Get started
Author

Yuanda Xu

Observed name: Xu, Yuanda
OpenAlex ID: A5126942858
Smaller Models, Better Rejects: Preference Distillation Scaling
2026 · Cai, Rui, Zhu, Wenhui, et al. · arXiv (Cornell University)
PDF
TREK: Distill to Explore, Reinforce to Refine
2026 · Xu, Yuanda, Zhou, Zhengze, et al. · arXiv (Cornell University)
PDF
TIP: Token Importance in On-Policy Distillation
2026 · Xu, Yuanda, Sang, Hejian, et al. · arXiv (Cornell University)
PDF
Robust Batch-Level Query Routing for Large Language Models under Cost and Capacity Constraints
2026 · Markovic-Voronov, Jelena, Behdin, Kayhan, et al. · arXiv (Cornell University)
PDF
PACED: Distillation and On-Policy Self-Distillation at the Frontier of Student Competence
2026 · Xu, Yuanda, Sang, Hejian, et al. · arXiv (Cornell University)
PDF
CRISP: Compressed Reasoning via Iterative Self-Policy Distillation
2026 · Sang, Hejian, Xu, Yuanda, et al. · arXiv (Cornell University)
PDF
Overconfident Errors Need Stronger Correction: Asymmetric Confidence Penalties for Reinforcement Learning
2026 · Xu, Yuanda, Sang, Hejian, et al. · arXiv (Cornell University)
PDF
Not all tokens are needed(NAT): token efficient reinforcement learning
2026 · Sang, Hejian, Xu, Yuanda, et al. · arXiv (Cornell University)
PDF
Beyond GRPO and On-Policy Distillation: An Empirical Sparse-to-Dense Reward Principle for Language-Model Post-Training
2026 · Yuanda Xu, Hejian Sang, et al. · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)
PDF
Works count: 9
Citation count:
H-index:
I10-index:
Year
Topic
Type