百晓学者学者目录

董怡

副教授、副研究员、助理教授、助理研究员、博导、教授、研究员、硕导、讲师，同济大学

精选作品

期刊论文

2026

Spatial-temporal motion planning for multiple nonholonomic robots with safety constraints

Tao Zhang, Yi Dong, Xiaoming Hu

International Journal Of Systems Science，Vol. 570, No. 2

DOI

2026

输入饱和约束下多四旋翼无人机有限时间容错编队控制研究

王晴，程俊哲，胡宏剑，辛斌，董怡

《中国科学:技术科学》

2026

DoS攻击下具有状态约束的非线性系统网络安全控制

宋若琳，洪奕光，董怡，辛斌，王晴，陈曦

《中国科学:信息科学》

2026

PhyCritic: Multimodal Critic Models for Physical AI

Tianyi Xiong, Shi-Hao Wang, Guilin Liu, Yi Dong, Ming Li, Heng Huang, Jan Kautz, Zhi-Ding Yu

arXiv.org

DOI

2026

Hierarchical Advantage Weighting for Online RL Fine-Tuning of VLAs from Sparse Episode Outcomes

Tongyan Fang, Si-Yuan Huang, N. Fang, Ganlong Zhao, Zhong-Jin Luo, Jian-Bo Liu, Xiao-Gang Wang, Yi Dong, Hong-Sheng Li

arXiv.org

DOI

2026

Golden Goose: A Simple Trick to Synthesize Unlimited RLVR Tasks from Unverifiable Internet Text

Ximing Lu, David Acuna, Jaehun Jung, Jian Hu, Di Zhang, Shi-Zhe Diao, Yun-Heng Zou, Shao-Kun Zhang, Brandon Cui, Ming-Jie Liu, Hyunwoo Kim, Prithviraj Ammanabrolu, Jan Kautz, Yi Dong, Yejin Choi

arXiv.org

DOI

2026

Molt: A Scalable PyTorch-Native Training Framework for Agentic Reinforcement Learning

Jian Hu, Hui-Ying Li, Hao Zhang, Bin-Feng Xu, Yi-Fan Zhang, Shao-Kun Zhang, Hemil Desai, Michael Demoret, Pavlo Molchanov, Jan Kautz, Yi Dong

arXiv.org

DOI

2026

Homotopy-guided parallel planning with dynamic control barrier functions for safety-critical navigation in dynamic environments

Tao Zhang, Yi Dong, Guangdeng Zong

Robotics and Autonomous Systems

DOI

2026

Data-driven Output Regulation of Constrained Systems with Unmeasurable Disturbance

ChaoYu Xia, Yi Dong, Zhiyong Chen, Jie Chen

IEEE Transactions on Automatic Control

DOI

2026

Resilient control of constrained nonlinear uncertain systems with impulsive FDI attacks

Meng Yao, Yi Dong

Asian Journal of Control

DOI

2026

Output Regulation of Constrained Linear Systems by Data-Driven Output Feedback Control

ChaoYu Xia, Yi Dong, C Z Wang, Shengyuan Xu

Lecture notes in electrical engineering

DOI

2026

Resilient and Safety Control of Uncertain Nonlinear Systems: Hybrid Governor Function

Meng Yao, Zhuang Ma, Litao He, Renjie Yan, Yi Dong, Yiguang Hong

Lecture notes in electrical engineering

DOI

2026

Data-Driven Cooperative Output Regulation of Singular Linear Multi-Agent Systems

Jialei Cai, Chi Zhou, Dong Liang, Yi Dong, Chaoli Wang, Yuanyingyi Sun

International Conference on Control and Automation

DOI

2025

ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language Models

Ming-Jie Liu, Shi-Zhe Diao, Ximing Lu, Jian Hu, Xin Dong, Yejin Choi, Jan Kautz, Yi Dong

Neural Information Processing Systems

DOI

2025

ToolOrchestra: Elevating Intelligence via Efficient Model and Tool Orchestration

Hongjin Su, Shi-Zhe Diao, Ximing Lu, Ming-Jie Liu, Jia-Cheng Xu, Xin Dong, Yong-Gan Fu, Peter Belcák, Han-Rong Ye, Hongxu Yin, Yi Dong, E. Bakhturina, Tao Yu, Yejin Choi, Jan Kautz, Pavlo Molchanov

arXiv.org

DOI

2025

Nemotron-Research-Tool-N1: Exploring Tool-Using Language Models with Reinforced Reasoning

