Nuo Li
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
Nuo Li has a total of 46 co-authors. Here are the top co-authors by number of shared publications:
- Bin Guo
Northwestern Polytechnical University
11 shared publications - Zhiwen Yu
Harbin Engineering University
11 shared publications - Yan Liu
Northwestern Polytechnical University
7 shared publications - Ning Gu
Fudan University, Shanghai, China
5 shared publications - Peng Zhang
Fudan University, Shanghai, China
5 shared publications - Tun Lu
Fudan University, Shanghai, China
5 shared publications
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 8451-8460
GazePruning: Gaze-Guided Token Pruning for LVLMs in Virtual Reality
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 8451-8460
Open AccessGazePruning: Gaze-Guided Token Pruning for LVLMs in Virtual Reality
- Open Access
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-23
Echoes of Norms: Investigating Counterspeech Bots’ Influence on Bystanders in Online Communities
Counterspeech offers a non-repressive approach to moderate hate speech in online communities. Research has examined how counterspeech chatbots restrain hate speakers and support targets, but their impact on bystanders remains unclear. Therefore, we developed a counterspeech strategy framework and built Civilbot for a mixed-method within-subjects study. Bystanders generally viewed Civilbot as credible and normative, though its shallow reasoning limited persuasiveness. Its behavioural effects were subtle: when performing well, it could guide participation or act as a stand-in; when performing poorly, it could discourage bystanders or motivate them to step in. Strategy proved critical: cognitive strategies that appeal to reason, especially when paired with a positive tone, were relatively effective, while mismatch of contexts and strategies could weaken impact. Based on these findings, we offer design insights for mobilizing bystanders and shaping online discourse, highlighting when to intervene and how to do so through reasoning-driven and context-aware strategies.
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-23
Open AccessEchoes of Norms: Investigating Counterspeech Bots’ Influence on Bystanders in Online Communities
Counterspeech offers a non-repressive approach to moderate hate speech in online communities. Research has examined how counterspeech chatbots restrain hate speakers and support targets, but their impact on bystanders remains unclear. Therefore, we developed a counterspeech strategy framework and built Civilbot for a mixed-method within-subjects study. Bystanders generally viewed Civilbot as credible and normative, though its shallow reasoning limited persuasiveness. Its behavioural effects were subtle: when performing well, it could guide participation or act as a stand-in; when performing poorly, it could discourage bystanders or motivate them to step in. Strategy proved critical: cognitive strategies that appeal to reason, especially when paired with a positive tone, were relatively effective, while mismatch of contexts and strategies could weaken impact. Based on these findings, we offer design insights for mobilizing bystanders and shaping online discourse, highlighting when to intervene and how to do so through reasoning-driven and context-aware strategies.
- 14 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Consumer Electronics
- Vol. PP (00983063) , 1
GroupTransfer: User Group Transferability Metric driven by Social Identity Theory
Effective knowledge transfer from source to target users is essential for enhancing prediction performance in data-sparse scenarios, particularly in consumer electronics applications such as personalized recommendations and health monitoring. However, existing approaches often suffer from excessive complexity and lack theoretical grounding, resulting in inefficiency and negative transfer. While some transferability metrics consider the relationship between source and target users, they fail to account for interactions within the source user group, limiting their ability to assess group-level transferability accurately. To address these limitations, this paper introduces GroupTrans, a novel transferability metric grounded in social identity theory, that simultaneously captures source-target relevance and intragroup interactions through dual modeling of consistency and diversity. Additionally, we introduce a similarity-guided incremental search algorithm to identify an optimal source user set, alleviating knowledge redundancy and enhancing transfer performance. Extensive experiments on both sparse and dense datasets demonstrate that GroupTrans effectively captures group dynamics and outperforms existing methods. The strong theoretical foundation and practical effectiveness of this framework have successfully addressed key challenges in personalized service applications, making it particularly valuable for data-sparse consumer electronics systems.
- 14 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Consumer Electronics
- Vol. PP (00983063) , 1
GroupTransfer: User Group Transferability Metric driven by Social Identity Theory
Effective knowledge transfer from source to target users is essential for enhancing prediction performance in data-sparse scenarios, particularly in consumer electronics applications such as personalized recommendations and health monitoring. However, existing approaches often suffer from excessive complexity and lack theoretical grounding, resulting in inefficiency and negative transfer. While some transferability metrics consider the relationship between source and target users, they fail to account for interactions within the source user group, limiting their ability to assess group-level transferability accurately. To address these limitations, this paper introduces GroupTrans, a novel transferability metric grounded in social identity theory, that simultaneously captures source-target relevance and intragroup interactions through dual modeling of consistency and diversity. Additionally, we introduce a similarity-guided incremental search algorithm to identify an optimal source user set, alleviating knowledge redundancy and enhancing transfer performance. Extensive experiments on both sparse and dense datasets demonstrate that GroupTrans effectively captures group dynamics and outperforms existing methods. The strong theoretical foundation and practical effectiveness of this framework have successfully addressed key challenges in personalized service applications, making it particularly valuable for data-sparse consumer electronics systems.
