Xun Zhou

Venues

Frequent coauthors

Papers

1. IndexTTS2: A Breakthrough in Emotionally Expressive and Duration-Controlled Auto-Regressive Zero-Shot Text-to-Speech
   AAAI 2026 ·

   Siyi Zhou

   DBLP profile ↗ORCID search ↗
2. Population-Aware Contrastive Surrogates for Expensive Multiobjective Optimization
   PPSN 2026 ·

   Songbai Liu

   DBLP profile ↗ORCID search ↗
3. Sparse Poisson Gamma Belief Networks for High-Dimensional Sparse Count Data
   AAAI 2026 ·

   Rui Huang

   DBLP profile ↗ORCID search ↗
4. Adaptive Domain Scaling for Personalized Sequential Modeling in Recommenders
   SIGIR 2025 ·

   Zheng Chai

   DBLP profile ↗ORCID search ↗
5. Design Principle Transfer in Neural Architecture Search via Large Language Models
   AAAI 2025 · Xun Zhou
6. Expert Race: A Flexible Routing Strategy for Scaling Diffusion Transformer with Mixture of Experts
   ICML 2025 ·

   Yike Yuan

   DBLP profile ↗ORCID search ↗
7. FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference
   ICLR 2025 ·

   Xunhao Lai

   DBLP profile ↗ORCID search ↗
8. HybridNorm: Towards Stable and Efficient Transformer Training via Hybrid Normalization
   NeurIPS 2025 ·

   Zhijian Zhuo

   DBLP profile ↗ORCID search ↗
9. Hyper-Connections
   ICLR 2025 ·

   Defa Zhu

   DBLP profile ↗ORCID search ↗
10. Large Memory Network for Recommendation
    WWW 2025 ·

    Hui Lu

    DBLP profile ↗ORCID search ↗
11. MARS: Unleashing the Power of Variance Reduction for Training Large Models
    ICML 2025 ·

    Huizhuo Yuan

    DBLP profile ↗ORCID search ↗
12. Model Merging in Pre-training of Large Language Models
    NeurIPS 2025 ·

    Yunshui Li

    DBLP profile ↗ORCID search ↗
13. Over-Tokenized Transformer: Vocabulary is Generally Worth Scaling
    ICML 2025 ·

    Hongzhi Huang

    DBLP profile ↗ORCID search ↗
14. Polynomial Composition Activations: Unleashing the Dynamics of Large Language Models
    ICLR 2025 ·

    Zhijian Zhuo

    DBLP profile ↗ORCID search ↗
15. PrevPredMap: Exploring Temporal Modeling with Previous Predictions for Online Vectorized HD Map Construction
    WACV 2025 ·

    Nan Peng

    DBLP profile ↗ORCID search ↗
16. RankMixer: Scaling Up Ranking Models in Industrial Recommenders
    CIKM 2025 ·

    Jie Zhu

    DBLP profile ↗ORCID search ↗
17. Real-time Indexing for Large-scale Recommendation by Streaming Vector Quantization Retriever
    SIGKDD 2025 ·

    Xingyan Bin

    DBLP profile ↗ORCID search ↗
18. Stepsize anything: A unified learning rate schedule for budgeted-iteration training
    NeurIPS 2025 ·

    Anda Tang

    DBLP profile ↗ORCID search ↗
19. Ultra-Sparse Memory Network
    ICLR 2025 ·

    Zihao Huang

    DBLP profile ↗ORCID search ↗
20. UniTraj: Learning a Universal Trajectory Foundation Model from Billion-Scale Worldwide Traces
    NeurIPS 2025 ·

    Yuanshao Zhu

    DBLP profile ↗ORCID search ↗
21. FT-GAN: Fine-Grained Tune Modeling for Chinese Opera Synthesis
    AAAI 2024 ·

    Meizhen Zheng

    DBLP profile ↗ORCID search ↗
22. MoTE: Reconciling Generalization with Specialization for Visual-Language to Video Knowledge Transfer
    NeurIPS 2024 ·

    Minghao Zhu

    DBLP profile ↗ORCID search ↗
23. SNF-Feat: Semantic-Guided Negative-Sample-Free Representation Learning for Local Feature Extraction
    IROS 2024 · Xun Zhou
24. Seeing the Image: Prioritizing Visual Correlation by Contrastive Alignment
    NeurIPS 2024 ·

    Xin Xiao

    DBLP profile ↗ORCID search ↗
25. World to Code: Multi-modal Data Generation via Self-Instructed Compositional Captioning and Filtering
    EMNLP 2024 ·

    Jiacong Wang

    DBLP profile ↗ORCID search ↗