Shao-Kun Zhang, Yi Dong, Jieyu Zhang, Jan Kautz, Bryan Catanzaro, A. Tao, Qing-Yun Wu, Zhi-Ding Yu, Guilin Liu

arXiv.org

DOI

2025

ProfBench: Multi-Domain Rubrics requiring Professional Knowledge to Answer and Judge

Zhilin Wang, Jaehun Jung, Ximing Lu, Shi-Zhe Diao, Ellie Evans, Jia-Qi Zeng, Pavlo Molchanov, Yejin Choi, Jan Kautz, Yi Dong

arXiv.org

DOI

2025

BroRL: Scaling Reinforcement Learning via Broadened Exploration

Jian Hu, Ming-Jie Liu, Ximing Lu, Fang Wu, Z. Harchaoui, Shi-Zhe Diao, Yejin Choi, Pavlo Molchanov, J. Yang, Jan Kautz, Yi Dong

arXiv.org

DOI

2025

Scaling Up RL: Unlocking Diverse Reasoning in LLMs via Prolonged Training

Ming-Jie Liu, Shi-Zhe Diao, Jian Hu, Ximing Lu, Xin Dong, Hao Zhang, A. Bukharin, Shao-Kun Zhang, Jia-Qi Zeng, Makesh Narsimhan Sreedhar, Gerald Shen, David Mosallanezhad, Di Zhang, Jonas Yang, J. Yang, Oleksii Kuchaiev, Guilin Liu, Zhi-Ding Yu, Pavlo Molchanov, Ye-Jin Choi, Jan Kautz, Yi Dong

arXiv.org

DOI

2025

RLBFF: Binary Flexible Feedback to bridge between Human Feedback & Verifiable Rewards

Zhilin Wang, Jia-Qi Zeng, Olivier Delalleau, Ellie Evans, Daniel Egert, Hoo-Chang Shin, Felipe Soares, Yi Dong, Oleksii Kuchaiev

arXiv.org

DOI

2025

Reward-aware Preference Optimization: A Unified Mathematical Framework for Model Alignment

Shengyang Sun, Yian Zhang, A. Bukharin, David Mosallanezhad, Jia-Qi Zeng, Soumye Singhal, Gerald Shen, Adithya Renduchintala, T. Konuk, Yi Dong, Zhilin Wang, Dmitry Chichkov, Olivier Delalleau, Oleksii Kuchaiev

arXiv.org

DOI

2025

HelpSteer3: Human-Annotated Feedback and Edit Data to Empower Inference-Time Scaling in Open-Ended General-Domain Tasks

Zhilin Wang, Jia-Qi Zeng, Olivier Delalleau, Daniel Egert, Ellie Evans, Hoo-Chang Shin, Felipe Soares, Yi Dong, Oleksii Kuchaiev

Annual Meeting of the Association for Computational Linguistics

DOI

2025

HelpSteer3-Preference: Open Human-Annotated Preference Data across Diverse Tasks and Languages

Zhilin Wang, Jia-Qi Zeng, Olivier Delalleau, Hoo-Chang Shin, Felipe Soares, A. Bukharin, Ellie Evans, Yi Dong, Oleksii Kuchaiev

Neural Information Processing Systems

DOI

2025

MM-Food-100K: A 100,000-Sample Multimodal Food Intelligence Dataset with Verifiable Provenance

Yi Dong, Yusuke Muraoka, Scott Shi, Yi Zhang

arXiv.org

DOI

2025

Two Intermediate Translations Are Better Than One: Fine-tuning LLMs for Document-level Translation Refinement

Yi Dong, Xinglin Lyu, Junhui Li, Dai-Meng Wei, Min Zhang, Shimin Tao, Hao Yang

Annual Meeting of the Association for Computational Linguistics

DOI

2025

REF-VLM: Triplet-Based Referring Paradigm for Unified Visual Decoding

Yan Tai, Lu-Hao Zhu, Zhiqiang Chen, Ynan Ding, Yi Dong, Xiao-Hong Liu, Guodong Guo

arXiv.org

DOI

2025

Receding‐Horizon Control for a Networked Nonlinear System Against Hybrid Attacks on Sensor and Actuator Channels

