← authors · overview

• SpeechT5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language Processing
  2021 · 30 citations
• Semantic Mask for Transformer based End-to-End Speech Recognition
  2019 · 24 citations
• SpeechLM: Enhanced Speech Pre-Training with Unpaired Textual Data
  2022 · 13 citations
• Towards Scientific Intelligence: A Survey of LLM-based Scientific Agents
  2025 · 6 citations
• TESSP: Text-Enhanced Self-Supervised Speech Pre-training
  2022 · 3 citations
• Cloud-native and Distributed Systems for Efficient and Scalable Large Language Models -- A Research Agenda
  2026
• World2VLM: Distilling World Model Imagination into VLMs for Dynamic Spatial Reasoning
  2026
• SWITCH: Benchmarking Modeling and Handling of Tangible Interfaces in Long-horizon Embodied Scenarios
  2025
• KTAE: A Model-Free Algorithm to Key-Tokens Advantage Estimation in Mathematical Reasoning
  2025
• Optimizing Alignment of Speech and Language Latent Spaces for End-to-End Speech Recognition and Understanding
  2021
• WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing
  2021
• Speech Pre-training with Acoustic Piece
  2022