Author name cluster

Cong Zhang

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

15 papers

2 author rows

AAAI Conference 2026 Conference Paper

Divide-and-Conquer Decoupled Network for Cross-Domain Few-Shot Segmentation

Runmin Cong
Anpeng Wang
Bin Wan
Cong Zhang
Xiaofei Zhou
Wei Zhang

Cross-domain few-shot segmentation (CD-FSS) aims to tackle the dual challenge of recognizing novel classes and adapting to unseen domains with limited annotations. However, encoder features often entangle domain-relevant and category-relevant information, limiting both generalization and rapid adaptation to new domains. To address this issue, we propose a Divide-and-Conquer Decoupled Network (DCDNet). In the training stage, to tackle feature entanglement that impedes cross-domain generalization and rapid adaptation, we propose the Adversarial-Contrastive Feature Decomposition (ACFD) module. It decouples backbone features into category-relevant private and domain-relevant shared representations via contrastive learning and adversarial learning. Then, to mitigate the potential degradation caused by the disentanglement, the Matrix-Guided Dynamic Fusion (MGDF) module adaptively integrates base, shared, and private features under spatial guidance, maintaining structural coherence. In addition, in the fine-tuning stage, to enhanced model generalization, the Cross-Adaptive Modulation (CAM) module is placed before the MGDF, where shared features guide private features via modulation ensuring effective integration of domain-relevant information. Extensive experiments on four challenging datasets show that DCDNet outperforms existing CD-FSS methods, setting a new state-of-the-art for cross-domain generalization and few-shot adaptation.

PDF Details DOI

TMLR Journal 2025 Journal Article

Collaboration with Dynamic Open Ad Hoc Team via Team State Modelling

Jing Sun
Cong Zhang
Zhiguang Cao

Open ad hoc teamwork presents the challenging problem of designing an autonomous agent that can rapidly adapt to collaborate with teammates without prior coordination in an open environment. Existing methods primarily rely on fixed, predefined teammate types, overlooking the fact that teammates may change dynamically. To address this limitation, we propose a novel reinforcement learning approach, the Open Online Teammate Adaptation Framework (Open-OTAF), which enables a controlled agent to collaborate with dynamic teammates in open ad hoc environments. To achieve this, the controlled agent employs a dual teamwork situation inference model to capture the current teamwork state, facilitating decision-making under partial observability. To handle the dynamic nature of teammate types, we first introduce a Chinese Restaurant Process-based model to categorize diverse teammate policies into distinct clusters, improving the efficiency of identifying teamwork situations. Next, to model heterogeneous agent relationships and accommodate a variable number of teammates, we represent the team as a heterogeneous graph and leverage heterogeneous graph attention neural networks to learn the representation of the teamwork situation. Extensive experiments across four challenging multi-agent benchmark tasks—Level-Based Foraging, Wolf-Pack, Cooperative Navigation, and FortAttack—demonstrate that our method successfully enables dynamic teamwork in open ad hoc settings. Open-OTAF outperforms state-of-the-art methods, achieving superior performance with faster convergence.

PDF Details

ICLR Conference 2025 Conference Paper

Graph Assisted Offline-Online Deep Reinforcement Learning for Dynamic Workflow Scheduling

Yifan Yang
Gang Chen
Hui Ma
Cong Zhang
Zhiguang Cao
Mengjie Zhang

Dynamic workflow scheduling (DWS) in cloud computing presents substantial challenges due to heterogeneous machine configurations, unpredictable workflow arrivals/patterns, and constantly evolving environments. However, existing research often assumes homogeneous setups and static conditions, limiting flexibility and adaptability in real-world scenarios. In this paper, we propose a novel *Graph assisted Offline-Online Deep Reinforcement Learning* (GOODRL) approach to building an effective and efficient scheduling agent for DWS. Our approach features three key innovations: (1) a *task-specific* graph representation and a *Graph Attention Actor Network* that enable the agent to dynamically assign focused tasks to heterogeneous machines while explicitly considering the future impact of each machine on these tasks; (2) a *system-oriented* graph representation and a *Graph Attention Critic Network* that facilitate efficient processing of new information and understanding its impact on the current state, crucial for managing unpredictable workflow arrivals/patterns in real-time; and (3) an *offline-online* method that utilizes imitation learning for effective offline training and applies gradient control and decoupled high-frequency critic training techniques during online learning to sustain the agent’s robust performance in rapidly changing environments. Experimental results demonstrate that GOODRL significantly outperforms several state-of-the-art algorithms, achieving substantially lower mean flowtime and high adaptability in various online and offline scenarios.

