Yuexian Zou

Venues

Frequent coauthors

Papers

1. Not All Tokens and Heads Are Equally Important: Dual-Level Attention Intervention for Hallucination Mitigation
   AAAI 2026 ·

   Lexiang Tang

   DBLP profile ↗ORCID search ↗
2. WhisperDiari: A Whisper-Based Speaker Diarization Framework in Token Space Leveraging Semantic and Speaker Information for Better Text Adaptability
   AAAI 2026 ·

   Yongkang Yin

   DBLP profile ↗ORCID search ↗
3. ATRI: Mitigating Multilingual Audio Text Retrieval Inconsistencies by Reducing Data Distribution Errors
   ACL 2025 ·

   Yuguo Yin

   DBLP profile ↗ORCID search ↗
4. Advancing General Multimodal Capability of Vision-language Models with Pyramid-descent Visual Position Encoding
   ACL 2025 ·

   Zhanpeng Chen

   DBLP profile ↗ORCID search ↗
5. FoleyMaster: High-Quality Video-to-Audio Synthesis via MLLM-Augmented Prompt Tuning and Joint Semantic-Temporal Adaptation
   InterSpeech 2025 ·

   Liming Liang

   DBLP profile ↗ORCID search ↗
6. Image Conductor: Precision Control for Interactive Video Synthesis
   AAAI 2025 ·

   Yaowei Li

   DBLP profile ↗ORCID search ↗
7. SpeechSEC: A Unified Multi-Task Framework for Speech Synthesis, Editing, and Continuation
   InterSpeech 2025 ·

   Liming Liang

   DBLP profile ↗ORCID search ↗
8. UniCoTT: A Unified Framework for Structural Chain-of-Thought Distillation
   ICLR 2025 ·

   Xianwei Zhuang

   DBLP profile ↗ORCID search ↗
9. VASparse: Towards Efficient Visual Hallucination Mitigation via Visual-Aware Token Sparsification
   CVPR 2025 ·

   Xianwei Zhuang

   DBLP profile ↗ORCID search ↗
10. AFL-Net: Integrating Audio, Facial, and Lip Modalities with a Two-step Cross-attention for Robust Speaker Diarization in the Wild
    InterSpeech 2024 ·

    Yongkang Yin

    DBLP profile ↗ORCID search ↗
11. Aligner²: Enhancing Joint Multiple Intent Detection and Slot Filling via Adjustive and Forced Cross-Task Alignment
    AAAI 2024 ·

    Zhihong Zhu

    DBLP profile ↗ORCID search ↗
12. Audio-text Retrieval with Transformer-based Hierarchical Alignment and Disentangled Cross-modal Representation
    InterSpeech 2024 ·

    Yifei Xin

    DBLP profile ↗ORCID search ↗
13. AudioGPT: Understanding and Generating Speech, Music, Sound, and Talking Head
    AAAI 2024 ·

    Rongjie Huang

    DBLP profile ↗ORCID search ↗
14. Code-Switching Can be Better Aligners: Advancing Cross-Lingual SLU through Representation-Level and Prediction-Level Alignment
    ACL 2024 ·

    Zhihong Zhu

    DBLP profile ↗ORCID search ↗
15. Cyclical Contrastive Learning Based on Geodesic for Zero-shot Cross-lingual Spoken Language Understanding
    ACL 2024 ·

    Xuxin Cheng

    DBLP profile ↗ORCID search ↗
16. Dance with Labels: Dual-Heterogeneous Label Graph Interaction for Multi-intent Spoken Language Understanding
    WSDM 2024 ·

    Zhihong Zhu

    DBLP profile ↗ORCID search ↗
17. DiffATR: Diffusion-based Generative Modeling for Audio-Text Retrieval
    InterSpeech 2024 ·

    Yifei Xin

    DBLP profile ↗ORCID search ↗
18. Dual-oriented Disentangled Network with Counterfactual Intervention for Multimodal Intent Detection
    EMNLP 2024 ·