Xiran Cui, Yi Dong, Yiguang Hong

International Journal of Robust and Nonlinear Control

DOI

2025

Distributed safety-critical control of nonlinear multi-agent systems

Xiaoyu Wang, Yi Dong, Yiguang Hong, Karl Henrik Johansson

Automatica

DOI

2025

Model-Free Output Regulation of Networked Systems Under Unknown Hybrid Attacks

Xiran Cui, Zheng‐Guang Wu, Yi Dong, Zhong‐Ping Jiang

IEEE Transactions on Cybernetics

DOI

2025

Robust Safety-Critical Control of Uncertain Nonlinear Systems With DoS Attacks

Yi Dong, Xiran Cui, Yiguang Hong, Jie Chen

IEEE Transactions on Automatic Control

DOI

2025

Security Control of Safety-Critical Systems

Yi Dong, Yiguang Hong, Jie Chen

IEEE Transactions on Cybernetics

DOI

2025

Fixed‐Time Control Lyapunov Function for Networked Non‐Linear Uncertain Systems

Yi Dong, Zhiyong Chen

International Journal of Robust and Nonlinear Control

DOI

2025

Affine-SLAM: A closed-form solution to the landmark-SLAM via affine relaxation

Shaoran Yang, Yi Dong

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

DOI

2025

Resilient Control of Nonlinear Uncertain Systems With State Constraints

Meng Yao, Zhuang Ma, Litao He, Renjie Yan, Yi Dong

China Automation Congress (CAC)

DOI

2025

Safety-Aware Pursuit-Evasion Game Based on Control Barrier Function and Reinforcement Learning

Yupeng Jia, Xiran Cui, Yi Dong, Xiaoming Hu A

IEEE Transactions on Systems Man and Cybernetics Systems

DOI

2025

Stackelberg game-based optimal secure control against hybrid attacks for networked control systems

Wei Xiong, Yi Dong, Liubin Zhou

Journal of Automation and Intelligence

DOI

2025

Low-complexity approach for full-state error prescribed performance control of nonlinear systems with actuator faults

Fan Geng, Yi Dong, Hao Fang, Xiaoming Hu A

International Journal of Dynamics and Control

DOI

2025

Unified Barrier Function Based Approach for Practical Fixed-Time Control of State-Constrained Nonlinear System

Fan Geng, Yi Dong, Yiguang Hong

Journal of Systems Science and Complexity

DOI

2025

Data-driven output regulation control for constrained linear systems

Chaoyu Xia, Yi Dong, Chaoli Wang, Shengyuan Xu

Science China Information Sciences

DOI

2025

Reinforcement learning-based receding-horizon control for optimal output regulation problem with sensor and actuator attacks

Xiran Cui, Yi Dong, Chaoli Wang, Shengyuan Xu

Neurocomputing

DOI

2025

Optimal Capture Strategy Design Based on Reinforcement Learning in the Pursuit-Evasion Game with Unknown Dynamics

Yupeng Jia, Yi Dong

Lecture notes in electrical engineering

DOI

2025

Approximate Optimal Control for Nonlinear System with State Constraints and Partially Unknown Dynamics

Fan Geng, Yi Dong, Liubin Zhou, Rongyan Li

Proceedings of the IEEE Conference on Decision & Control, including the Symposium on Adaptive Processes

DOI

2024

Diverging Preferences: When do Annotators Disagree and do Models Know?

Michael J.Q. Zhang, Zhilin Wang, Jena D. Hwang, Yi Dong, Olivier Delalleau, Ye-Jin Choi, Eunsol Choi, Xiang Ren, Valentina Pyatkin

International Conference on Machine Learning

DOI

2024

NeMo-Aligner: Scalable Toolkit for Efficient Model Alignment

Gerald Shen, Zhilin Wang, Olivier Delalleau, Jia-Qi Zeng, Yi Dong, Daniel Egert, Shengyang Sun, Jimmy J. Zhang, Sahil Jain, Ali Taghibakhshi, M. S. Ausin, Ashwath Aithal, Oleksii Kuchaiev

arXiv.org

DOI

2024

HelpSteer2-Preference: Complementing Ratings with Preferences

Zhilin Wang, A. Bukharin, Olivier Delalleau, Daniel Egert, Gerald Shen, Jia-Qi Zeng, Oleksii Kuchaiev, Yi Dong