Details

YNIMG Journal 2025 Journal Article

Low-intensity transcranial ultrasound stimulation promotes the extinction of fear memory through the BDNF-TrkB signaling pathway

Degong Meng
Cong Zhang
Jiamin Pei
Xiao Zhang
Hanna Lu
Hui Ji
Xiangjian Zhang
Yi Yuan

Synaptic plasticity plays a crucial role in the extinction of fearful memories. Low-intensity transcranial ultrasound stimulation (TUS) can modulate synaptic plasticity and promote the extinction of fear memories. However, the mechanism by which TUS promotes the extinction of fear memory remains unclear. This study aimed to explore whether and how synaptic plasticity under TUS is involved in modulating fear memory and the role of the brain-derived neurotrophic factor (BDNF)-the tropomyosin-related kinase B (TrkB) signaling pathway in this process. We used behavioral tests and two-photon fluorescence imaging to investigate the modulatory effects of TUS on fear memory and examined the formation/elimination of dendritic spines and the calcium activity of pyramidal neurons in the prefrontal cortex in mice in vivo. We found that TUS of the prefrontal cortex can promote fear memory extinction in mice while promoting dendritic spine formation, reducing dendritic spine elimination, increasing pyramidal neuron activity, and enhancing the expression of BDNF and its receptor TrkB. Conversely, inhibiting the BDNF-TrkB signaling pathway weakened these effects of ultrasound stimulation. Our study demonstrated that TUS could promote the extinction of fear memories, indicating that TUS has the potential to be used in the clinical treatment of patients with fear memory.

Details DOI

IROS Conference 2025 Conference Paper

On-Board Vision-Language Models (VLMs) for Personalized Motion Control of Autonomous Vehicles

Can Cui 0009
Zichong Yang
Yupeng Zhou
Juntong Peng
Sung-Yeon Park
Cong Zhang
Yunsheng Ma
Xu Cao

Personalized driving refers to an autonomous vehicle’s ability to adapt its driving behavior or control strategies to match individual users’ preferences and driving styles while maintaining safety and comfort standards. However, existing works either fail to capture every individual’s preference precisely or become computationally inefficient as the user base expands. Vision-Language Models (VLMs) offer promising solutions to this front through their natural language understanding and scene reasoning capabilities. In this work, we propose a lightweight yet effective on-board VLM framework that provides low-latency personalized driving performance while maintaining strong reasoning capabilities. Our solution incorporates a Retrieval-Augmented Generation (RAG)-based memory module that enables continuous learning of individual driving preferences through human feedback. Through comprehensive real-world vehicle experiments, our system has demonstrated the ability to provide safe, comfortable, and personalized driving experiences across various scenarios and significantly reduce takeover rates by up to 76. 9%. To the best of our knowledge, this work represents the first personalized VLM motion control system in real-world autonomous vehicles. The demo video can be watched at https://tinyurl.com/4xsnz79n.

