Zunnan Xu

Venues

Frequent coauthors

Papers

1. Training-Free Adaptive Speculative Decoding via Linguistic Priors
   ACL 2026 ·

   Jingyi Wang

   DBLP profile ↗ORCID search ↗
2. Zo3T: Zero-Shot 3D-Aware Trajectory-Guided Image-to-Video Generation via Test-Time Training
   AAAI 2026 ·

   Ruicheng Zhang

   DBLP profile ↗ORCID search ↗
3. AToM: Aligning Text-to-Motion Model at Event-Level with GPT-4Vision Reward
   CVPR 2025 ·

   Haonan Han

   DBLP profile ↗ORCID search ↗
4. Audio-Visual Controlled Video Diffusion with Masked Selective State Spaces Modeling for Natural Talking Head Generation
   ICCV 2025 ·

   Fa-Ting Hong

   DBLP profile ↗ORCID search ↗
5. Densely Connected Parameter-Efficient Tuning for Referring Image Segmentation
   AAAI 2025 ·

   Jiaqi Huang

   DBLP profile ↗ORCID search ↗
6. FireEdit: Fine-grained Instruction-based Image Editing via Region-aware Vision Language Model
   CVPR 2025 ·

   Jun Zhou

   DBLP profile ↗ORCID search ↗
7. HunyuanPortrait: Implicit Condition Control for Enhanced Portrait Animation
   CVPR 2025 · Zunnan Xu
8. InterAnimate: Taming Region-Aware Diffusion Model for Realistic Human Interaction Animation
   ACM MM 2025 ·

   Yukang Lin

   DBLP profile ↗ORCID search ↗
9. REPARO: Compositional 3D Assets Generation with Differentiable 3D Layout Alignment
   ICCV 2025 ·

   Haonan Han

   DBLP profile ↗ORCID search ↗
10. SAM-R1: Leveraging SAM for Reward Feedback in Multimodal Segmentation via Reinforcement Learning
    NeurIPS 2025 ·

    Jiaqi Huang

    DBLP profile ↗ORCID search ↗
11. Separate to Collaborate: Dual-Stream Diffusion Model for Coordinated Piano Hand Motion Synthesis
    ACM MM 2025 ·

    Zihao Liu

    DBLP profile ↗ORCID search ↗
12. BATON: Aligning Text-to-Audio Model Using Human Preference Feedback
    IJCAI 2024 ·

    Huan Liao

    DBLP profile ↗ORCID search ↗
13. Chain of Generation: Multi-Modal Gesture Synthesis via Cascaded Conditional Control
    AAAI 2024 · Zunnan Xu
14. Consistent123: One Image to Highly Consistent 3D Asset Using Case-Aware Diffusion Priors
    ACM MM 2024 ·

    Yukang Lin

    DBLP profile ↗ORCID search ↗
15. MaPPER: Multimodal Prior-guided Parameter Efficient Tuning for Referring Expression Comprehension
    EMNLP 2024 ·

    Ting Liu

    DBLP profile ↗ORCID search ↗
16. MambaTalk: Efficient Holistic Gesture Synthesis with Selective State Space Models
    NeurIPS 2024 · Zunnan Xu