PPaperPicks

Kai Yu

Shanghai Jiao Tong University, Computer Science and Engineering Department, China

36 papers at tracked venues · 21 at CORE A* · active 2024–2026

DBLP profile ↗ORCID 0000-0002-7102-9826 ↗Homepage ↗

Venues

InterSpeech ×7ACL ×6NeurIPS ×5AAAI ×4EMNLP ×4ICML ×3ACM MM ×2NAACL ×2EACL ×1ICCV ×1WSDM ×1

Frequent coauthors

Hongshen Xu
DBLP profile ↗ORCID search ↗
×3
Yiwei Guo
DBLP profile ↗ORCID search ↗
×2
Yifan Yang
DBLP profile ↗ORCID search ↗
×2
Senyu Han
DBLP profile ↗ORCID search ↗
×2
Yang Han
DBLP profile ↗ORCID search ↗
×2
Ruisheng Cao
DBLP profile ↗ORCID search ↗
×2
Da Ma
DBLP profile ↗ORCID search ↗
×2
Tao Liu
DBLP profile ↗ORCID search ↗
×2
Haoran Wang
DBLP profile ↗ORCID search ↗
×1
Qixi Zheng
DBLP profile ↗ORCID search ↗
×1
Xiao Li
DBLP profile ↗ORCID search ↗
×1
Kunyun Wang
DBLP profile ↗ORCID search ↗
×1