Details

NeurIPS Conference 2025 Conference Paper

Robust SuperAlignment: Weak-to-Strong Robustness Generalization for Vision-Language Models

Junhao Dong
Cong Zhang
Xinghua Qu
Zejun Ma
Piotr Koniusz
Yew Soon Ong

Numerous well-established studies have demonstrated the superhuman capabilities of modern Vision-Language Models (VLMs) across a wide range of tasks. However, growing is the doubt about the continuing availability of reliable high-quality labeling (supervision) from human annotators, leading to stagnation of the model's performance. To address this challenge, ``superalignment'' employs the so-called weak-to-strong generalization paradigm, where the supervision from a weak model can provide generalizable knowledge for a strong model. While effective in aligning knowledge for clean samples between the strong and weak models, the standard weak-to-strong approach typically fails to capture adversarial robustness, exposing strong VLMs to adversarial attacks. This inability to transfer adversarial robustness is because adversarial samples are normally missing in the superalignment stage. To this end, we are the first to propose the weak-to-strong (adversarial) robustness generalization method to elicit zero-shot robustness in large-scale models by an unsupervised scheme, mitigating the unreliable information source for alignment from two perspectives: alignment re-weighting and source guidance refinement. We analyze settings under which robustness generalization is possible. Extensive experiments across various vision-language benchmarks validate the effectiveness of our method in numerous scenarios, demonstrating its plug-and-play applicability to large-scale VLMs.

PDF Details

IROS Conference 2025 Conference Paper

VET: A Visual-Electronic Tactile System for Immersive Human-Machine Interaction

Cong Zhang
Yisheng Yang
Shilong Mu
Chuqiao Lyu
Shoujie Li
Xinyue Chai
Wenbo Ding 0001

In the pursuit of deeper immersion in human-machine interaction, achieving higher-dimensional tactile input and output on a single interface has become a key research focus. This study introduces the Visual-Electronic Tactile (VET) System, which builds upon vision-based tactile sensors (VBTS) and integrates electrical stimulation feedback to enable bidirectional tactile communication. We propose and implement a system framework that seamlessly integrates an electrical stimulation film with VBTS using a screen-printing preparation process, eliminating interference from traditional methods. While VBTS captures multi-dimensional input through visuotactile signals, electrical stimulation feedback directly stimulates neural pathways, preventing interference with visuotactile information. The potential of the VET system is demonstrated through experiments on finger electrical stimulation sensitivity zones, as well as applications in interactive gaming and robotic arm teleoperation. This system paves the way for new advancements in bidirectional tactile interaction and its broader applications.

Details

AIJ Journal 2025 Journal Article

Weighted EF1 allocations for indivisible chores

Xiaowei Wu
Cong Zhang
Shengwei Zhou

We study how to fairly allocate a set of indivisible chores to a group of agents, where each agent i has a non-negative weight w i that represents her obligation for undertaking the chores. We consider the fairness notion of weighted envy-freeness up to one item (WEF1) and propose an efficient picking sequence algorithm for computing WEF1 allocations. Our analysis is based on a natural and powerful continuous interpretation for the picking sequence algorithms in the weighted setting, which might be of independent interest. Using this interpretation, we establish the necessary and sufficient conditions under which picking sequence algorithms can guarantee other fairness notions in the weighted setting. We also study the best-of-both-worlds setting and propose a lottery that guarantees ex-ante WEF and ex-post WEF( 1, 1 ). Then we study the existence of fair and efficient allocations and propose efficient algorithms for computing WEF1 and PO allocations for bi-valued instances. Our result generalizes that of Garg et al. (AAAI 2022) and Ebadian et al. (AAMAS 2022) to the weighted setting. Our work also studies the price of fairness for WEF1, and the implications of WEF1 to other fairness notions.

Details DOI

EAAI Journal 2024 Journal Article

CCNet: Collaborative Camouflaged Object Detection via decoder-induced information interaction and supervision refinement network

