Author

Yecheng Wu

Observed name: Wu, Yecheng

Institution: Massachusetts Institute of Technology

Observed institution: Massachusetts Institute of Technology

OpenAlex ID: A5133672726

Weaken to Strengthen: Weakening-Induced On-Policy Self-Distillation for Large Reasoning Models

2026 · Wu, Yecheng, Han, Song, et al. · arXiv (Cornell University)

Lightning Weave: Improving the Accuracy-Efficiency Frontier of Reasoning Models through Capability Composition

2026 · Wu, Yecheng, Han, Song, et al. · arXiv (Cornell University)

Lightning OPD 2.0: Mitigating Style Bias in Cross-Teacher On-Policy Distillation for Large Reasoning Models

2026 · Wu, Yecheng, Han, Song, et al. · arXiv (Cornell University)

Hide to Guide: Learning via Semantic Masking

2026 · Liu, Ruitao, Hu, Qinghao, et al. · arXiv (Cornell University)

Lightning OPD: Efficient Post-Training for Large Reasoning Models with Offline On-Policy Distillation

2026 · Wu, Yecheng, Han, Song, et al. · arXiv (Cornell University)

Works count: 5

Citation count:

H-index:

I10-index: