SG
Shangding Gu
cs.AIcs.LGcs.ROcs.CLcs.MAcs.CRbi-direction informationcs.DCcs.SEcs.SI
On Valency
published · living versionsW_uvwr2g9k·v1 · currentpublished
Physical AI: Concepts, Techniques, and Challenges
with Weinan Zhang, Chunhua Shen, Tianfan Xue, Bin Zhao +47
1 version
Preprints & journals
42 papers in the corpus · 2020–2026Physical AI: Concepts, Techniques, and Challenges2610.27045v1 · Weinan Zhang, Chunhua Shen, Tianfan Xue et al.2026 · 0 citationsarXivon Valency
Who Improves the Robot? Toward Physical Recursive Self-Improvement2610.18842v1 · Hai Zhou, Fan Yang, Zeyi Chen et al.2026 · 0 citationsarXiv
Groundability, Not Scale Alone: When Weak Reviewers Can Audit Strong Coding Agents2610.01023v1 · Junyu Guo, Shangding Gu, Ming Jin et al.2026 · 0 citationsarXiv
TRACE: Governing Memory Validity in Evolving Multi-Agent Systems2609.33517v1 · Wenjun Xiong, Shengtao Zhang, Shangding Gu et al.2026 · 0 citationsarXiv
HarnessPAI: An Evolving Harness for Physical AI2609.29166v2 · Xin Wang, Wenhao Wu, Menghao Zhang et al.2026 · 0 citationsarXiv
WolfSociety: Understanding Collective Risk from Harmful-Agent Scaling in Financial Agent Societies2609.05591v1 · Lejun Zhang, Sarah Lu-Liang, Xin Jiang et al.2026 · 0 citationsarXiv
MAPLE-Guard: Memory-Aware Link Enforcement Against Memory-Link Poisoning in Multi-Agent Systems2608.00426v2 · Wenjun Xiong, Yijin Zhou, Jiaqian Wang et al.2026 · 0 citationsarXiv
Understanding and Evaluating Claw-like Agent Security Through a Computer-Systems Lens2606.30755v1 · Peizhi Niu, Wenjie Qu, Shangding Gu et al.2026 · 0 citationsarXiv
From Model Scaling to System Scaling: Scaling the Harness in Agentic AI2605.26112v1 · Shangding Gu2026 · 1 citationarXiv
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents2605.17830v1 · Ahmad Al-Tawaha, Shangding Gu, Peizhi Niu et al.2026 · 0 citationsarXiv
Steering semi-flexible molecular diffusion model for structure-based drug design with reinforcement learning.41984966 · Zhang, Xudong, Qu, Sanqing, Lu, Fan et al.2026 · 1 citationScience advances. 2026;12(16):eady9955
LLMs Should Express Uncertainty Explicitly2604.05306v2 · Junyu Guo, Shangding Gu, Ming Jin et al.2026 · 0 citationsarXiv
Long Context, Less Focus: A Scaling Gap in LLMs Revealed through Privacy and Personalization2602.15028v1 · Shangding Gu2026 · 0 citationsarXiv
AgenticPay: A Multi-Agent LLM Negotiation System for Buyer-Seller Transactions2602.06008v1 · Xianyang Liu, Shangding Gu, Dawn Song2026 · 1 citationarXiv
Understanding Agent Scaling in LLM-Based Multi-Agent Systems via Diversity2602.03794v1 · Yingxuan Yang, Chengrui Qu, Muning Wen et al.2026 · 1 citationarXiv
AccidentBench: Benchmarking Multimodal Understanding and Reasoning in Vehicle Accidents and Beyond2509.26636v1 · Shangding Gu, Xiaohan Wang, Donghao Ying et al.2025 · 0 citationsarXiv
StyleBench: Evaluating thinking styles in Large Language Models2509.20868v2 · Junyu Guo, Shangding Gu, Ming Jin et al.2025 · 0 citationsarXiv
Agentic Web: Weaving the Next Web with AI Agents2507.21206v1 · Yingxuan Yang, Mulei Ma, Yuxuan Huang et al.2025 · 2 citationsarXiv
Data Uniformity Improves Training Efficiency and More, with a Convergence Framework Beyond the NTK Regime2506.24120v2 · Yuqing Wang, Shangding Gu2025 · 0 citationsarXiv
RLBenchNet: The Right Network for the Right Reinforcement Learning Task2505.15040v1 · Ivan Smirnov, Shangding Gu2025 · 0 citationsarXiv
Few-Shot Test-Time Optimization Without Retraining for Semiconductor Recipe Generation and Beyond2505.16060v1 · Shangding Gu, Donghao Ying, Ming Jin et al.2025 · 0 citationsarXiv
