Chenjia Bai

Northwestern Polytechnical University — China

Computer Science · Physical Sciences

10h-index401citations89works0.82yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

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

Research Topics

Reinforcement Learning in Robotics(41), Advanced Bandit Algorithms Research(12), Evolutionary Algorithms and Applications(9), Adaptive Dynamic Programming Control(9), Natural Language Processing Techniques(8)

Publications89 total

Continuous alignment of multi-target preferences via instructed diffusion model
Pattern Recognition·2025
Efficient Cross-Domain Offline Reinforcement Learning with Dynamics- and Value-Aligned Data Filtering
ArXiv.org·2025Open Access
Steering Vision-Language-Action Models as Anti-Exploration: A Test-Time Scaling Approach
arXiv (Cornell University)·2025Open Access
Preference Aligned Diffusion Planner for Quadrupedal Locomotion Control
2025
Humanoid Whole-Body Locomotion on Narrow Terrain via Dynamic Balance and Reinforcement Learning
2025
Skill-Nav: enhanced navigation with versatile quadrupedal locomotion via waypoint interface
Vicinagearth.·2025Open Access
Unsupervised Skill Discovery Through Skill Regions Differentiation
IEEE Transactions on Neural Networks and Learning Systems·2025
Towards Reliable LLM-based Robot Planning via Combined Uncertainty Estimation
arXiv (Cornell University)·2025Open Access
KungfuBot2: Learning Versatile Motion Skills for Humanoid Whole-Body Control
arXiv (Cornell University)·2025Open Access
Align-Then-stEer: Adapting the Vision-Language Action Models through Unified Latent Guidance
arXiv (Cornell University)·2025Open Access
Temporal consistent multi-view perception for robust embodied manipulation
Pattern Recognition·2025
Provably efficient information-directed sampling algorithms for multi-agent reinforcement learning
Artificial Intelligence·2025
HumanoidGen: Data Generation for Bimanual Dexterous Manipulation via LLM Reasoning
arXiv (Cornell University)·2025Open Access
Skill-Nav: Enhanced Navigation with Versatile Quadrupedal Locomotion via Waypoint Interface
arXiv (Cornell University)·2025Open Access
Unsupervised Skill Discovery through Skill Regions Differentiation
arXiv (Cornell University)·2025Open Access
KungfuBot: Physics-Based Humanoid Whole-Body Control for Learning Highly-Dynamic Skills
arXiv (Cornell University)·2025Open Access
MoRE: Mixture of Residual Experts for Humanoid Lifelike Gaits Learning on Complex Terrains
arXiv (Cornell University)·2025Open Access
Learn as Individuals, Evolve as a Team: Multi-agent LLMs Adaptation in Embodied Environments
arXiv (Cornell University)·2025Open Access
Distributional Off-Policy Evaluation in Reinforcement Learning
Journal of the American Statistical Association·2025· 1 cited
Towards a Generalizable Bimanual Foundation Policy via Flow-based Video Prediction
arXiv (Cornell University)·2025Open Access
page 1 of 5Next →

Frequent Co-authors

Peng Liu(12), Lingxiao Wang(11), Zhaoran Wang(10), Xuelong Li(10), Haoran He(8), Zhen Wang(7), Xiu Li(7), Jianye Hao(6), Zhuoran Yang(6), Animesh Garg(5), Lei Han(5), Bin Zhao(5), Xudong Yu(5), Xianglong Tang(4), Zhen Wang(4), Jinyi Liu(3), Yingnan Zhao(3), Kang Xu(3), Weinan Zhang(3), Xiaoyu Wen(3)