PPaperPicks

Yang Feng

Chinese Academy of Sciences, Institute of Computing Technology, Key Laboratory of Intelligent Information Processing, Beijing, China

26 papers at tracked venues · 23 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. Efficient Training for Cross-lingual Speech Language Models
  2. FreezeEmpath: Efficient Training for Empathetic Spoken Chatbots with Frozen LLMs
  3. Language on Demand, Knowledge at Core: Composing LLMs with Encoder-Decoder Translation Models for Extensible Multilinguality
  4. AlignX: Advancing Multilingual Large Language Models with Multilingual Representation Alignment
  5. Efficient Speech Language Modeling via Energy Distance in Continuous Latent Space
  6. FastLongSpeech: Enhancing Large Speech-Language Models for Efficient Long-Speech Processing
  7. FlexRAG: A Flexible and Comprehensive Framework for Retrieval-Augmented Generation
  8. IG-Pruning: Input-Guided Block Pruning for Large Language Models
  9. LLM-based Translation Inference with Iterative Bilingual Understanding
  10. LLaMA-Omni 2: LLM-based Real-time Spoken Chatbot with Autoregressive Streaming Speech Synthesis
  11. LLaMA-Omni: Seamless Speech Interaction with Large Language Models
  12. LLaVA-Mini: Efficient Image and Video Large Multimodal Models with One Vision Token
  13. Large Language Models Are Read/Write Policy-Makers for Simultaneous Generation
  14. MoCE: Adaptive Mixture of Contextualization Experts for Byte-based Neural Machine Translation
  15. Overcoming Non-monotonicity in Transducer-based Streaming Generation
  16. A Non-autoregressive Generation Framework for End-to-End Simultaneous Speech-to-Any Translation
  17. CTC-based Non-autoregressive Textless Speech-to-Speech Translation
  18. Can We Achieve High-quality Direct Speech-to-Speech Translation without Parallel Speech Data?
  19. Decoder-only Streaming Transformer for Simultaneous Translation
  20. Improving Multilingual Neural Machine Translation by Utilizing Semantic and Linguistic Features
  21. Integrating Multi-scale Contextualized Information for Byte-based Neural Machine Translation
  22. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations), ACL 2024, Bangkok, Thailand, August 11-16, 2024
  23. Speculative Decoding with CTC-based Draft Model for LLM Inference Acceleration
  24. StreamSpeech: Simultaneous Speech-to-Speech Translation with Multi-task Learning
  25. Truth-Aware Context Selection: Mitigating Hallucinations of Large Language Models Being Misled by Untruthful Contexts
  26. TruthX: Alleviating Hallucinations by Editing Large Language Models in Truthful Space