Lune

Profiles2022-2026

Qingkai Fang

University of Chinese Academy of Sciences

16Papers
0Last author
12Unique co-authors
8First author
0Solo

First and last author come from byline position, which some venues assign alphabetically.

Recent papers16

  1. Efficient Training for Cross-lingual Speech Language ModelsAuthor 2 of 4ACL Findings 2026
  2. FastLongSpeech: Enhancing Large Speech-Language Models for Efficient Long-Speech ProcessingAuthor 3 of 6NeurIPS 2025 · 4 citations
  3. LLaMA-Omni: Seamless Speech Interaction with Large Language ModelsAuthor 1 of 6ICLR 2025 · 2 citations
  4. LLaMA-Omni 2: LLM-based Real-time Spoken Chatbot with Autoregressive Streaming Speech SynthesisAuthor 1 of 5ACL 2025
  5. LLaVA-Mini: Efficient Image and Video Large Multimodal Models with One Vision TokenAuthor 2 of 4ICLR 2025
  6. A Non-autoregressive Generation Framework for End-to-End Simultaneous Speech-to-Any TranslationAuthor 2 of 6ACL 2024 · 5 citations
  7. Can We Achieve High-quality Direct Speech-to-Speech Translation without Parallel Speech Data?Author 1 of 5ACL 2024 · 1 citation
  8. StreamSpeech: Simultaneous Speech-to-Speech Translation with Multi-task LearningAuthor 2 of 6ACL 2024
  9. CMOT: Cross-modal Mixup via Optimal Transport for Speech TranslationAuthor 2 of 4ACL 2023 · 24 citations
  10. DASpeech: Directed Acyclic Transformer for Fast and High-quality Speech-to-Speech TranslationAuthor 1 of 3NeurIPS 2023 · 22 citations
  11. Understanding and Bridging the Modality Gap for Speech TranslationAuthor 1 of 2ACL 2023 · 12 citations
  12. Back Translation for Speech-to-text Translation Without TranscriptsAuthor 1 of 3ACL 2023 · 9 citations
  13. Bridging the Gap between Synthetic and Authentic Images for Multimodal Machine TranslationAuthor 2 of 4EMNLP 2023 · 5 citations
  14. Low-resource Neural Machine Translation with Cross-modal AlignmentAuthor 2 of 3EMNLP 2022 · 4 citations
  15. Neural Machine Translation with Phrase-Level Universal Visual RepresentationsAuthor 1 of 2ACL 2022
  16. STEMM: Self-learning with Speech-text Manifold Mixup for Speech TranslationAuthor 1 of 5ACL 2022
Dusk over the sea between two cliffs drawn in fine vertical lines