PW
Pengcheng Wang
cs.LGcs.CLcs.AIcs.ROcs.CVeess.ASmath.DGstat.MLCallithrixCerebral Cortex
On Valency
published · living versionsW_tb85nsch·v1 · currentpublished
Self-Labeled Preference Transfer for Steerable Robot Manipulation
with Kaiwen Hong, Shaoting Peng, Xiangyu Zeng, Boyuan Tian +4
1 version
Preprints & journals
32 papers in the corpus · 2007–2026Agentic-DuplexGen: Decoupling Content, Timing, and Acoustics for Synthetic Dialogue Speech2608.16053v2 · Pengcheng Wang, Sheng Li, Jiyi Li et al.2026 · 0 citationsarXiv
Human-Guided Causal Knowledge Injection for Virtual Cells2608.08430v1 · Pengcheng Wang, Changjian Chen, Zhuo Tang et al.2026 · 0 citationsarXiv
Pin Once, Swap Light: Subspace-Aligned Centroid-Residual Training for Efficient Ultra-LoRA Serving2608.03579v1 · Xiang Li, Pengcheng Wang, Huazheng Wang et al.2026 · 0 citationsarXiv
CLIFT: Turning Gemini Robotics On-Device into Humanoid Specialists via Non-Invasive Closed-Loop Iterative Fine-Tuning2607.29172v1 · Yuxin Chen, Hari Srikanth, Nathan Jew et al.2026 · 0 citationsarXiv
Diagnosing Compositional Generalization in Sequential Robot Tasks2607.29687v2 · Yixiao Wang, Cheng-En Wu, Lingfeng Sun et al.2026 · 0 citationsarXiv
Look Less, Think Faster: Joint Token-Compute Adaptation for Multimodal LLMs2607.20357v1 · Pengcheng Wang, Zhiquan Wang, Jayoung Lee et al.2026 · 0 citationsarXiv
CORA: Per-Slice Coherent Orthogonal Rotation for SVD-based Low-Rank Adaptation2607.02576v1 · Pengcheng Wang, Ziran Liu, Wei Wang et al.2026 · 0 citationsarXiv
REAR: Test-time Preference Realignment through Reward Decomposition2606.30339v1 · Fuxiang Zhang, Pengcheng Wang, Chenran Li et al.2026 · 0 citationsarXiv
Diffusion-Proof: Recipe for Formal Theorem Proving Beyond Auto-Regressive Generation2606.19315v1 · Ruida Wang, Rui Pan, Pengcheng Wang et al.2026 · 0 citationsarXiv
Lean4Agent: Formal Modeling and Verification for Agent Workflow and Trajectory2606.06523v3 · Ruida Wang, Jerry Huang, Pengcheng Wang et al.2026 · 0 citationsarXiv
Geometric and Spectral Alignment for Deep Neural Network I2605.02108v1 · Ziran Liu, Wei Wang, Jinhao Wang et al.2026 · 0 citationsarXiv
Geometric and Spectral Alignment for Deep Neural Network II2605.02111v1 · Ziran Liu, Wei Wang, Jinhao Wang et al.2026 · 0 citationsarXiv
DiscreteRTC: Discrete Diffusion Policies are Natural Asynchronous Executors2604.25050v3 · Pengcheng Wang, Kaiwen Hong, Chensheng Peng et al.2026 · 0 citationsarXiv
AgentSPEX: An Agent SPecification and EXecution Language2604.13346v1 · Pengcheng Wang, Jerry Huang, Jiarui Yao et al.2026 · 0 citationsarXiv
Mean Flow Policy with Instantaneous Velocity Constraint for One-step Action Generation2602.13810v2 · Guojian Zhan, Letian Tao, Pengcheng Wang et al.2026 · 0 citationsarXiv
DADP: Domain Adaptive Diffusion Policy2602.04037v3 · Pengcheng Wang, Qinghang Liu, Haotian Lin et al.2026 · 0 citationsarXiv
Mind Your Entropy: From Maximum Entropy to Trajectory Entropy-Constrained RL2511.11592v1 · Guojian Zhan, Likun Wang, Pengcheng Wang et al.2025 · 0 citationsarXiv