International Conference on Learning Representations

DOI

2024

Nemotron-4 340B Technical Report

Nvidia Bo Adler, Niket Agarwal, Ashwath Aithal, D. H. Anh, Pallab Bhattacharya, Annika Brundyn, J. Casper, B. Catanzaro, Sharon Clay, Jonathan Cohen, Sirshak Das, Ayush Dattagupta, Olivier Delalleau, Leon Derczynski, Yi Dong, Daniel Egert, Ellie Evans, Aleksander Ficek, Denys Fridman, Shaona Ghosh, Boris Ginsburg, Igor Gitman, Tomasz Grzegorzek, R. Hero, Jining Huang, Vibhu Jawa, Joseph Jennings, Aastha Jhunjhunwala, John Kamalu, Sadaf Khan, Oleksii Kuchaiev, P. LeGresley, Hui Li, Jiwei Liu, Zi-Han Liu, Eileen Long, A. Mahabaleshwarkar, Somshubra Majumdar, James Maki, Miguel Martínez, Maer Rodrigues de Melo, Ivan Moshkov, Deepak Narayanan, Sean Narenthiran, J. Navarro, Phong T. Nguyen, Osvald Nitski, V. Noroozi, Guruprasad Nutheti, Christopher Parisien, Jupinder Parmar, M. Patwary, Krzysztof Pawelec, Wei Ping, Shrimai Prabhumoye, Rajarshi Roy, Trisha Saar, Vasanth Rao Naik Sabavat, S. Satheesh, Jane Scowcroft, Jason D. Sewall, Pavel Shamis, Gerald Shen, M. Shoeybi, D. Sizer, Misha Smelyanskiy, Felipe Soares, Makesh Narsimhan Sreedhar, Dan Su, Sandeep Subramanian, Shengyang Sun, Shubham Toshniwal, Hao Wang, Zhilin Wang, Jiaxuan You, Jia-Qi Zeng, Jimmy J. Zhang, Jing Zhang, Vivian Zhang, Yian Zhang, Chen Zhu

arXiv.org

DOI

2024

HelpSteer2: Open-source dataset for training top-performing reward models

Zhilin Wang, Yi Dong, Olivier Delalleau, Jia-Qi Zeng, Gerald Shen, Daniel Egert, Jimmy J. Zhang, Makesh Narsimhan Sreedhar, Oleksii Kuchaiev

Neural Information Processing Systems

DOI

2024

Safe motion planning and formation control of quadruped robots

Zhenyang ji, Yi Dong

Autonomous Intelligent Systems

DOI

2024

Optimal Capture Strategy Design Based on Reinforcement Learning in the Pursuit-Evasion Game with Unknown Dynamics

Yupeng Jia, Yi Dong

Proceedings of the ... American Control Conference/Proceedings of the American Control Conference

DOI

2024

Data-Driven Cooperative Output Regulation of Linear Discrete-Time Multiagent Systems With Unknown Dynamics

Dong Liang, Yi Dong, Chaoli Wang, Ganghui Zhai

IEEE Transactions on Systems Man and Cybernetics Systems

DOI

2023

HelpSteer: Multi-attribute Helpfulness Dataset for SteerLM

Zhilin Wang, Yi Dong, Jia-Qi Zeng, Virginia Adams, Makesh Narsimhan Sreedhar, Daniel Egert, Olivier Delalleau, Jane Scowcroft, Neel Kant, Aidan Swope, Oleksii Kuchaiev

North American Chapter of the Association for Computational Linguistics

DOI

2023

SteerLM: Attribute Conditioned SFT as an (User-Steerable) Alternative to RLHF

Yi Dong, Zhilin Wang, Makesh Narsimhan Sreedhar, Xianchao Wu, Oleksii Kuchaiev

Conference on Empirical Methods in Natural Language Processing

DOI

2023

Safety critical control design for nonlinear system with tracking and safety objectives

Yi Dong, Xiaoyu Wang, Yiguang Hong

Automatica

DOI

2023

Global asymptotic fault-tolerant tracking for time-varying nonlinear complex systems with prescribed performance

Zhikai Zhang, Yi Dong, Guang‐Ren Duan

Automatica

DOI

2023

Prescribed‐time cooperative output regulation of heterogeneous multi‐agent systems

Dong Liang, Yi Dong, Chaoli Wang

International Journal of Robust and Nonlinear Control

DOI

2023

Adaptive output observer for a nonautonomous leader system over periodic switching topologies and its applications to the formation control of offshore vessels

Panpan Zhou, Xiaoming Hu A, Yi Dong

International Journal of Robust and Nonlinear Control

DOI

2023

Safety Critical Control Design of Second-order Nonlinear System and Its Application in Biped Robot

Xiaoyu Wang, Yi Dong

International Symposium on Autonomous Systems (ISAS)

DOI

2023

Adaptive coordinated control of networked non-affine nonlinear systems with a non-autonomous nonlinear leader

Yi Dong, Rongrong Gu

Nonlinear Dynamics

DOI

2022

Fixed-Time Robust Networked Observers and Its Application to Attitude Synchronization of Spacecraft Systems

Yi Dong, Zhiyong Chen

IEEE Transactions on Cybernetics

DOI

2022

Fixed-time synchronization of networked uncertain Euler–Lagrange systems

Yi Dong, Zhiyong Chen

Automatica

DOI

2022

An internal‐model‐based event‐triggered strategy for rendezvous with connectivity preservation problem of multi‐agent systems

Xun Cheng Wu, Yi Dong

International Journal of Robust and Nonlinear Control

DOI

2022

Internal Model-Based Observer Design for Synchronization of Nonlinear Multiagent Systems in Switching Networks

Yi Dong, Zhiyong Chen

IEEE Transactions on Control of Network Systems

DOI

2022

Finite-time Cooperative Control of Multiple Uncertain Euler-Lagrange Systems

Yi Dong

International Conference on Control and Automation

DOI

2022

Online adaptive parameter identification of an unmanned surface vehicle without persistency of excitation

Jiawang Yue, Lu Liu, Nan Gu, Zhouhua Peng, Dan Wang, Yi Dong

Ocean Engineering

DOI

2022

Recent advances on micro-control for near-critical complex systems

Di Zhao, Yi Dong

Control Theory and Technology

DOI

2022

Robust cooperative output regulation of linear uncertain multi-agent systems by distributed event-triggered dynamic feedback control

Dong Liang, Yi Dong

Neurocomputing

DOI

2021

An Event-Triggered Observer and Its Applications in Cooperative Control of Multiagent Systems

Yi Dong, Zongli Lin

IEEE Transactions on Automatic Control

DOI

2021

Nonlinear observer-based approach for cooperative control of networked rigid spacecraft systems

Yi Dong, Jie Chen

Automatica

DOI

2020

Rendezvous With Connectivity Preservation Problem of Linear Multiagent Systems via Parallel Event-Triggered Control Strategies

Yi Dong, Shengyuan Xu

IEEE Transactions on Cybernetics

DOI

2020

Event-triggered Control Strategies for Rendezvous Problem of Multiple Linear Systems

Yi Dong

International Conference on Control and Automation

DOI

2020

A Novel Connectivity-Preserving Control Design for Rendezvous Problem of Networked Uncertain Nonlinear Systems

Yi Dong, Shengyuan Xu

IEEE Transactions on Neural Networks and Learning Systems

DOI

2019

Cooperative Output Regulation Problem of Nonlinear Multiagent Systems With Proximity Graph via Output Feedback Control

Yi Dong, Shengyuan Xu

IEEE Transactions on Cybernetics

DOI

2014

Leader-following Rendezvous with Connectivity Preservation of Single-integrator Multi-agent Systems

Yi Dong, Jie Huang

IEEE/CAA Journal of Automatica Sinica

Uncovering Factor-Level Preference to Improve Human-Model Alignment Anonymous ACL submission

Yuntao Bai, Saurav Kadavath, Sandipan Kundu, A. Askell, John Kernion, Andy Jones, Anna Chen, Anna Goldie, Azalia Mirhoseini, Yi Dong, Makesh Zhilin Wang, N. Sreedhar, Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, A. Glaese, Nat McAleese, Maja Tr ̨ebacz, John Aslanides, Vlad Firoiu, T. Ewalds, Maribeth Rauh, Laura Weidinger, Martin Chadwick, Phoebe Thacker, Shangmin Guo, Biao Zhang, Tian-Lin Liu, Tian-Qi Liu, Yebowen Hu, Kai-Qiang Song, Sangwoo Cho, Xiao-Yang Wang, H. Foroosh, Fei Liu, Hamish Ivison, Yizhong Wang, Jia-Cheng Liu, Zeqiu Wu, V. Pyatkin, Nathan Lambert, Noah A. Smith, Albert Q. Jiang, Alexandre Sablayrolles, Antoine Roux, Seungone Kim, Jamin Shin, Yejin Cho, J. Jang, Sunghwan Kim, Dongjin Kang, Taeyoon Kwon, Kalpesh Krishna, Erin Bransom, Mohit Bailey Kuehl, Pradeep Iyyer, Arman Dasigi, C. Kyle, Ló, Harrison Lee, Samrat Phatale, H. Mansoor, Yang Liu, Dan Iter, Yi-Chong Xu, Shuo Wang, Aman Madaan, Niket Tandon, Prakhar Gupta, Sewon Min, Xinxi Lyu, Wen Lewis, Pang-Wei Yih, M. Koh, Iyyer, Luke S. Zettlemoyer, Hanna Hajishirzi, Reiichiro Nakano, Jacob Hilton, S. Balaji, Jeff Wu, Xu Jiang, K. Cobbe, Tyna Eloundou, K. Krueger, M. Button, Benjamin Knight

