Tianyi Wang

Tianyi Wang

Undergraduate student in Computer Science and Technology at BUPT, focused on post-training RL and optimizer implementation.

Posts by Collection

portfolio

publications

Anchored Policy Optimization: Mitigating Exploration Collapse via Support-Constrained Rectification

Published in ICML 2026, 2026

Introduces support-constrained rectification for RLVR to mitigate exploration collapse and improve both Pass@1 and response diversity.

arXiv | GitHub

Recommended citation: @misc{wang2026anchoredpolicyoptimizationmitigating, title={Anchored Policy Optimization: Mitigating Exploration Collapse Via Support-Constrained Rectification}, author={Tianyi Wang and Long Li and Hongcan Guo and Yibiao Chen and Yixia Li and Yong Wang and Yun Chen and Guanhua Chen}, year={2026}, eprint={2602.05717}, archivePrefix={arXiv}, primaryClass={cs.AI}, url={https://arxiv.org/abs/2602.05717}, }
Download Paper

DyJR: Preserving Diversity in Reinforcement Learning with Verifiable Rewards via Dynamic Jensen-Shannon Replay

Published in Under Review, 2026

Introduces Dynamic Jensen-Shannon Replay to preserve diversity in reinforcement learning through verifiable rewards mechanism.

arXiv

Recommended citation: @misc{li2026dyjrpreservingdiversityreinforcement, title={DyJR: Preserving Diversity in Reinforcement Learning with Verifiable Rewards via Dynamic Jensen-Shannon Replay}, author={Long Li and Zhijian Zhou and Tianyi Wang and Weidi Xu and Zuming Huang and Wei Chu and Zhe Wang and Shirui Pan and Chao Qu and Yuan Qi}, year={2026}, eprint={2603.16157}, archivePrefix={arXiv}, primaryClass={cs.LG}, url={https://arxiv.org/abs/2603.16157}, }

SPPO: Sequence-Level PPO for Long-Horizon Reasoning

Published in ACL 2026 Oral, 2026

Reformulates long-horizon reasoning as a sequence-level contextual bandit with a decoupled scalar value function to improve stability and reduce memory cost.

arXiv | GitHub

Recommended citation: @misc{wang2026spposequencelevelppolonghorizon, title={SPPO: Sequence-Level PPO for Long-Horizon Reasoning Tasks}, author={Tianyi Wang and Yixia Li and Long Li and Yibiao Chen and Shaohan Huang and Yun Chen and Peng Li and Yang Liu and Guanhua Chen}, year={2026}, eprint={2604.08865}, archivePrefix={arXiv}, primaryClass={cs.AI}, url={https://arxiv.org/abs/2604.08865}, }
Download Paper

talks

teaching

Teaching experience 1

Undergraduate course, University 1, Department, 2014

This is a description of a teaching experience. You can use markdown like any other post.

Teaching experience 2

Workshop, University 1, Department, 2015

This is a description of a teaching experience. You can use markdown like any other post.