RAG-Boost: Retrieval-Augmented Generation Enhanced LLM-based Speech Recognition2508.14048v1 · Pengcheng Wang, Sheng Li, Takahiro Shinozaki2025 · 0 citationsarXiv
Cat-Eye Inspired Active-Passive-Composite Aperture-Shared Sub-Terahertz Meta-Imager for Non-Interactive Concealed Object Detection2504.01473v1 · Mingshuang Hu, Yuzhong Wang, Zhe Jiang et al.2025 · 4 citationsarXiv
Residual Policy Gradient: A Reward View of KL-regularized Objective2503.11019v2 · Pengcheng Wang, Xinghao Zhu, Yuxin Chen et al.2025 · 0 citationsarXiv
TD-M(PC): Improving Temporal Difference MPC Through Policy Constraint2502.03550v1 · Haotian Lin, Pengcheng Wang, Jeff Schneider et al.2025 · 0 citationsarXiv
Decoding cortical folding patterns in marmosets using machine learning and large language model.39864569 · Wu, Yue, Gao, Xuesong, Liu, Zhengliang et al.2025 · 0 citationsNeuroImage. 2025;308:121031
Entropy-Regularized Process Reward Model2412.11006v2 · Hanning Zhang, Pengcheng Wang, Shizhe Diao et al.2024 · 1 citationarXiv
Residual-MPPI: Online Policy Customization for Continuous Control2407.00898v5 · Pengcheng Wang, Chenran Li, Catherine Weaver et al.2024 · 0 citationsarXiv
Active Prompting with Chain-of-Thought for Large Language Models2302.12246v5 · Shizhe Diao, Pengcheng Wang, Yong Lin et al.2023 · 92 citationsarXiv
Temperature Self-Calibration of Always-On, Field-Deployed Ion-Selective Electrodes Based on Differential Voltage Measurement.36074898 · Saha, Ajanta, Yermembetova, Aiganym, Mi, Ye et al.2022 · 29 citationsACS sensors. 2022;7(9):2661-2670
JANUS: Benchmarking Commercial and Open-Source Cloud and Edge Platforms for Object and Anomaly Detection Workloads2012.04880v1 · Karthick Shankar, Pengcheng Wang, Ran Xu et al.2020 · 17 citations"JANUS: Benchmarking Commercial and Open-Source Cloud and Edge Platforms for Object and Anomaly Detection Workloads," IEEE International Conference on Cloud Computing (IEEE Cloud), pp. 1--10, Oct 18-24, 2020
GLGE: A New General Language Generation Evaluation Benchmark2011.11928v3 · Dayiheng Liu, Yu Yan, Yeyun Gong et al.2020 · 47 citationsarXiv
ApproxDet: Content and Contention-Aware Approximate Object Detection for Mobiles2010.10754v1 · Ran Xu, Chen-lin Zhang, Pengcheng Wang et al.2020 · 6 citationsarXiv
MASSD: Multi-scale attention single shot detector for surgical instruments.32658787 · Yu, Lingtao, Wang, Pengcheng, Yan, Yusheng et al.2021 · 9 citationsComputers in biology and medicine. 2020;123:103867
ApproxNet: Content and Contention-Aware Video Analytics System for Embedded Clients1909.02068v5 · Ran Xu, Rakesh Kumar, Pengcheng Wang et al.2019 · 11 citationsarXiv
[Construction and research for a web-based economic PACS].18161371 · Wang, Peng-Cheng, Liu, Wei, Zhai, Xiao-Juan2012 · 1 citationZhongguo yi liao qi xie za zhi = Chinese journal of medical instrumentation. 2007;31(5):338-40
Career total: 81 works. 32 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.