会议论文

2023

Data-driven Optimal Cooperative Output Regulation of Unknown Linear Discrete-time Multi-agent Systems

Dong Liang, Yi Dong, Chaoli Wang, Engang Tian

《第35届中国控制与决策会议论文集（4）》

DOI

2022

Multi-agent Path Planning based on Heuristic Priority Planning

Yifan Shan, Li Li, Yi Dong

《第34届中国控制与决策会议论文集（5）》

DOI

2022

A Unified Approach for Safety Critical Control Problem via Output Regulation Theory and Barrier Function

Xiaoyu Wang, Ziliang Lyu, Yi Dong

《第41届中国控制会议论文集（2）》

DOI

2016

Containment Control of Multiple Uncertain Lagrangian Systems

Yi Dong, Shengyuan Xu

《第28届中国控制与决策会议论文集（上）》

预印本

2026

OSWorld-Pro: Process-based Evaluation for Computer Use Agents

Zhilin Wang, Shaokun Zhang, Yifan Zhang, Hao Zhang, Jin Xu, Binfeng Xu, Jian Hu, Yunheng Zou, Karan Sapra, Andrew Tao, Jan Kautz, Yi Dong

arXiv preprint

2026

LoGRA: Scaling LLM Reinforcement Learning with Low-Rank Gradient Sketches

Shaokun Zhang, Yifan Zhang, Jian Hu, Yueying Li, Hao Zhang, Binfeng Xu, Jan Kautz, Yi Dong

arXiv preprint

2026

Mid-Harness: Scaling Actions Between Model and Harness for Terminal Agents

Minki Kang, Ryo Hachiuma, Shaokun Zhang, Subhashree Radhakrishnan, Yonggan Fu, Jindong Jiang, Mingjie Liu, Ehsan Hosseini-Asl, Yi Dong, Yu-Chiang Frank Wang, Byung-Kwan Lee

arXiv preprint

2026

Agora: Git as Shared Memory for Collective AutoResearch

Yifan Zhang, Yunheng Zou, Shaokun Zhang, Jian Hu, Hao Zhang, Binfeng Xu, Jan Kautz, Yi Dong

arXiv preprint

2026

Responsible Agentic AI Requires Explicit Provenance

Jinwei Hu, Xinmiao Huang, Qisong He, Youcheng Sun, Yi Dong, Xiaowei Huang

arXiv preprint

2026

PrefixGuard: Online Failure Warning and Trace-Grounded Diagnosis for LLM Agents

Xinmiao Huang, Jinwei Hu, Qisong He, Rajarshi Roy, Changshun Wu, Yi Dong, Xiaowei Huang

arXiv preprint

2026

SCARCE: Scalable Cascade Analysis for Rare-event Characterisation via Embeddings

Yingjie Wang, Yi Dong, Edmund Lau, Jie Meng, Taylor T Johnson, Xiaowei Huang

arXiv preprint

2026

Lying with Truths: Open-Channel Multi-Agent Collusion for Belief Manipulation via Generative Montage

Jinwei Hu, Xinmiao Huang, Youcheng Sun, Yi Dong, Xiaowei Huang

arXiv preprint

DOI

2026

FragileFlow: Spectral Control of Correct-but-Fragile Predictions for Foundation Model Robustness

Zhuoyun Li, Boxuan Wang, Jinwei Hu, Xiaowei Huang, Yi Dong

arXiv preprint

2026

The One-Pixel of Reasoning: One Truthful Relation Is Enough to Mislead LLM Agents

Jinwei Hu, Youcheng Sun, Yi Dong, Xiaowei Huang

arXiv preprint

2026

Grounded Continuation: A Linear-Time Runtime Verifier for LLM Conversations

Qisong He, Jinwei Hu, Xinmiao Huang, Changshun Wu, Yi Dong, Xiaowei Huang

arXiv preprint

2026

Safety-Constrained Reinforcement Learning with Post-Training Reachability Verification for Robot Navigation

Qisong He, Xinmiao Huang, Jinwei Hu, Zhuoyun Li, Yi Dong, Changshun Wu, Xiaowei Huang

arXiv preprint

2026

SkillFuzz: Fuzzing Skill Composition for Implicit Intents Discovery in Open Skill Marketplaces

