Rui Liu

Ph.D. candidate in Computer Science, University of Maryland

• ruiiu.github.io
• ruiliu@umd.edu
• Google Scholar

Research interests

RL for LLM post-training; Reward modeling and verification; Agentic LLMs and recursive self-improvement.

Education

Experience

Publications (24)

1. DeltaRubric: Generative Multimodal Reward Modeling via Joint Planning and Verification

   R. Liu, D. Yu, Z. Liang, Y. Shi, T. Zheng, R. Dai, H. Mi, P. Tokekar, L.

   Preprint, 2026

2. Align Then Reason: A Multimodal Lip-Sync Judge for Dubbing

   R. Liu, B. Jawade, H. Li, S. Mehta, K. Saxena, Y. Lan, C. Wolfe

   Preprint, 2026

3. CARE: Certifying Acceleration for Vision-Language-Action Inference

   R. Liu, T. Zheng, J. Gu, Z. Wang

   Preprint, 2026

4. Reinforcing Multimodal Reasoning Against Visual Degradation

   R. Liu, D. Yu, H. Liu, Y. Shi, T. Zheng, R. Dai, H. Mi, P. Tokekar, L.

   The Fortieth Annual Conference on Neural Information Processing Systems (NeurIPS, 2026)

5. Dual-Uncertainty Guided Policy Learning for Multimodal Reasoning

   R. Liu, D. Yu, T. Zheng, R. Dai, Z. Li, W. Yu, Z. Liang, L. Song, H. Mi, P. Tokekar, D. Yu

   The 2026 Conference on Empirical Methods in Natural Language Processing (EMNLP Findings, 2026)

6. Stable and Efficient Single-Rollout RL for Multimodal Reasoning

   R. Liu, D. Yu, L. Ke, H. Liu, Y. Zhou, Z. Liang, H. Mi, P. Tokekar, D. Yu

   The IEEE/CVF Conference on Computer Vision and Pattern Recognition 2026 (CVPR, 2026)

7. Dream-RSI: Recursive Self-Improvement through Evolving Worlds

   T. Zheng, X. Wu, Z. Zhang, Z. He, C. Zhang, B. Coleman, R. Wei, D. Bai, H. Liu, R. Liu, X. Wang, Y. Zhuan, W. Kang, R. Xiang, H. Huang, X. Cheng, Y. Guo

   Preprint, 2026

8. Active Asymmetric Multi-Agent Multimodal Learning under Uncertainty

   R. Liu, P. Tokekar, M. Lin

   Preprint, 2026

9. Adaptive Conformal Guidance for Learning under Uncertainty

   R. Liu, P. Gao, Y. Shen, M. Lin, P. Tokekar

   The Fourteenth International Conference on Learning Representations (ICLR, 2026)

10. Small RL Controller, Large Language Model: RL-Guided Adaptive Sampling for Test-Time Scaling

    R. Dai, T. Zheng, R. Liu, C. Huang, H. Zhu

    The 2026 Conference on Empirical Methods in Natural Language Processing (EMNLP, 2026)

11. LLMs Improving LLMs: Agentic Discovery for Test-Time Scaling

    T. Zheng, H. Liu, C. Huang, H. Bao, S. Zhang, R. Liu, R. Dai, R. Chen, C. Liu, T. Xiong, X. Wu, H. Zhang, H. Huang

    The Fortieth Annual Conference on Neural Information Processing Systems (NeurIPS, 2026)

12. Parallel-Probe: Towards Efficient Parallel Thinking via 2D Probing

    T. Zheng, C. Huang, R. Dai, Y. He, R. Liu, X. Ni, H. Bao, K. Wang, H. Zhu, J. Huang, F. Huang, H. Huang

    Forty-Third International Conference on Machine Learning (ICML, 2026)

13. Save the Good Prefix: Precise Error Penalization via Process-Supervised RL to Enhance LLM Reasoning

    H. Liu, D. Yu, S. Lu, Y. Zhou, R. Liu, Z. Liang, H. Mi, C. Wei, D. Yu

    The 64th Annual Meeting of the Association for Computational Linguistics (ACL Findings, 2026)

14. Self-Rewarding Vision-Language Model via Reasoning Decomposition

    Z. Li, W. Yu, C. Huang, R. Liu, Z. Liang, F. Liu, J. Chen, D. Yu, J. Boyd-Graber, H. Mi, D. Yu

    The Fourteenth International Conference on Learning Representations (ICLR, 2026)

15. Parallel-R1: Towards Parallel Thinking via Reinforcement Learning

    T. Zheng, H. Zhang, W. Yu, X. Wang, R. Dai, R. Liu, H. Bao, C. Huang, H. Huang, D. Yu

    The Fourteenth International Conference on Learning Representations (ICLR, 2026)

16. CDE: Curiosity-Driven Exploration for Efficient Reinforcement Learning in Large Language Models

    R. Dai, L. Song, H. Liu, Z. Liang, D. Yu, H. Mi, Z. Tu, R. Liu, T. Zheng, H. Zhu, D. Yu

    The Fourteenth International Conference on Learning Representations (ICLR, 2026)

17. Plug-and-Play Reweighting for Resilient Collaborative Decision-Making in Connected Autonomous Driving

    J. Liu, R. Liu, M. Lee, M. Lin, X. Liu, P. Gao

    2026 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS, 2026)

18. CAML: Collaborative Auxiliary Modality Learning for Multi-Agent Systems

    R. Liu, Y. Shen, P. Gao, P. Tokekar, M. Lin

    The Thirty-Ninth Annual Conference on Neural Information Processing Systems (NeurIPS, 2025)

19. MMCD: Multi-Modal Collaborative Decision-Making for Connected Autonomy with Knowledge Distillation

    R. Liu, P. Gao, Y. Shen, P. Tokekar, M. Lin

    2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS, 2025)

20. IMRL: Integrating Visual, Physical, Temporal, and Geometric Representations for Enhanced Food Acquisition

    R. Liu, Z. Mahammad, A. Bhaskar, P. Tokekar

    2025 IEEE International Conference on Robotics and Automation (ICRA, 2025)

21. Towards Efficient Risk-Sensitive Policy Gradient: An Iteration Complexity Analysis

    R. Liu, A. Gupta, E. Noorani, P. Tokekar

    Preprint, 2025

22. LAVA: Long-horizon Visual Action based Food Acquisition

    A. Bhaskar, R. Liu, V. Sharma, G. Shi, P. Tokekar

    2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS, 2024) Best Paper Award at ICRA 2024 Workshop on Cooking Robotics: Perception and Motion Planning

23. Data-Driven Distributionally Robust Optimal Control with State-Dependent Noise

    R. Liu, G. Shi, P. Tokekar

    2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS, 2023)

24. Adaptive Visual Imitation Learning for Robotic Assisted Feeding Across Varied Bowl Configurations and Food Types

    R. Liu, A. Bhaskar, P. Tokekar

    2024 IEEE International Conference on Robotics and Automation (Workshop)