Search papers, labs, and topics across Lattice.
Institute of Computing and Intelligence, Harbin Institute of Technology (Shenzhen), China
2
0
5
1
Context-aware ASR corrections can be dramatically improved by leveraging a dynamically structured ontology memory, leading to more accurate and relevant corrections in long conversations.
LLMs can rewrite bad job descriptions and category-aware MoEs can better match candidates, leading to a 19.4% boost in recruitment click-through rates and millions saved.