Jinwei Hu, Yi Dong, Youcheng Sun, Xiaowei Huang

arXiv preprint

2026

Skill Use or Skill Theater? Evaluating the Reasoning Backroom in Skill-Augmented Language Agents

Jinwei Hu, Yi Qi, Xinmiao Huang, Youcheng Sun, Yi Dong, Xiaowei Huang

arXiv preprint

2026

Dive into Ambiguity: A*-Inspired Multi-Agents Commonsense Obfuscation Attack on LLM Prompts

Boxuan Wang, Zhuoyun Li, Xiaowei Huang, Yi Dong

arXiv preprint

2026

Where Do Prompt Perturbations Break Generation? A Segment-Level View of Robustness in LoRA-Tuned Language Models

Zhuoyun Li, Boxuan Wang, Jinwei Hu, Zhenglin Huang, Qisong He, Xinmiao Huang, Guangliang Cheng, Xiaowei Huang, Yi Dong

arXiv preprint

2026

Do We Need Complex Topology Control? Distinct-Peer Random Routing Improves Cost-Efficiency in Sparse Multi-Agent Debate

Boxuan Wang, Zhuoyun Li, Xiaowei Huang, Yi Dong

arXiv preprint

2026

DDSA: Dual-Domain Strategic Attack for Spatial-Temporal Efficiency in Adversarial Robustness Testing

Jinwei Hu, Shiyuan Meng, Yi Dong, Xiaowei Huang

arXiv preprint

DOI

2026

Same evidence, different judgments: Evidence noncommutative in vision/speech-text conflicts

Zhuoyun Li, Boxuan Wang, Xiaowei Huang, Yi Dong

arXiv preprint

2026

SCOPE: Sequential Conformal Probing for Reliable OOD Rejection in LLM Services

Zhuoyun Li, Boxuan Wang, Changshun Wu, Xiaowei Huang, Yi Dong

arXiv preprint

2025

The Invisible Leash: Why RLVR May or May Not Escape Its Origin

Fang Wu, Weihao Xuan, Danny Xing, Ximing Lu, Mingjie Liu, Yi Dong, Zaid Harchaoui, Yejin Choi

arXiv preprint

2025

TAIJI: Textual Anchoring for Immunizing Jailbreak Images in Vision Language Models

Xiangyu Yin, Yi Qi, Jinwei Hu, Zhen Chen, Yi Dong, Xingyu Zhao, Xiaowei Huang, Wenjie Ruan

arXiv preprint

2025

Distributed Nash Equilibrium Seeking Algorithm in Aggregative Games for Heterogeneous Multi-Robot Systems

Yi Dong, Zhongguo Li, Sarvapali D. Ramchurn, Xiaowei Huang

arXiv preprint

2025

FALCON: Fine-grained Activation Manipulation by Contrastive Orthogonal Unalignment for Large Language Model

Jinwei Hu, Zhenglin Huang, Xiangyu Yin, Wenjie Ruan, Guangliang Cheng, Yi Dong, Xiaowei Huang

arXiv preprint

2025

CeTAD: Towards Certified Toxicity-Aware Distance in Vision Language Models

Xiangyu Yin, Jiaxu Liu, Zhen Chen, Jinwei Hu, Yi Dong, Xiaowei Huang, Wenjie Ruan

arXiv preprint

2025

Rethinking Multi-Agent Intelligence Through the Lens of Small-World Networks

Boxuan Wang, Zhuoyun Li, Xiaowei Huang, Yi Dong

arXiv preprint

2025

Safe Pruning LoRA: Robust Distance-Guided Pruning for Safety Alignment in Adaptation of LLMs

Shuang Ao, Yi Dong, Jinwei Hu, Sarvapali Ramchurn

arXiv preprint

2025

Enhancing Robustness of LLM-Driven Multi-Agent Systems through Randomized Smoothing

Jinwei Hu, Yi Dong, Zhengtao Ding, Xiaowei Huang

arXiv preprint

2025

Position: Towards a Responsible LLM-empowered Multi-Agent Systems

Jinwei Hu, Yi Dong, Shuang Ao, Zhuoyun Li, Boxuan Wang, Lokesh Singh, Guangliang Cheng, Sarvapali D. Ramchurn, Xiaowei Huang

arXiv preprint

2025

Chain-of-Thought as a Lens: Evaluating Structured Reasoning Alignment between Human Preferences and Large Language Models

Boxuan Wang, Zhuoyun Li, Xinmiao Huang, Xiaowei Huang, Yi Dong

arXiv preprint

2025

Tapas Are Free! Training-Free Adaptation of Programmatic Agents via LLM-Guided Program Synthesis in Dynamic Environments

