy and interpretability.
