CZChongjie Zhang

Chongjie Zhang

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Chongjie Zhang has a total of 66 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Cross-robot behavior adaptation through intention alignment

    by Xi Chen, Yuan Gao, Hangxin Liu, Fangkai Yang, Ali Ghadirzadeh, Jun Yang, Bin Liang, Chongjie Zhang, Tin Lun Lam, Song-Chun Zhu

    Imitation learning (IL) has succeeded in enabling robots to perform new tasks by learning from demonstrations. However, its success is often constrained by the need for direct skill mappings between a learner and a demonstrator under identical conditions, limiting its adaptability to diverse environments and generalization across robots with different physical embodiments. To address these challenges, we introduce the Intention-Aligned Imitation Learning (IAIL) framework, a behavior adaptation approach that extends the conventional scope of IL by enabling robots to reproduce motions demonstrated by heterogeneous peers, even in previously unseen situations. Inspired by human cultural learning, IAIL aligns and adapts robot motions on the basis of high-level intentions annotated in natural language rather than by directly copying motor movements. This alignment is achieved by constructing a shared intention space that connects robot-generated motions with linguistic annotations, enabling inference-time behavior adaptation across diverse embodiments and environmental contexts. The framework further supports scalable task allocation in heterogeneous robot teams by leveraging differences in capabilities and constraints. We validated IAIL through real-world experiments involving seven distinct robots performing multistep collaboration tasks across 30 scenarios. Our results demonstrate that IAIL enables robust intention-aligned behavior adaptation across variations in embodiment, motion modality, and task configuration. These capabilities enable flexible behavior transfer across heterogeneous robots and support resilient, autonomous multirobot systems for reliable real-world collaboration.


  • Open Access

    Learning Recommender Mechanisms for Bayesian Stochastic Games

    by Bengisu Guresti, Chongjie Zhang, Yevgeniy Vorobeychik

    An important challenge in non-cooperative game theory is coordinating on a single (approximate) equilibrium from many possibilities - a challenge that becomes even more complex when players hold private information. Recommender mechanisms tackle this problem by recommending strategies to players based on their reported type profiles. A key consideration in such mechanisms is to ensure that players are incentivized to participate, report their private information truthfully, and follow the recommendations. While previous work has focused on designing recommender mechanisms for one-shot and extensive-form games, these approaches cannot be effectively applied to stochastic games, particularly if we constrain recommendations to be Markov stationary policies. To bridge this gap, we introduce a novel bi-level reinforcement learning approach for automatically designing recommender mechanisms in Bayesian stochastic games. Our method produces a mechanism represented by a parametric function (such as a neural network), and is therefore highly efficient at execution time. Experimental results on two repeated and two stochastic games demonstrate that our approach achieves social welfare levels competitive with cooperative multi-agent reinforcement learning baselines, while also providing significantly improved incentive properties.

  • Open Access

    EcoLoRA: Communication-Efficient Federated Fine-Tuning of Large Language Models

    by Han Liu, Ruoyao Wen, Srijith Nair, Jia Liu, Wenjing Lou, Chongjie Zhang, William Yeoh, Yevgeniy Vorobeychik, Ning Zhang

    Han Liu, Ruoyao Wen, Srijith Nair, Jia Liu, Wenjing Lou, Chongjie Zhang, William Yeoh, Yevgeniy Vorobeychik, Ning Zhang. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.


  • Open Access

    IBGP: Imperfect Byzantine Generals Problem for Zero-Shot Robustness in Communicative Multi-Agent Systems

    by Yihuan Mao, Yipeng Kang, Peilun Li, Ning Zhang, Wei Xu, Chongjie Zhang

    As large language model (LLM) agents increasingly integrate into our infrastructure, their robust coordination and message synchronization become vital. The Byzantine Generals Problem (BGP) is a critical model for constructing resilient multi-agent systems (MAS) under adversarial attacks. It describes a scenario where malicious agents with unknown identities exist in the system-situations that, in our context, could result from LLM agents' hallucinations or external attacks. In BGP, the objective of the entire system is to reach a consensus on the action to be taken. Traditional BGP requires global consensus among all agents; however, in practical scenarios, global consensus is not always necessary and can even be inefficient. Therefore, there is a pressing need to explore a refined version of BGP that aligns with the local coordination patterns observed in MAS. We refer to this refined version as Imperfect BGP (IBGP) in our research, aiming to address this discrepancy. To tackle this issue, we propose a framework that leverages consensus protocols within general MAS settings, providing provable resilience against communication attacks and adaptability to changing environments, as validated by empirical results. Additionally, we present a case study in a sensor network environment to illustrate the practical application of our protocol.

