DL
Deyuan Liu
cs.AIcs.CLcs.CVcs.LGAneuploidyChromosome Mappingcs.SEDNA Copy Number VariationsGene mutationGenetic Loci
On Valency
published · living versionsW_gvhmvt9r·v1 · currentpublished
Supervising the Visible State: Separating Representation from View Selection in Streaming Video
with Yihao Hu, Pan Wang, Yitong Lin, Zhihao Wen +6
1 version
W_5y4khhex·v1published
Preprints & journals
19 papers in the corpus · 2011–2026Robust non-uniform illumination correction for instrument images based on improved K-means clustering and an adaptive 2D Gamma function.42837554 · Hu, Yunlong, Liu, Deyuan, Chen, Jinghui et al.2026 · 0 citationsApplied optics. 2026;65(28):9729-9739
Vidu S2: Real-Time Interactive, Editable, and Spatial Video Generation2609.11638v1 · Jintao Zhang, Kai Jiang, Jintao Chen et al.2026 · 0 citationsarXivon Valency
FlowCPO: A Unified Divergence View of Preference Alignment for Flow Models2609.09905v1 · Yansen Han, Shengyi Liao, Peng Sun et al.2026 · 0 citationsarXiv
LLaDA-Image: Building Strong Image Generators with Fully Open Training Recipes2609.03796v1 · Chuyan Chen, Haoxing Chen, Kun Chen et al.2026 · 0 citationsarXiv
Three-Body Scattering for Generative Modeling2607.18198v1 · Peng Sun, Zhenglin Cheng, Deyuan Liu et al.2026 · 0 citationsarXiv
Self-Adversarial One Step Generation via Condition Shifting2604.12322v1 · Deyuan Liu, Peng Sun, Yansen Han et al.2026 · 0 citationsarXiv
Gradients Must Earn Their Influence: Unifying SFT with Generalized Entropic Objectives2602.11424v1 · Zecheng Wang, Deyuan Liu, Chunshan Li et al.2026 · 0 citationsarXiv
Efficient Generative Model Training via Embedded Representation Warmup2504.10188v3 · Deyuan Liu, Peng Sun, Xufeng Li et al.2025 · 0 citationsarXiv
Mitigating Gender Bias in Code Large Language Models via Model Editing2410.07820v1 · Zhanyue Qin, Haochuan Wang, Zecheng Wang et al.2024 · 0 citationsarXiv
Pruning via Merging: Compressing LLMs via Manifold Alignment Based Layer Merging2406.16330v2 · Deyuan Liu, Zhanyue Qin, Hairu Wang et al.2024 · 2 citationsarXiv
UNO Arena for Evaluating Sequential Decision-Making Capability of Large Language Models2406.16382v1 · Zhanyue Qin, Haochuan Wang, Deyuan Liu et al.2024 · 1 citationarXiv
Checkpoint Merging via Bayesian Optimization in LLM Pretraining2403.19390v2 · Deyuan Liu, Zecheng Wang, Bingning Wang et al.2024 · 1 citationarXiv
Adaptive Reflection Detection and Control Strategy of Pointer Meters Based on YOLOv5s.36904765 · Liu, Deyuan, Deng, Changgen, Zhang, Haodong et al.2023 · 8 citationsSensors (Basel, Switzerland). 2023;23(5)
A rapid improved multiplex ligation detection reaction method for the identification of gene mutations in hereditary hearing loss.30973918 · Liu, Yalan, Hu, Chang, Liu, Chang et al.2020 · 21 citationsPloS one. 2019;14(4):e0215212
A copy number variation genotyping method for aneuploidy detection in spontaneous abortion specimens.27977861 · Chen, Songchang, Liu, Deyuan, Zhang, Junyu et al.2017 · 22 citationsPrenatal diagnosis. 2017;37(2):176-183
SNPscan as a high-performance screening tool for mutation hotspots of hearing loss-associated genes.26004784 · Li, Haibo, Wang, Benjing, Liu, Deyuan et al.2016 · 15 citationsGenomics. 2015;106(2):83-7
A modified multiplex ligation-dependent probe amplification method for the detection of 22q11.2 copy number variations in patients with congenital heart disease.25952753 · Zhang, Xiaoqing, Xu, Yuejuan, Liu, Deyuan et al.2016 · 59 citationsBMC genomics. 2015;16:364
Mutation analysis of the NRXN1 gene in a Chinese autism cohort.22405623 · Liu, Yalan, Hu, Zhengmao, Xun, Guanglei et al.2012 · 41 citationsJournal of psychiatric research. 2012;46(5):630-4
A novel locus for congenital simple microphthalmia family mapping to 17p12-q12.21345985 · Hu, Zhengmao, Yu, Changhong, Li, Jingzhi et al.2011 · 25 citationsInvestigative ophthalmology & visual science. 2011;52(6):3425-9
Career total: 108 works. 19 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.