Jinwei Hu, Yi Dong, Youcheng Sun, Xiaowei Huang

arXiv preprint

2025

Spatial-DISE: A Unified Benchmark for Evaluating Spatial Reasoning in Vision-Language Models

Xinmiao Huang, Qisong He, Zhenglin Huang, Boxuan Wang, Zhuoyun Li, Guangliang Cheng, Yi Dong, Xiaowei Huang

arXiv preprint

2025

Hierarchical Testing with Rabbit Optimization for Industrial Cyber-Physical Systems

Jinwei Hu, Zezhi Tang, Xin Jin, Benyuan Zhang, Yi Dong, Xiaowei Huang

arXiv preprint

2025

Stop Reducing Responsibility in LLM-Powered Multi-Agent Systems to Local Alignment

Jinwei Hu, Yi Dong, Shuang Ao, Zhuoyun Li, Boxuan Wang, Lokesh Singh, Guangliang Cheng, Sarvapali D. Ramchurn, Xiaowei Huang

arXiv preprint

2024

Safeguarding Large Language Models: A Survey

Yi Dong, Ronghui Mu, Yanghao Zhang, Siqi Sun, Tianle Zhang, Changshun Wu, Gaojie Jin, Yi Qi, Jinwei Hu, Jie Meng, Saddek Bensalem, Xiaowei Huang

arXiv preprint

2024

Privacy-Preserving Distributed Learning for Residential Short-Term Load Forecasting

Yi Dong, Yingjie Wang, Mariana Gama, Mustafa A. Mustafa, Geert Deconinck, Xiaowei Huang

arXiv preprint

DOI

2024

Building Guardrails for Large Language Models

Yi Dong, Ronghui Mu, Gaojie Jin, Yi Qi, Jinwei Hu, Xingyu Zhao, Jie Meng, Wenjie Ruan, Xiaowei Huang

arXiv preprint

2024

Discrete-Time Stress Matrix-Based Formation Control of General Linear Multi-Agent Systems

Okechi Onuoha, Suleiman Kurawa, Zezhi Tang, Yi Dong

arXiv preprint

2024

Trust-Oriented Adaptive Guardrails for Large Language Models

Jinwei Hu, Yi Dong, Xiaowei Huang

arXiv preprint

2023

A Survey of Safety and Trustworthiness of Large Language Models through the Lens of Verification and Validation

Xiaowei Huang, Wenjie Ruan, Wei Huang, Gaojie Jin, Yi Dong, Changshun Wu, Saddek Bensalem, Ronghui Mu, Yi Qi, Xingyu Zhao, Kaiwen Cai, Yanghao Zhang, Sihao Wu, Peipei Xu, Dengyu Wu, Andre Freitas, Mustafa A. Mustafa

arXiv preprint

2023

STPA for Learning-Enabled Systems: A Survey and A New Practice

Yi Qi, Yi Dong, Siddartha Khastgir, Paul Jennings, Xingyu Zhao, Xiaowei Huang

arXiv preprint

2023

Decentralised and Cooperative Control of Multi-Robot Systems through Distributed Optimisation

Yi Dong, Zhongguo Li, Xingyu Zhao, Zhengtao Ding, Xiaowei Huang

arXiv preprint

2022

Short-term Load Forecasting with Distributed Long Short-Term Memory

Yi Dong, Yang Chen, Xingyu Zhao, Xiaowei Huang

arXiv preprint

2022

Reachability Verification Based Reliability Assessment for Deep Reinforcement Learning Controlled Robotics and Autonomous Systems

Yi Dong, Xingyu Zhao, Sen Wang, Xiaowei Huang

arXiv preprint

2021

Detecting Operational Adversarial Examples for Reliable Deep Learning

Xingyu Zhao, Wei Huang, Sven Schewe, Yi Dong, Xiaowei Huang

arXiv preprint

DOI

2021

Reliability Assessment and Safety Arguments for Machine Learning Components in System Assurance

Yi Dong, Wei Huang, Vibhav Bharti, Victoria Cox, Alec Banks, Sen Wang, Xingyu Zhao, Sven Schewe, Xiaowei Huang

arXiv preprint

DOI

2021

Dependability Analysis of Deep Reinforcement Learning based Robotics and Autonomous Systems through Probabilistic Model Checking

Yi Dong, Xingyu Zhao, Xiaowei Huang

arXiv preprint

DOI

研究方向

人工智能无人系统机器学习分布式控制

此主页由公开资料整理，尚未经学者本人认领。