Publications

Selected recent publications and preprints by Prof. Shangding Gu and lab members.

Selected Recent Publications

ICLR 2025

Robust Gymnasium: A Unified Modular Benchmark for Robust Reinforcement Learning.

Shangding Gu, Laixi Shi, Muning Wen, Ming Jin, Eric Mazumdar, Yuejie Chi, Adam Wierman, Costas Spanos.

International Conference on Learning Representations.

[Paper], [Code]

IEEE TPAMI

Safe and Balanced: A Framework for Constrained Multi-Objective Reinforcement Learning.

Shangding Gu, Bilgehan Sel, Yuhao Ding, Lu Wang, Qingwei Lin, Alois Knoll, Ming Jin.

IEEE Transactions on Pattern Analysis and Machine Intelligence.

[Paper], [Code]

TMLR

TeaMs-RL: Teaching LLMs to Generate Better Instruction Datasets via Reinforcement Learning.

Shangding Gu, Alois Knoll, Ming Jin.

Transactions on Machine Learning Research.

[Paper], [Code]

NeurIPS 2024

Enhancing Efficiency of Safe Reinforcement Learning via Sample Manipulation.

Shangding Gu, Laixi Shi, Yuhao Ding, Alois Knoll, Costas Spanos, Adam Wierman, Ming Jin.

Advances in Neural Information Processing Systems.

[Paper], [Code]

IEEE TPAMI

A Review of Safe Reinforcement Learning: Methods, Theory and Applications.

Shangding Gu, Long Yang, Yali Du, Guang Chen, Florian Walter, Jun Wang, Alois Knoll.

IEEE Transactions on Pattern Analysis and Machine Intelligence.

[Paper], [Code], [机器之心]

AAAI 2024

Balancing Reward and Safety Optimization for Safe Reinforcement Learning: A Perspective of Gradient Manipulation.

Shangding Gu, Bilgehan Sel, Yuhao Ding, Lu Wang, Qingwei Lin, Ming Jin, Alois Knoll.

Association for the Advancement of Artificial Intelligence.

[Paper], [Code]

IEEE TII

Safe Multiagent Learning With Soft-Constrained Policy Optimization in Real Robot Control.

Shangding Gu, Dianye Huang, Muning Wen, Guang Chen, Alois Knoll.

IEEE Transactions on Industrial Informatics.

[Paper], [Code]

IEEE TASE

ROSCOM: Robust Safe Reinforcement Learning on Stochastic Constraint Manifolds.

Shangding Gu, Puze Liu, Alap Kshirsagar, Guang Chen, Jan Peters, Alois Knoll.

IEEE Transactions on Automation Science and Engineering.

[Paper], [Code]

AIJ

Safe Multi-Agent Reinforcement Learning for Multi-Robot Control.

Shangding Gu, Jakub Grudzien Kuba, Yuanpei Chen, Yali Du, Long Yang, Alois Knoll, Yaodong Yang.

The Journal of Artificial Intelligence.

[Paper], [Code]

IEEE TAI

Safe Multi-Agent Reinforcement Learning with Bilevel Optimization in Autonomous Driving.

Zheng Zhi, Shangding Gu.

IEEE Transactions on Artificial Intelligence.

[Paper], [Code]

Selected Recent Preprints

From Model Scaling to System Scaling: Scaling the Harness in Agentic AI.

Shangding Gu

[Paper], [Code], [DAIR.AI]
Long Context, Less Focus: A Scaling Gap in LLMs Revealed through Privacy and Personalization.

Shangding Gu

[Paper], [Code]
Understanding Agent Scaling in LLM-Based Multi-Agent Systems via Diversity.

Yingxuan Yang, Chengrui Qu, Muning Wen, Laixi Shi, Ying Wen, Weinan Zhang, Adam Wierman, Shangding Gu

[Paper], [Code], [机器之心]
Agentic web: Weaving the next web with AI agents.

Yingxuan Yang, Mulei Ma, Yuxuan Huang, Huacan Chai, Chenyu Gong, Haoran Geng, Yuanjian Zhou, Ying Wen, Meng Fang, Muhao Chen, Shangding Gu, Ming Jin, Costas Spanos, Yang Yang, Pieter Abbeel, Dawn Song, Weinan Zhang, Jun Wang

[Paper], [Code], [IEEE Spectrum], [The Economist], [机器之心]
AccidentBench: Benchmarking Multimodal Understanding and Reasoning in Vehicle Accidents and Beyond.

Shangding Gu, Xiaohan Wang, Donghao Ying, Haoyu Zhao, Runing Yang, Boyi Li, Ming Jin, Marco Pavone, Serena Yeung-Levy, Jun Wang, Dawn Song, Costas Spanos

[Paper], [Code]
Data Uniformity Improves Training Efficiency and More, with a Convergence Framework Beyond the NTK Regime.

Yuqing Wang, Shangding Gu

[Paper], [Code]
RLBenchNet: The Right Network for the Right Reinforcement Learning Task.

Ivan Smirnov, Shangding Gu

[Paper], [Code]

For more details, please see Google Scholar.