500AI
← People

Xingjian Du

Source-listed: Ph.D. student, Department of Electrical and Computer Engineering · University of Rochester

  • Language models
  • Speech and audio
  • Sequence models

Selected work

3
  1. RWKV: Reinventing RNNs for the Transformer EraAuthor · 2023
  2. HTS-AT: A Hierarchical Token-Semantic Audio Transformer for Sound Classification and DetectionContributor · 2022
  3. ByteCover3: Accurate Cover Song Identification on Short QueriesFirst author · 2023

Source-linked involvement

1
  1. Eagle and Finch: RWKV with Matrix-Valued States and Dynamic RecurrenceAuthor · 2024