Safe and Balanced: A Framework for Constrained Multi-Objective Reinforcement Learning.40031004 · Gu, Shangding, Sel, Bilgehan, Ding, Yuhao et al.2025 · 16 citationsIEEE transactions on pattern analysis and machine intelligence. 2025;47(5):3322-3331
MMLU-ProX: A Multilingual Benchmark for Advanced Large Language Model Evaluation2503.10497v2 · Weihao Xuan, Rui Yang, Heli Qi et al.2025 · 10 citationsarXiv
Safe Continual Domain Adaptation after Sim2Real Transfer of Reinforcement Learning Policies in Robotics2503.10949v1 · Josip Josifovski, Shangding Gu, Mohammadhossein Malmir et al.2025 · 0 citationsarXiv
Robust Gymnasium: A Unified Modular Benchmark for Robust Reinforcement Learning2502.19652v1 · Shangding Gu, Laixi Shi, Muning Wen et al.2025 · 1 citationarXiv
Don't Trade Off Safety: Diffusion Regularization for Constrained Offline RL2502.12391v2 · Junyu Guo, Zhi Zheng, Donghao Ying et al.2025 · 0 citationsarXiv
A Review of Safe Reinforcement Learning: Methods, Theories, and Applications.39255180 · Gu, Shangding, Yang, Long, Du, Yali et al.2024 · 326 citationsIEEE transactions on pattern analysis and machine intelligence. 2024;46(12):11216-11235
Multi-Agent Reinforcement Learning for Autonomous Driving: A Survey2408.09675v1 · Ruiqi Zhang, Jing Hou, Florian Walter et al.2024 · 4 citationsarXiv
Enhancing Efficiency of Safe Reinforcement Learning via Sample Manipulation2405.20860v1 · Shangding Gu, Laixi Shi, Yuhao Ding et al.2024 · 0 citationsarXiv
Safe Multi-Agent Reinforcement Learning with Bilevel Optimization in Autonomous Driving2405.18209v1 · Zhi Zheng, Shangding Gu2024 · 15 citationsarXiv
Balance Reward and Safety Optimization for Safe Reinforcement Learning: A Perspective of Gradient Manipulation2405.01677v3 · Shangding Gu, Bilgehan Sel, Yuhao Ding et al.2024 · 11 citationsarXiv
Hybrid Residual Multiexpert Reinforcement Learning for Spatial Scheduling of High-Density Parking Lots.37871089 · Hou, Jing, Chen, Guang, Li, Zhijun et al.2024 · 19 citationsIEEE transactions on cybernetics. 2024;54(5):2771-2783
TeaMs-RL: Teaching LLMs to Generate Better Instruction Datasets via Reinforcement Learning2403.08694v4 · Shangding Gu, Alois Knoll, Ming Jin2024 · 1 citationarXiv
Mutual Enhancement of Large Language and Reinforcement Learning Models through Bi-Directional Feedback Mechanisms: A Planning Case Study2401.06603v2 · Shangding Gu2024 · 1 citationarXiv
Spreeze: High-Throughput Parallel Reinforcement Learning Framework2312.06126v1 · Jing Hou, Guang Chen, Ruiqi Zhang et al.2023 · 3 citationsarXiv
A human-centered safe robot reinforcement learning framework with interactive behaviors.38023448 · Gu, Shangding, Kshirsagar, Alap, Du, Yali et al.2024 · 21 citationsFrontiers in neurorobotics. 2023;17:1280341
SCPO: Safe Reinforcement Learning with Safety Critic Policy Optimization2311.00880v1 · Jaafar Mhamed, Shangding Gu2023 · 0 citationsarXiv
A Review of Safe Reinforcement Learning: Methods, Theory and Applications2205.10330v5 · Shangding Gu, Long Yang, Yali Du et al.2022 · 112 citationsarXiv
A Circle Grid-based Approach for Obstacle Avoidance Motion Planning of Unmanned Surface Vehicles2202.04494v1 · Man Zhu, Changshi Xiao, Shangding Gu et al.2022 · 10 citationsarXiv
Multi-Agent Constrained Policy Optimisation2110.02793v2 · Shangding Gu, Jakub Grudzien Kuba, Munning Wen et al.2021 · 22 citationsarXiv
Settling the Variance of Multi-Agent Policy Gradients2108.08612v3 · Jakub Grudzien Kuba, Muning Wen, Yaodong Yang et al.2021 · 45 citationsarXiv
Unmanned Surface Vehicle Path Planning from the Perspective of Multi-Modality Constraints: A Comprehensive Analysis2007.01691v3 · Chunhui Zhou, Shangding Gu, Yuanqiao Wen et al.2020 · 0 citationsOcean Engineering,2020
Career total: 63 works. 42 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.