Papers

  1. AHAMask: Reliable Task Specification for Large Audio Language Models Without Instructions
    AAAI 2026 ·
    Yiwei Guo
    DBLP profile ↗ORCID search ↗
  2. BSCodec: A Band-Split Neural Codec for High-Quality Universal Audio Reconstruction
    EACL 2026 ·
    Haoran Wang
    DBLP profile ↗ORCID search ↗
  3. Accelerating Flow-Matching-Based Text-to-Speech via Empirically Pruned Step Sampling
    InterSpeech 2025 ·
    Qixi Zheng
    DBLP profile ↗ORCID search ↗
  4. Alignment for Efficient Tool Calling of Large Language Models
    EMNLP 2025 ·
    Hongshen Xu
    DBLP profile ↗ORCID search ↗
  5. Bitrate-Controlled Diffusion for Disentangling Motion and Content in Video
    ICCV 2025 ·
    Xiao Li
    DBLP profile ↗ORCID search ↗
  6. Communication-Efficient Diffusion Denoising Parallelization via Reuse-then-Predict Mechanism
    NeurIPS 2025 ·
    Kunyun Wang
    DBLP profile ↗ORCID search ↗
  7. Enhancing Speech-to-Speech Dialogue Modeling with End-to-End Retrieval-Augmented Generation
    EMNLP 2025 ·
    Pengchao Feng
    DBLP profile ↗ORCID search ↗
  8. F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching
    ACL 2025 ·
    Yushen Chen
    DBLP profile ↗ORCID search ↗
  9. GigaSpeech 2: An Evolving, Large-Scale and Multi-domain ASR Corpus for Low-Resource Languages with Automated Crawling, Transcription and Refinement
    ACL 2025 ·
    Yifan Yang
    DBLP profile ↗ORCID search ↗
  10. Heads up! Large Language Models Can Perform Tasks Without Your Instruction via Selective Attention Head Masking
    ICML 2025 ·
    Senyu Han
    DBLP profile ↗ORCID search ↗
  11. LSCodec: Low-Bitrate and Speaker-Decoupled Discrete Speech Codec
    InterSpeech 2025 ·
    Yiwei Guo
    DBLP profile ↗ORCID search ↗
  12. MMAR: A Challenging Benchmark for Deep Reasoning in Speech, Audio, Music, and Their Mix
    NeurIPS 2025 ·
    Ziyang Ma
    DBLP profile ↗ORCID search ↗
  13. MS-BART: Unified Modeling of Mass Spectra and Molecules for Structure Elucidation
    NeurIPS 2025 ·
    Yang Han
    DBLP profile ↗ORCID search ↗
  14. MobA: Multifaceted Memory-Enhanced Adaptive Planning for Efficient Mobile Task Automation
    NAACL 2025 ·
    Zichen Zhu
    DBLP profile ↗ORCID search ↗
  15. NeuSym-RAG: Hybrid Neural Symbolic Retrieval with Multiview Structuring for PDF Question Answering
    ACL 2025 ·
    Ruisheng Cao
    DBLP profile ↗ORCID search ↗
  16. Pseudo-Autoregressive Neural Codec Language Models for Efficient Zero-Shot Text-to-Speech Synthesis
    ACM MM 2025 ·
    Yifan Yang
    DBLP profile ↗ORCID search ↗
  17. Reducing Tool Hallucination via Reliability Alignment
    ICML 2025 ·
    Hongshen Xu
    DBLP profile ↗ORCID search ↗
  18. SLAM-Omni: Timbre-Controllable Voice Interaction System with Single-Stage Training
    ACL 2025 ·
    Wenxi Chen
    DBLP profile ↗ORCID search ↗
  19. Task-Specific Data Selection for Instruction Tuning via Monosemantic Neuronal Activations
    NeurIPS 2025 ·
    Da Ma
    DBLP profile ↗ORCID search ↗
  20. URO-Bench: Towards Comprehensive Evaluation for End-to-End Spoken Dialogue Models
    EMNLP 2025 ·
    Ruiqi Yan
    DBLP profile ↗ORCID search ↗
  21. Unlocking Temporal Flexibility: Neural Speech Codec with Variable Frame Rate
    InterSpeech 2025 ·
    Hanglei Zhang
    DBLP profile ↗ORCID search ↗
  22. VQTalker: Towards Multilingual Talking Avatars Through Facial Motion Tokenization
    AAAI 2025 ·
    Tao Liu
    DBLP profile ↗ORCID search ↗
  23. VietASR: Achieving Industry-level Vietnamese ASR with 50-hour labeled data and Large-Scale Speech Pretraining
    InterSpeech 2025 ·
    Jianheng Zhuo
    DBLP profile ↗ORCID search ↗
  24. AlignSum: Data Pyramid Hierarchical Fine-tuning for Aligning with Human Summarization Preference
    EMNLP 2024 ·
    Yang Han
    DBLP profile ↗ORCID search ↗
  25. AniTalker: Animate Vivid and Diverse Talking Faces through Identity-Decoupled Facial Motion Encoding
    ACM MM 2024 ·
    Tao Liu
    DBLP profile ↗ORCID search ↗
  26. CoE-SQL: In-Context Learning for Multi-Turn Text-to-SQL with Chain-of-Editions
    NAACL 2024 ·
    Hanchong Zhang
    DBLP profile ↗ORCID search ↗
  27. DiveSound: LLM-Assisted Automatic Taxonomy Construction for Diverse Audio Generation
    InterSpeech 2024 ·
    Baihan Li
    DBLP profile ↗ORCID search ↗
  28. Evolving Subnetwork Training for Large Language Models
    ICML 2024 ·
    Hanqi Li
    DBLP profile ↗ORCID search ↗
  29. Hierarchical Multimodal Pre-training for Visually Rich Webpage Understanding
    WSDM 2024 ·
    Hongshen Xu
    DBLP profile ↗ORCID search ↗
  30. IBSEN: Director-Actor Agent Collaboration for Controllable and Interactive Drama Script Generation
    ACL 2024 ·
    Senyu Han
    DBLP profile ↗ORCID search ↗
  31. On the Effectiveness of Acoustic BPE in Decoder-Only TTS
    InterSpeech 2024 ·
    Bohan Li
    DBLP profile ↗ORCID search ↗
  32. SciEval: A Multi-Level Large Language Model Evaluation Benchmark for Scientific Research
    AAAI 2024 ·
    Liangtai Sun
    DBLP profile ↗ORCID search ↗
  33. Sparsity-Accelerated Training for Large Language Models
    ACL 2024 ·
    Da Ma
    DBLP profile ↗ORCID search ↗
  34. Spider2-V: How Far Are Multimodal Agents From Automating Data Science and Engineering Workflows?
    NeurIPS 2024 ·
    Ruisheng Cao
    DBLP profile ↗ORCID search ↗
  35. Text-aware Speech Separation for Multi-talker Keyword Spotting
    InterSpeech 2024 ·
    Haoyu Li
    DBLP profile ↗ORCID search ↗
  36. UniCATS: A Unified Context-Aware Text-to-Speech Framework with Contextual VQ-Diffusion and Vocoding
    AAAI 2024 ·
    Chenpeng Du
    DBLP profile ↗ORCID search ↗