Runsheng Yu

Computer Science · Physical Sciences

9h-index798citations29works1.42yr avg
OpenAlex↗Google Scholar↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Reinforcement Learning in Robotics(10), Generative Adversarial Networks and Image Synthesis(5), Domain Adaptation and Few-Shot Learning(4), Image Enhancement Techniques(3), Game Theory and Applications(3)

Publications29 total

How Much Information Can a Vision Token Hold? A Scaling Law for Recognition Limits in VLMs
arXiv (Cornell University)·2026Open Access
How Much Information Can a Vision Token Hold? A Scaling Law for Recognition Limits in VLMs
arXiv (Cornell University)·2026Open Access
Effect of vacancy-mediated precipitation on the microstructure and mechanical properties of 7075 aluminum alloy
Materials Characterization·2025
Transition-Informed Reinforcement Learning for Large-Scale Stackelberg Mean-Field Games
Proceedings of the AAAI Conference on Artificial Intelligence·2024· 6 citedOpen Access
Enhanced meta learning for few-shot learning, and recommendation system
2024· 1 cited
Mechanism of hydrogen-induced defects and cracking in Ti and Ti–Mo alloy
International Journal of Hydrogen Energy·2022· 17 cited
Image-Adaptive YOLO for Object Detection in Adverse Weather Conditions
Proceedings of the AAAI Conference on Artificial Intelligence·2022· 497 citedOpen Access
DO-GAN: A Double Oracle Framework for Generative Adversarial Networks
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)·2022· 1 cited
Constraint-aware Policy Optimization to Solve the Vehicle Routing Problem with Time Windows
Information Technology And Control·2022· 6 citedOpen Access
Image-Adaptive YOLO for Object Detection in Adverse Weather Conditions
arXiv (Cornell University)·2021· 3 citedOpen Access
RMIX: Learning Risk-Sensitive Policies forCooperative Reinforcement Learning Agents
arXiv (Cornell University)·2021· 1 citedOpen Access
RMIX: Learning risk-sensitive policies for cooperative reinforcement learning agents
Singapore Management University Institutional Knowledge (InK) (Singapore Management University)·2021Open Access
Neural Regret-Matching for Distributed Constraint Optimization Problems
2021· 4 citedOpen Access
Personalized Adaptive Meta Learning for Cold-start User Preference Prediction
Proceedings of the AAAI Conference on Artificial Intelligence·2021· 55 citedOpen Access
RMIX: Risk-Sensitive Multi-Agent Reinforcement Learning
2021· 2 cited
DO-GAN: A Double Oracle Framework for Generative Adversarial Networks
arXiv (Cornell University)·2021· 2 citedOpen Access
RMIX: Learning Risk-Sensitive Policies for Cooperative Reinforcement Learning Agents
arXiv (Cornell University)·2021· 16 citedOpen Access
Personalized Adaptive Meta Learning for Cold-start User Preference Prediction
arXiv (Cornell University)·2020· 1 citedOpen Access
Learning to Collaborate in Multi-Module Recommendation via Multi-Agent Reinforcement Learning without Communication
2020· 33 cited
Learning to Collaborate in Multi-Module Recommendation via Multi-Agent Reinforcement Learning without Communication
arXiv (Cornell University)·2020· 9 citedOpen Access
page 1 of 2Next →

Frequent Co-authors

Bo An(17), Xinrun Wang(12), Rundong Wang(11), Xu He(7), Zinovi Rabinovich(7), Wei Qiu(6), Svetlana Obraztsova(4), Wenyu Liu(3), Gaofeng Ren(2), Jianke Zhu(2), Yu Gong(2), Qingwen Liu(2), Wenwu Ou(2), Yanghua Li(2), Haikai Chen(2), Xin Li(2), Te Zhu(2), Xingzhong Cao(2), Xu He(2), Zhenyu Shi(2)