Di Wang

Venues

Frequent coauthors

Papers

1. Reinforcement Learning on Pre-Training Data
   ACL 2026 ·

   Siheng Li

   DBLP profile ↗ORCID search ↗
2. TransMamba: A Sequence-Level Hybrid Transformer-Mamba Language Model
   AAAI 2026 ·

   Yixing Li

   DBLP profile ↗ORCID search ↗
3. Union-of-Experts: Neurons in Mixture-of-Experts are Secretly Routers
   ACL 2026 ·

   Songhao Wu

   DBLP profile ↗ORCID search ↗
4. Autonomy-of-Experts Models
   ICML 2025 ·

   Ang Lv

   DBLP profile ↗ORCID search ↗
5. DHCP: Detecting Hallucinations by Cross-modal Attention Pattern in Large Vision-Language Models
   ACM MM 2025 ·

   Yudong Zhang

   DBLP profile ↗ORCID search ↗
6. Fighting Fire with Fire (F3): A Training-free and Efficient Visual Adversarial Example Purification Method in LVLMs
   ACM MM 2025 ·

   Yudong Zhang

   DBLP profile ↗ORCID search ↗
7. HMoE: Heterogeneous Mixture of Experts for Language Modeling
   EMNLP 2025 ·

   An Wang

   DBLP profile ↗ORCID search ↗
8. Hydraulis: Balancing Large Transformer Model Training via Co-designing Parallel Strategies and Data Assignment
   SIGMOD 2025 ·

   Haoyang Li

   DBLP profile ↗ORCID search ↗
9. Scaling Laws for Floating-Point Quantization Training
   ICML 2025 ·

   Xingwu Sun

   DBLP profile ↗ORCID search ↗
10. The Security Threat of Compressed Projectors in Large Vision-Language Models
    EMNLP 2025 ·

    Yudong Zhang

    DBLP profile ↗ORCID search ↗
11. Surge Phenomenon in Optimal Learning Rate and Batch Size Scaling
    NeurIPS 2024 ·

    Shuaipeng Li

    DBLP profile ↗ORCID search ↗
12. Truth Forest: Toward Multi-Scale Truthfulness in Large Language Models through Intervention without Tuning
    AAAI 2024 ·

    Zhongzhi Chen

    DBLP profile ↗ORCID search ↗