Da-Cheng Yin

Most-cited papers

1. R1-Onevision: Advancing Generalized Multimodal Reasoning Through Cross-Modal Formalization

   Yi Yang, Xiao-Xuan He, H. Pan, Xi-Yan Jiang +8 more

   2025IEEE International Conference on Computer Vision425 citations

   Semantic Scholar

   Save

2. TempFlow-GRPO: When Timing Matters for GRPO in Flow Models

   Xiao-Xuan He, Siming Fu, Yuke Zhao, Wan-Li Li +4 more

   2025arXiv.org107 citations

   Semantic Scholar

   Save

3. MMAR: Towards Lossless Multi-Modal Auto-Regressive Probabilistic Modeling

   Jian Yang, Da-Cheng Yin, Yizhou Zhou, Feng-Yun Rao +3 more

   2024Computer Vision and Pattern Recognition21 citations Open access

   Semantic Scholar

   Save

4. WeThink: Toward General-purpose Vision-Language Reasoning via Reinforcement Learning

   Jie Yang, Fei-Peng Ma, Zi-Tian Wang, Da-Cheng Yin +3 more

   2025arXiv.org15 citations

   Semantic Scholar

   Save

5. AdaMem: Adaptive User-Centric Memory for Long-Horizon Dialogue Agents

   Shan-Nan Yan, Jingchen Ni, Leqi Zheng, Jiajun Zhang +5 more

   2026arXiv.org12 citations

   Semantic Scholar

   Save

6. Beyond Chain-of-Thought: Rewrite as a Universal Interface for Generative Multimodal Embeddings

   Pei-Xi Wu, Ke Mei, Fei-Peng Ma, Bo-Song Chai +14 more

   2026arXiv.org4 citations

   Semantic Scholar

   Save

7. SAIL: Self-Amplified Iterative Learning for Diffusion Model Alignment with Minimal Human Feedback

   Xiao-Xuan He, Siming Fu, Wan-Li Li, Zhiyuan Li +4 more

   2026arXiv.org4 citations

   Semantic Scholar

   Save

8. Flash-GRPO: Efficient Alignment for Video Diffusion via One-Step Policy Optimization

   Xiao-Xuan He, Siming Fu, Ze-Yue Xue, Wei-Jie Wang +8 more

   2026arXiv.org4 citations

   Semantic Scholar

   Save

9. Unified Urban Tuning: Co-Enhancing Satellite and Street View Reasoning with a Progressive Tuning Framework

   Yong Li, Wei-Yu Zhang, Ling Dai, Jian Yang +5 more

   20262026 IEEE/CVF Conference on Computer Vision and Pattern Recognition- FINDINGS Track (CVPRF)2 citations

   Semantic Scholar

   Save

10. REVERSE: Reinforcing Evidence Verification and Search for Agentic Image geo-localization

    Yong Li, Fu-Rong Jia, Da-Cheng Yin, Kang Rong +3 more

    2026arXiv.org2 citations

    Semantic Scholar

    Save

11. WeMMU: Enhanced Bridging of Vision-Language Models and Diffusion Models via Noisy Query Tokens

    Jian Yang, Da-Cheng Yin, Xiao-Xuan He, Yong Li +5 more

    2025arXiv.org1 citations

    Semantic Scholar

    Save

12. Interpolated Policy Distillation: A Controllable Continuum Between Off-Policy and On-Policy Distillation

    You-Xu Shi, Yi-Fan Sun, Da-Cheng Yin, Hao-Miao Tang +4 more

    20260 citations

    Semantic Scholar

    Save