Publications

2026

• P2Voxel: Pyramid Pivot Voxelization for 3D Mesh Tokenization Manuscript First
  Zhenhong Sun, Haozhe Liu, Yifu Wang, Xibin Song, Steve Wang, Huadong Mo, Daoyi Dong, Hongdong Li, Pan Ji
  Submitted to a Top-Tier Machine Learning Conference, 2026.
• Hi-TOPS: Hierarchical Topology-aware Scoring Prior for 3D Part Decomposition Manuscript Co-First
  Ruoyu Wu, Zhenhong Sun, Xiaoming Gong, Yuxin Xian, Zhi Wang, Yawen Chen, Huadong Mo, Daoyi Dong
  Submitted to a Top-Tier Graphics Conference, 2026.
• Look-Before-Move: Narrative-Grounded World Visual Attention in Dynamic 3D Story Worlds Manuscript Leader
  Jiaming Bian, Bingliang Li, Yuehao Wu, Pichao Wang, Zhi Wang, Hailan Ma, Huadong Mo, Zhenhong Sun
  Under Review, arXiv preprint arXiv:2606.26964, 2026.
• XTalker: Turn, Smile, and Speak in Controllable Talking Portrait Animation Manuscript First
  Zhenhong Sun, Beier Wang, Zhicheng Zhang, Zhongju Wang, Yu Zhang, Hailan Ma, Daoyi Dong, Huadong Mo, Ming Lin
  Submitted to IEEE Transactions on Cybernetics, 2026.
• Social Structure Matters in 3D Human-Human Interaction Generation Manuscript Leader
  Zhongju Wang, Beier Wang, Yatao Bian, Pichao Wang, Zhi Wang, Daoyi Dong, Hongdong Li, Huadong Mo, Zhenhong Sun
  Under Review, arXiv preprint arXiv:2606.24255, 2026.
• Escaping Confidence Trap: Evolutionary Decoding for Mathematical Reasoning in Diffusion LLMs Manuscript First
  Zhenhong Sun, Hanqing Zhao, Yatao Bian, Rong-Cheng Tu, Liuyue Xie, Xu Zhang, Jue Wang, Davide Modolo, Daoyi Dong, Dacheng Tao
  Submitted to a Top-Tier Machine Learning Conference, 2026.
• From Conflict to Consensus: Boosting Medical Reasoning via Multi-Round Agentic RAG Conference
  Wenhao Wu, Zhentao Tang, Yafu Li, Shixiong Kai, Mingxuan Yuan, Zhenhong Sun, Chunlin Chen, Zhi Wang
  International Conference on Machine Learning (ICML 2026).
• Scalable In-Context Q-Learning Conference
  Jinmei Liu, Fuhong Liu, Zhenhong Sun, Jianye Hao, Huaxiong Li, Bo Wang, Daoyi Dong, Chunlin Chen, Zhi Wang
  International Conference on Learning Representations (ICLR 2026).
• StoryBlender: Inter-Shot Consistent and Editable 3D Storyboard with Spatial-temporal Dynamics ECCV Co-First Leader
  Bingliang Li, Zhenhong Sun, Jiaming Bian, Yuehao Wu, Yifu Wang, Hongdong Li, Yatao Bian, Huadong Mo, Daoyi Dong
  European Conference on Computer Vision (ECCV), 2026.
• 3DXTalker: Unifying Identity, Lip Sync, Emotion, and Spatial Dynamics in Expressive 3D Talking Avatars Preprint Co-First Leader
  Zhongju Wang, Zhenhong Sun, Beier Wang, Yifu Wang, Daoyi Dong, Huadong Mo, Hongdong Li
  arXiv preprint arXiv:2602.10516, 2026.
• Learning Hierarchical Time-Frequency Representation for Long-Term Time Series Forecasting Journal
  Zhongju Wang, Zhenhong Sun, Yatao Bian, Huadong Mo, Daoyi Dong
  Information Processing & Management, 63(2):104358, 2026.
• Beyond the Dirac Delta: Mitigating Diversity Collapse in Reinforcement Fine-Tuning for Versatile Image Generation Preprint
  Jinmei Liu, Haoru Li, Zhenhong Sun, Chaofeng Chen, Yatao Bian, Bo Wang, Daoyi Dong, Chunlin Chen, Zhi Wang
  arXiv preprint arXiv:2601.12401, 2026.
• T3-S2S: Training-free Triplet Tuning for Sketch to Scene Generation Journal First
  Zhenhong Sun, Yifu Wang, Yonhon Ng, Yunfei Duan, Daoyi Dong, Hongdong Li, Pan Ji
  Transactions on Machine Learning Research (TMLR), 2026.