JQ
Junbin Qiu
cond-mat.stat-mechcs.CLcs.LGq-bio.NCcond-mat.dis-nncs.NELanguageModels, NeurologicalNeural Networks, Computerstat.ML
On Valency
published · living versionsW_x2xfah7a·v1 · currentpublished
The Cost of Mismatch: Noise Amplification in Zeroth-Order Reinforcement Learning
with Lianmin Chen, Chenxing Wei, Yao Shu, Kun He
1 version
Preprints & journals
5 papers in the corpus · 2021–2026Predicting Quantization Price for Selecting PTQ Configurations Before Deployment2609.28270v1 · Junbin Qiu, Jian Mu, Weitong Zhang et al.2026 · 0 citationsarXiv
Revisiting Zeroth-Order Hessian Approximation: A Single-Step Policy Optimization Lens2605.30960v1 · Junbin Qiu, Zhaowei Hong, Renzhe Xu et al.2026 · 0 citationsarXiv
Meta predictive learning model of languages in neural circuits.38755909 · Li, Chan, Qiu, Junbin, Huang, Haiping2024 · 1 citationPhysical review. E. 2024;109(4-1):044309
An optimization-based equilibrium measure describes non-equilibrium steady state dynamics: application to edge of chaos2401.10009v2 · Junbin Qiu, Haiping Huang2024 · 9 citations2025 Commun. Theor. Phys. 77 035601
Equivalence between algorithmic instability and transition to replica symmetry breaking in perceptron learning systems2111.13302v2 · Yang Zhao, Junbin Qiu, Mingshan Xie et al.2021 · 4 citationsPhys. Rev. Research 4, 023023 (2022)
Career total: 9 works. 5 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.