EZ
Erle Zhu
cs.AIcs.LGcs.CLcs.ROFinetuningNeural Networks, ComputerPretrainingReinforcement learningReinforcement, PsychologyUnsupervised Machine Learning
On Valency
published · living versionsW_2a6nnmah·v1 · currentpublished
AI Cosmos: An Agentic Infra for Situated Learning
with AI Cosmos Team, Jinfeng Zhou, Yuxuan Chen, Fangming Chang +30
1 version
W_9tfqgtmg·v1published
Preprints & journals
8 papers in the corpus · 2023–2026SkillEvolver: Skill Learning as a Meta-Skill2605.10500v1 · Genrui Zhang, Erle Zhu, Jinfeng Zhou et al.2026 · 0 citationsarXiv
GLM-5: from Vibe Coding to Agentic Engineering2602.15763v2 · GLM-5-Team: Aohan Zeng, Xin Lv, Zhenyu Hou et al.2026 · 6 citationsarXiv
Data-Efficient RLVR via Off-Policy Influence Guidance2510.26491v2 · Erle Zhu, Dazhi Jiang, Yuan Wang et al.2025 · 0 citationsarXiv
GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models2508.06471v1 · GLM-4.5 Team: Aohan Zeng, Xin Lv, Qinkai Zheng et al.2025 · 6 citationsarXiv
Corrigendum to "Self-Referencing agents for unsupervised reinforcement learning" [Neural Networks Volume 188, August 2025, 107448].40409013 · Zhao, Andrew, Zhu, Erle, Lu, Rui et al.2025 · 0 citationsNeural networks : the official journal of the International Neural Network Society. 2025;189:107632
Self-Referencing Agents for Unsupervised Reinforcement Learning.40198945 · Zhao, Andrew, Zhu, Erle, Lu, Rui et al.2025 · 4 citationsNeural networks : the official journal of the International Neural Network Society. 2025;188:107448
MAPS: Advancing Multi-Modal Reasoning in Expert-Level Physical Science2501.10768v2 · Erle Zhu, Yadi Liu, Zhe Zhang et al.2025 · 0 citationsProceedings of the 13th International Conference on Learning Representations (ICLR), 2025
Augmenting Unsupervised Reinforcement Learning with Self-Reference2311.09692v1 · Andrew Zhao, Erle Zhu, Rui Lu et al.2023 · 1 citationarXiv
Career total: 9 works. 8 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.