  • Open Access

    Efficient Multi-agent Reinforcement Learning by Planning

    by Qihan Liu, Jianing Ye, Xiaoteng Ma, Jun Yang, Bin Liang, Chongjie Zhang

    Multi-agent reinforcement learning (MARL) algorithms have accomplished remarkable breakthroughs in solving large-scale decision-making tasks. Nonetheless, most existing MARL algorithms are model-free, limiting sample efficiency and hindering their applicability in more challenging scenarios. In contrast, model-based reinforcement learning (MBRL), particularly algorithms integrating planning, such as MuZero, has demonstrated superhuman performance with limited data in many tasks. Hence, we aim to boost the sample efficiency of MARL by adopting model-based approaches. However, incorporating planning and search methods into multi-agent systems poses significant challenges. The expansive action space of multi-agent systems often necessitates leveraging the nearly-independent property of agents to accelerate learning. To tackle this issue, we propose the MAZero algorithm, which combines a centralized model with Monte Carlo Tree Search (MCTS) for policy search. We design a novel network structure to facilitate distributed execution and parameter sharing. To enhance search efficiency in deterministic environments with sizable action spaces, we introduce two novel techniques: Optimistic Search Lambda (OS($λ$)) and Advantage-Weighted Policy Optimization (AWPO). Extensive experiments on the SMAC benchmark demonstrate that MAZero outperforms model-free approaches in terms of sample efficiency and provides comparable or better performance than existing model-based methods in terms of both sample and computational efficiency. Our code is available at https://github.com/liuqh16/MAZero.


  • Open Access

    Imitation Learning from Observation with Automatic Discount Scheduling

    by Yuyang Liu, Weijun Dong, Yingdong Hu, Chuan Wen, Zhao-Heng Yin, Chongjie Zhang, Yang Gao

    Humans often acquire new skills through observation and imitation. For robotic agents, learning from the plethora of unlabeled video demonstration data available on the Internet necessitates imitating the expert without access to its action, presenting a challenge known as Imitation Learning from Observations (ILfO). A common approach to tackle ILfO problems is to convert them into inverse reinforcement learning problems, utilizing a proxy reward computed from the agent's and the expert's observations. Nonetheless, we identify that tasks characterized by a progress dependency property pose significant challenges for such approaches; in these tasks, the agent needs to initially learn the expert's preceding behaviors before mastering the subsequent ones. Our investigation reveals that the main cause is that the reward signals assigned to later steps hinder the learning of initial behaviors. To address this challenge, we present a novel ILfO framework that enables the agent to master earlier behaviors before advancing to later ones. We introduce an Automatic Discount Scheduling (ADS) mechanism that adaptively alters the discount factor in reinforcement learning during the training phase, prioritizing earlier rewards initially and gradually engaging later rewards only when the earlier behaviors have been mastered. Our experiments, conducted on nine Meta-World tasks, demonstrate that our method significantly outperforms state-of-the-art methods across all tasks, including those that are unsolvable by them.

  • Open Access

    Leveraging Hyperbolic Embeddings for Coarse-to-Fine Robot Design

    by Heng Dong, Junyu Zhang, Chongjie Zhang

    Multi-cellular robot design aims to create robots comprised of numerous cells that can be efficiently controlled to perform diverse tasks. Previous research has demonstrated the ability to generate robots for various tasks, but these approaches often optimize robots directly in the vast design space, resulting in robots with complicated morphologies that are hard to control. In response, this paper presents a novel coarse-to-fine method for designing multi-cellular robots. Initially, this strategy seeks optimal coarse-grained robots and progressively refines them. To mitigate the challenge of determining the precise refinement juncture during the coarse-to-fine transition, we introduce the Hyperbolic Embeddings for Robot Design (HERD) framework. HERD unifies robots of various granularity within a shared hyperbolic space and leverages a refined Cross-Entropy Method for optimization. This framework enables our method to autonomously identify areas of exploration in hyperbolic space and concentrate on regions demonstrating promise. Finally, the extensive empirical studies on various challenging tasks sourced from EvoGym show our approach's superior efficiency and generalization capability.

  • Celebrating Diversity With Subtask Specialization in Shared Multiagent Reinforcement Learning

    by Chenghao Li, Tonghan Wang, Chengjie Wu, Qianchuan Zhao, Jun Yang, Chongjie Zhang

    Subtask decomposition offers a promising approach for achieving and comprehending complex cooperative behaviors in multiagent systems. Nonetheless, existing methods often depend on intricate high-level strategies, which can hinder interpretability and learning efficiency. To tackle these challenges, we propose a novel approach that specializes subtasks for subgroups by employing diverse observation representation encoders within information bottlenecks. Moreover, to enhance the efficiency of subtask specialization while promoting sophisticated cooperation, we introduce diversity in both optimization and neural network architectures. These advancements enable our method to achieve state-of-the-art performance and offer interpretable subtask factorization across various scenarios in Google Research Football (GRF).