Get started
Author

Hepeng Wang

Observed name: Wang, Hepeng
Observed institution: Harbin Institute of Technology
OpenAlex ID: A5122945934
MAESTRO: Meta-learning Adaptive Estimation of Scalarization Trade-offs for Reward Optimization
2026 · Association for Computational Linguistics 2026, Cai, Bibo, et al. · Underline Science Inc.
Consolidation or Adaptation? PRISM: Disentangling SFT and RL Data via Gradient Concentration
2026 · Association for Computational Linguistics 2026, Cai, Bibo, et al. · Underline Science Inc.
Consolidation or Adaptation? PRISM: Disentangling SFT and RL Data via Gradient Concentration
2026 · Zhao, Yang, Ouyang, Yangou, et al. · arXiv (Cornell University)
PDF
MAESTRO: Meta-learning Adaptive Estimation of Scalarization Trade-offs for Reward Optimization
2026 · Zhao, Yang, Wang, Hepeng, et al. · arXiv (Cornell University)
PDF
MAESTRO: Meta-learning Adaptive Estimation of Scalarization Trade-offs for Reward Optimization
2026 · Yang Zhao, Hepeng Wang, et al. · Proceedings of the conference - Association for Computational Linguistics. Meeting
PDF
Consolidation or Adaptation? PRISM: Disentangling SFT and RL Data via Gradient Concentration
2026 · Yang Zhao, Yangou Ouyang, et al. · Proceedings of the conference - Association for Computational Linguistics. Meeting
PDF
Works count: 6
Citation count:
H-index:
I10-index:
Year
Topic
Type