Cong Zhang
Hongbo Bi
Disen Mo
Weihan Sun
Jinghui Tong
Wei Jin
Yongqiang Sun

Recently, research based on the camouflaged object detection (COD) task has achieved great progress, while the collaborative camouflaged object detection (CoCOD) task is still lacking. Our research focuses on the simultaneous detection and localization of the collaborative camouflaged objects, i. e. , CoCOD task. We use the cooperative information between a single image and a group of camouflage images to discover cooperative camouflaged objects effectively. In this paper, we propose a collaborative cross-scale feature learning network (CCNet). Our model is characterized by two innovative constructions: We proposed an edge augmentation module (EAM), which effectively extracts edge information of the camouflaged object and integrates it with the collaborative information employed in auxiliary supervision. In addition, we design a group decoder module (GDM) to extract and merge co-camouflage information. Extensive experiments on CoCOD8K datasets demonstrate that our CCNet significantly outperforms the existing 13 state-of-the-art COD and 6 state-of-the-art collaborative salient object detection (CoSOD) methods under six widely used evaluation metrics. The code will be available at: https: //github. com/zc199823/CCNet--CoCOD.

Details DOI

ICLR Conference 2024 Conference Paper

Deep Reinforcement Learning Guided Improvement Heuristic for Job Shop Scheduling

Cong Zhang
Zhiguang Cao
Wen Song 0004
Yaoxin Wu
Jie Zhang 0002

Recent studies in using deep reinforcement learning (DRL) to solve Job-shop scheduling problems (JSSP) focus on construction heuristics. However, their performance is still far from optimality, mainly because the underlying graph representation scheme is unsuitable for modelling partial solutions at each construction step. This paper proposes a novel DRL-guided improvement heuristic for solving JSSP, where graph representation is employed to encode complete solutions. We design a Graph-Neural-Network-based representation scheme, consisting of two modules to effectively capture the information of dynamic topology and different types of nodes in graphs encountered during the improvement process. To speed up solution evaluation during improvement, we present a novel message-passing mechanism that can evaluate multiple solutions simultaneously. We prove that the computational complexity of our method scales linearly with problem size. Experiments on classic benchmarks show that the improvement policy learned by our method outperforms state-of-the-art DRL-based methods by a large margin.

Details

UAI Conference 2024 Conference Paper

Learning Topological Representations with Bidirectional Graph Attention Network for Solving Job Shop Scheduling Problem

Cong Zhang
Zhiguang Cao
Yaoxin Wu
Wen Song 0004
Jing Sun

Existing learning-based methods for solving job shop scheduling problems (JSSP) usually use off-the-shelf GNN models tailored to undirected graphs and neglect the rich and meaningful topological structures of disjunctive graphs (DGs). This paper proposes the topology-aware bidirectional graph attention network (TBGAT), a novel GNN architecture based on the attention mechanism, to embed the DG for solving JSSP in a local search framework. Specifically, TBGAT embeds the DG from a forward and a backward view, respectively, where the messages are propagated by following the different topologies of the views and aggregated via graph attention. Then, we propose a novel operator based on the message-passing mechanism to calculate the forward and backward topological sorts of the DG, which are the features for characterizing the topological structures and exploited by our model. In addition, we theoretically and experimentally show that TBGAT has linear computational complexity to the number of jobs and machines, respectively, strengthening our method’s practical value. Besides, extensive experiments on five synthetic datasets and seven classic benchmarks show that TBGAT achieves new SOTA results by outperforming a wide range of neural methods by a large margin. All the code and data are publicly available online at https: //github. com/zcaicaros/TBGAT.

Details

YNIMG Journal 2024 Journal Article

Low-intensity transcranial ultrasound stimulation improves memory in vascular dementia by enhancing neuronal activity and promoting spine formation

Jiamin Pei
Cong Zhang
Xiao Zhang
Zhe Zhao
Xiangjian Zhang
Yi Yuan

Memory is closely associated with neuronal activity and dendritic spine formation. Low-intensity transcranial ultrasound stimulation (TUS) improves the memory of individuals with vascular dementia (VD). However, it is unclear whether neuronal activity and dendritic spine formation under ultrasound stimulation are involved in memory improvement in VD. In this study, we found that seven days of TUS improved memory in VD model while simultaneously increasing pyramidal neuron activity, promoting dendritic spine formation, and reducing dendritic spine elimination. These effects lasted for 7 days but disappeared on 14 d after TUS. Neuronal activity and dendritic spine formation strongly corresponded to improvements in memory behavior over time. In addition, we also found that the memory, neuronal activity and dendritic spine of VD mice cannot be restored again by TUS of 7 days after 28 d. Collectively, these findings suggest that TUS increases neuronal activity and promotes dendritic spine formation and is thus important for improving memory in patients with VD.