    Zhanpeng Chen

    DBLP profile ↗ORCID search ↗
19. Embracing Language Inclusivity and Diversity in CLIP through Continual Language Learning
    AAAI 2024 ·

    Bang Yang

    DBLP profile ↗ORCID search ↗
20. Exploiting Auxiliary Caption for Video Grounding
    AAAI 2024 ·

    Hongxiang Li

    DBLP profile ↗ORCID search ↗
21. GPA: Global and Prototype Alignment for Audio-Text Retrieval
    InterSpeech 2024 ·

    Yuxin Xie

    DBLP profile ↗ORCID search ↗
22. Game on Tree: Visual Hallucination Mitigation via Coarse-to-Fine View Tree and Game Theory
    EMNLP 2024 ·

    Xianwei Zhuang

    DBLP profile ↗ORCID search ↗
23. Generating More Audios for End-to-End Spoken Language Understanding
    IJCAI 2024 ·

    Xuxin Cheng

    DBLP profile ↗ORCID search ↗
24. KDProR: A Knowledge-Decoupling Probabilistic Framework for Video-Text Retrieval
    ECCV 2024 ·

    Xianwei Zhuang

    DBLP profile ↗ORCID search ↗
25. Learning to Match Representations is Better for End-to-End Task-Oriented Dialog System
    EMNLP 2024 ·

    Wanshi Xu

    DBLP profile ↗ORCID search ↗
26. MaCSC: Towards Multimodal-augmented Pre-trained Language Models via Conceptual Prototypes and Self-balancing Calibration
    NAACL 2024 ·

    Xianwei Zhuang

    DBLP profile ↗ORCID search ↗
27. MoE-SLU: Towards ASR-Robust Spoken Language Understanding via Mixture-of-Experts
    ACL 2024 ·

    Xuxin Cheng

    DBLP profile ↗ORCID search ↗
28. On the Worst Prompt Performance of Large Language Models
    NeurIPS 2024 ·

    Bowen Cao

    DBLP profile ↗ORCID search ↗
29. PCAD: Towards ASR-Robust Spoken Language Understanding via Prototype Calibration and Asymmetric Decoupling
    ACL 2024 ·

    Xianwei Zhuang

    DBLP profile ↗ORCID search ↗
30. Relevance Is a Guiding Light: Relevance-aware Adaptive Learning for End-to-end Task-oriented Dialogue System
    EMNLP 2024 ·

    Zhanpeng Chen

    DBLP profile ↗ORCID search ↗
31. Retrieval is Accurate Generation
    ICLR 2024 ·

    Bowen Cao

    DBLP profile ↗ORCID search ↗
32. Robust Heterophily Graph Learning via Uniformity Augmentation
    CIKM 2024 ·

    Xusheng Yang

    DBLP profile ↗ORCID search ↗
33. SaLa: Scenario-aware Label Graph Interaction for Multi-intent Spoken Language Understanding
    CIKM 2024 ·

    Zhihong Zhu

    DBLP profile ↗ORCID search ↗
34. Soul-Mix: Enhancing Multimodal Machine Translation with Manifold Mixup
    ACL 2024 ·

    Xuxin Cheng

    DBLP profile ↗ORCID search ↗
35. Towards Explainable Joint Models via Information Theory for Multiple Intent Detection and Slot Filling
    AAAI 2024 ·

    Xianwei Zhuang

    DBLP profile ↗ORCID search ↗
36. Towards Multi-Intent Spoken Language Understanding via Hierarchical Attention and Optimal Transport
    AAAI 2024 ·

    Xuxin Cheng

    DBLP profile ↗ORCID search ↗
37. Towards Multimodal-augmented Pre-trained Language Models via Self-balanced Expectation-Maximization Iteration
    ACM MM 2024 ·

    Xianwei Zhuang

    DBLP profile ↗ORCID search ↗
38. What are the Generator Preferences for End-to-end Task-Oriented Dialog System?
    EMNLP 2024 ·

    Wanshi Xu

    DBLP profile ↗ORCID search ↗