Scholar
Qinwei Ma
Google Scholar ID: LwUaV3kAAAAJ
Tsinghua University
Machine Learning
Reinforcement Learning
Natural Language Processing
Follow
Google Scholar
↗
Citations & Impact
All-time
Citations
39
H-index
3
i10-index
2
Publications
5
Co-authors
0
Publications
9 items
SkillCycle: Co-Evolving Agent Policies and Skill Banks
2026
Cited
0
Timestep Weighting: A Hidden Key to Effective ELBO-Based Flow-Matching RL
2026
Cited
0
Position: The Inevitable End of One-Architecture-Fits-All-Domains in Time Series Forecasting
2026
Cited
0
ERA: Transforming VLMs into Embodied Agents via Embodied Prior Learning and Online Reinforcement Learning
2025
Cited
0
PRISM-Physics: Causal DAG-Based Process Evaluation for Physics Reasoning
2025
Cited
0
Explore-Execute Chain: Towards an Efficient Structured Reasoning Paradigm
2025
Cited
0
Gradient Imbalance in Direct Preference Optimization
2025
Cited
0
Explaining Context Length Scaling and Bounds for Language Models
2025
Cited
0
Load more