Details DOI

YNIMG Journal 2023 Journal Article

Modulation effects of low-intensity transcranial ultrasound stimulation on the neuronal firing activity and synaptic plasticity of mice

Zhe Zhao
Hui Ji
Cong Zhang
Jiamin Pei
Xiangjian Zhang
Yi Yuan

Low-intensity transcranial ultrasound stimulation (TUS) has been effective in modulating several neurological and psychiatric disorders. However, how TUS modulates neuronal firing activity and synaptic plasticity remains unclear. Thus, we behaviorally tested the whisker-dependent novel object discrimination ability in mice after ultrasound stimulation and examined the cortical neuronal firing activity and synaptic plasticity in awake mice after ultrasound stimulation by two-photon fluorescence imaging. The current study presented the following results: (1) TUS could significantly improve the whisker-dependent new object discrimination ability of mice, suggesting that their learning and memory abilities were significantly enhanced; (2) TUS significantly enhanced neuronal firing activity; and (3) TUS increased the growth rate of dendritic spines in the barrel cortex, but did not promote the extinction of dendritic spines, resulting in enhanced synaptic plasticity. The above results indicate that TUS can improve the learning and memory ability of mice and enhance the neuronal firing activity and synaptic plasticity that are closely related to it. This study provides a research basis for the application of ultrasound stimulation in the treatment of learning- and memory-related diseases.

Details DOI

NeurIPS Conference 2020 Conference Paper

Learning to Dispatch for Job Shop Scheduling via Deep Reinforcement Learning

Cong Zhang
Wen Song
Zhiguang Cao
Jie Zhang
Puay Siew Tan
Xu Chi

Priority dispatching rule (PDR) is widely used for solving real-world Job-shop scheduling problem (JSSP). However, the design of effective PDRs is a tedious task, requiring a myriad of specialized knowledge and often delivering limited performance. In this paper, we propose to automatically learn PDRs via an end-to-end deep reinforcement learning agent. We exploit the disjunctive graph representation of JSSP, and propose a Graph Neural Network based scheme to embed the states encountered during solving. The resulting policy network is size-agnostic, effectively enabling generalization on large-scale instances. Experiments show that the agent can learn high-quality PDRs from scratch with elementary raw features, and demonstrates strong performance against the best existing PDRs. The learned policies also perform well on much larger instances that are unseen in training.

PDF Details

ICRA Conference 2017 Conference Paper

Mechanical design of a compact Serial Variable Stiffness Actuator (SVSA) based on lever mechanism

Jiantao Sun
Yubing Zhang
Cong Zhang
Zhao Guo
Xiaohui Xiao

Compliant actuator is widely accepted for physical human-robot interaction due to its safety aspect, dynamic performance improvements and energy saving abilities. In this paper, based on the variable ratio lever mechanism, a new kind of Serial Variable Stiffness Actuator (SVSA) is proposed by using an Archimedean Spiral Relocation Mechanism (ASRM) to change the position of the pivot, implementing large range of adjustable stiffness. The ASRM introduced here makes the SVSA design has continuous stiffness adjustment ability and simply mechanical structure. Within the Variable Stiffness Mechanism (VSM), two linear springs are assembled antagonistically on a spring shaft. Their displacements are perpendicular to the output link to transmit the spring force more efficiently. Stiffness modeling and analysis of the SVSA are carried out to cover large deflection angle. The physical implementation of the SVSA shows that the output stiffness of the VSM is changed from 1. 72 to 150. 56 Nm/rad using a linear spring with stiffness 1882 N/m, working range covered from 0 to 360°. Control experiments also proved the wide range of stiffness adjustment ability of the SVSA.

Details