- 29 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Services Computing
- Vol. 18 (6) , 3609-3622
Cross-F$^{2}$SCIL: A Federated Few-Shot Class Incremental Learning Method for Cross Mobile Edge Network Environments
Edge Federated Learning (EFL) has demonstrated significant potential in the field of Artificial Intelligence of Things (AIoT) by protecting data privacy and reducing communication costs. However, in real-world scenarios, multiple independent edge networks seldom collaborate due to factors such as data heterogeneity and the absence of a central server. Mobile devices, acting as bridges across different environments, offer an opportunity to enable dynamic collaboration among multiple edge networks. Nevertheless, as mobile devices transition between edge networks, they may encounter new classes with only a few samples, leading to catastrophic forgetting of previous knowledge and overfitting in new environments. To address this challenge, we propose Cross-F $^{2}$ SCIL, a Federated Few-Shot Class Incremental Learning method that enables on-demand dynamic collaboration in mobile edge network environments. Cross-F $^{2}$ SCIL allows mobile devices to efficiently learn new class knowledge from few-shot samples upon entering new edge networks while consolidating prior knowledge to prevent forgetting. Specifically, to mitigate the forgetting caused by new class overwriting on devices and parameter dilution at the server, we design a two-phase training framework. In the first phase, we learn a local model using Prototype Augmentation to enhance the retention of prior knowledge. In the second phase, we obtain the global model via Hierarchical Personalized Parameter Aggregation to effectively integrate learned knowledge across devices. To effectively learn new class information while reducing overfitting, we incorporate Self-Supervised Knowledge Aggregation and Prototype Knowledge Fusion to enhance model generalization and seamlessly integrate new classes into the existing model. Compared to the best-performing baseline on each dataset, Cross-F $^{2}$ SCIL achieves an average improvement of 5.52% in Average Accuracy across five datasets, with the maximum improvement reaching 7.97%.
- 29 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Services Computing
- Vol. 18 (6) , 3609-3622
Cross-F$^{2}$SCIL: A Federated Few-Shot Class Incremental Learning Method for Cross Mobile Edge Network Environments
Edge Federated Learning (EFL) has demonstrated significant potential in the field of Artificial Intelligence of Things (AIoT) by protecting data privacy and reducing communication costs. However, in real-world scenarios, multiple independent edge networks seldom collaborate due to factors such as data heterogeneity and the absence of a central server. Mobile devices, acting as bridges across different environments, offer an opportunity to enable dynamic collaboration among multiple edge networks. Nevertheless, as mobile devices transition between edge networks, they may encounter new classes with only a few samples, leading to catastrophic forgetting of previous knowledge and overfitting in new environments. To address this challenge, we propose Cross-F $^{2}$ SCIL, a Federated Few-Shot Class Incremental Learning method that enables on-demand dynamic collaboration in mobile edge network environments. Cross-F $^{2}$ SCIL allows mobile devices to efficiently learn new class knowledge from few-shot samples upon entering new edge networks while consolidating prior knowledge to prevent forgetting. Specifically, to mitigate the forgetting caused by new class overwriting on devices and parameter dilution at the server, we design a two-phase training framework. In the first phase, we learn a local model using Prototype Augmentation to enhance the retention of prior knowledge. In the second phase, we obtain the global model via Hierarchical Personalized Parameter Aggregation to effectively integrate learned knowledge across devices. To effectively learn new class information while reducing overfitting, we incorporate Self-Supervised Knowledge Aggregation and Prototype Knowledge Fusion to enhance model generalization and seamlessly integrate new classes into the existing model. Compared to the best-performing baseline on each dataset, Cross-F $^{2}$ SCIL achieves an average improvement of 5.52% in Average Accuracy across five datasets, with the maximum improvement reaching 7.97%.
- Open Access
- 1 September 2025
- Published by International Joint Conferences on Artificial Intelligence
- Vol. 10, 8705-8713
Tree-of-AdEditor: Heuristic Tree Reasoning for Automated Video Advertisement Editing with Large Language Model
Video advertising has become a popular marketing strategy on e-commerce platforms, requiring high-level semantic reasoning like selling point discovery, narrative organization. Previous rule-based methods struggle with these complex tasks, and learning-based approaches demand large datasets and high training costs. Recently, Large Language Models have opened incredible opportunities for advancing intelligent video advertisement editing. However, Input-output (IO) prompting and Chain-of-Thought (CoT) struggle to adapt to the nonlinear thinking hierarchy of video editing, where editors iteratively select shots or revert them to explore potential editing solutions. While Tree-of-Thought (ToT) offers a conceptual structure that mirrors this hierarchy, it falls short in aligning with effective video advertising strategies and lacks robust fact-checking mechanisms. To address these, we propose a novel framework, Tree-of-AdEditor (ToAE), which constructs a reasoning tree to mimic human editors, and incorporates domain-specific theories and heuristic fact-checking to identify optimal editing solutions. Specifically, motivated by effective advertisement principles, we develop a "local-global" mechanism to guide LLM in both the shot level and sequence level decision-making. We introduce a visual incoherence pruning module to provide external heuristic fact-checking, ensuring visual attractiveness and reducing computation costs. Quantitative experiments and expert evaluation demonstrate the superiority of our method compared to baselines.
