YM
Yixiu Mao
cs.LGcs.AIstat.MLcs.CL
On Valency
published · living versionsW_4z2ggxnu·v1 · currentpublished
Does Scaling Toward AGI Depend on What System-1 Lets System-2 Execute?
with Qi Wang, Yun Qu, Lizhou Cai, Heming Zou +8
1 version
Preprints & journals
12 papers in the corpus · 2020–2026Model predictive task sampling for efficient and robust adaptation.42265083 · Wang, Qi Cheems, Xiao, Zehao, Mao, Yixiu et al.2026 · 4 citationsNature communications. 2026;17(1)
RLVR without Ineffective Samples: Group Prioritized Off-Policy Optimization for LLM Reasoning2606.01281v1 · Yixiu Mao, Yun Qu, Qi Wang et al.2026 · 0 citationsarXiv
Dynamics-Predictive Sampling for Active RL Finetuning of Large Reasoning Models2603.10887v1 · Yixiu Mao, Yun Qu, Qi Wang et al.2026 · 0 citationsarXiv
Small Generalizable Prompt Predictive Models Can Steer Efficient RL Post-Training of Large Reasoning Models2602.01970v2 · Yun Qu, Qi Wang, Yixiu Mao et al.2026 · 0 citationsarXiv
Utility-Diversity Aware Online Batch Selection for LLM Supervised Fine-tuning2510.16882v4 · Heming Zou, Yixiu Mao, Yun Qu et al.2025 · 0 citationsarXiv
Can Prompt Difficulty be Online Predicted for Accelerating RL Finetuning of Reasoning Models?2507.04632v5 · Yun Qu, Qi Wang, Yixiu Mao et al.2025 · 0 citationsarXiv
Fast and Robust: Task Sampling with Posterior and Diversity Synergies for Adaptive Decision-Makers in Randomized Environments2504.19139v3 · Yun Qu, Qi Cheems Wang, Yixiu Mao et al.2025 · 0 citationsarXiv
Latent Reward: LLM-Empowered Credit Assignment in Episodic Reinforcement Learning2412.11120v2 · Yun Qu, Yuhang Jiang, Boyuan Wang et al.2024 · 6 citationsarXiv
Offline Reinforcement Learning with OOD State Correction and OOD Action Suppression2410.19400v4 · Yixiu Mao, Qi Wang, Chen Chen et al.2024 · 7 citationsarXiv
Robust Fast Adaptation from Adversarially Explicit Task Distribution Generation2407.19523v4 · Cheems Wang, Yiqin Lv, Yixiu Mao et al.2024 · 3 citationsarXiv
Supported Trust Region Optimization for Offline Reinforcement Learning2311.08935v1 · Yixiu Mao, Hongchang Zhang, Chen Chen et al.2023 · 6 citationsarXiv
A Hypergradient Approach to Robust Regression without Correspondence2012.00123v2 · Yujia Xie, Yixiu Mao, Simiao Zuo et al.2020 · 8 citationsarXiv
Career total: 12 works. 12 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.