- 1 September 2025
- Published by International Joint Conferences on Artificial Intelligence
- Vol. 10, 8705-8713
Open AccessTree-of-AdEditor: Heuristic Tree Reasoning for Automated Video Advertisement Editing with Large Language Model
Video advertising has become a popular marketing strategy on e-commerce platforms, requiring high-level semantic reasoning like selling point discovery, narrative organization. Previous rule-based methods struggle with these complex tasks, and learning-based approaches demand large datasets and high training costs. Recently, Large Language Models have opened incredible opportunities for advancing intelligent video advertisement editing. However, Input-output (IO) prompting and Chain-of-Thought (CoT) struggle to adapt to the nonlinear thinking hierarchy of video editing, where editors iteratively select shots or revert them to explore potential editing solutions. While Tree-of-Thought (ToT) offers a conceptual structure that mirrors this hierarchy, it falls short in aligning with effective video advertising strategies and lacks robust fact-checking mechanisms. To address these, we propose a novel framework, Tree-of-AdEditor (ToAE), which constructs a reasoning tree to mimic human editors, and incorporates domain-specific theories and heuristic fact-checking to identify optimal editing solutions. Specifically, motivated by effective advertisement principles, we develop a "local-global" mechanism to guide LLM in both the shot level and sequence level decision-making. We introduce a visual incoherence pruning module to provide external heuristic fact-checking, ensuring visual attractiveness and reducing computation costs. Quantitative experiments and expert evaluation demonstrate the superiority of our method compared to baselines.
- 23 June 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 293
Federated multi-agent reinforcement learning: A comprehensive survey of methods, applications and challenges
- 23 June 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 293
Federated multi-agent reinforcement learning: A comprehensive survey of methods, applications and challenges
- Open Access
Adaptive Human-Agent Teaming: A Review of Empirical Studies from the Process Dynamics Perspective
The rapid advancement of AI, including Large Language Models, has propelled autonomous agents forward, accelerating the human-agent teaming (HAT) paradigm to leverage complementary strengths. However, HAT research remains fragmented, often focusing on isolated team development phases or specific challenges like trust calibration while overlooking the real-world need for adaptability. Addressing these gaps, a process dynamics perspective is adopted to systematically review HAT using the T$^4$ framework: Team Formation, Task and Role Development, Team Development, and Team Improvement. Each phase is examined in terms of its goals, actions, and evaluation metrics, emphasizing the co-evolution of task and team dynamics. Special focus is given to the second and third phases, highlighting key factors such as team roles, shared mental model, and backup behaviors. This holistic perspective identifies future research directions for advancing long-term adaptive HAT.
Open AccessAdaptive Human-Agent Teaming: A Review of Empirical Studies from the Process Dynamics Perspective
The rapid advancement of AI, including Large Language Models, has propelled autonomous agents forward, accelerating the human-agent teaming (HAT) paradigm to leverage complementary strengths. However, HAT research remains fragmented, often focusing on isolated team development phases or specific challenges like trust calibration while overlooking the real-world need for adaptability. Addressing these gaps, a process dynamics perspective is adopted to systematically review HAT using the T$^4$ framework: Team Formation, Task and Role Development, Team Development, and Team Improvement. Each phase is examined in terms of its goals, actions, and evaluation metrics, emphasizing the co-evolution of task and team dynamics. Special focus is given to the second and third phases, highlighting key factors such as team roles, shared mental model, and backup behaviors. This holistic perspective identifies future research directions for advancing long-term adaptive HAT.
- 23 January 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 270
A label knowledge graph powered multi-task framework for crowdsourcing and mobile crowd sensing tasks
- 23 January 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 270
A label knowledge graph powered multi-task framework for crowdsourcing and mobile crowd sensing tasks
- 25 November 2024
- Published by Elsevier in Expert Systems with Applications
- Vol. 264
Scalable order dispatching through Federated Multi-Agent Deep Reinforcement Learning
- 25 November 2024
- Published by Elsevier in Expert Systems with Applications
- Vol. 264
Scalable order dispatching through Federated Multi-Agent Deep Reinforcement Learning