TWTingting Wu

Tingting Wu

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Tingting Wu has a total of 30 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Auditing Data Provenance in LLM Fine-tuning via Intrinsic Distributional Fingerprints

    by Zirui Huang, Yunlong Mao, Wei Tong, Tingting Wu, Xin Ge, Sheng Zhong

  • Open Access

    A general learning rate improvement strategy for deep neural networks training

    by Tingting Wu, Qingwei Dong, Wei Yu, Zheng Li, Manxue Guo


  • Recursive Offloading for LLM Serving in Multi-Tier Networks

    by Zhiyuan Wu, Sheng Sun, Yuwei Wang, Min Liu, Bo Gao, Jinda Lu, Tingting Wu, Zheming Yang, Tian Wen

    Heterogeneous device-edge-cloud computing infrastructures have become the backbone of modern telecommunication operators and Wide Area Networks (WANs), providing multi-tier computational support for emerging intelligent applications. With the rapid proliferation of Large Language Model (LLM) services, efficiently coordinating inference tasks and reducing communication burden within these multi-tier network architectures becomes a critical deployment challenge. Current LLM serving paradigms exhibit significant limitations: on-device deployment restricts service to lightweight LLMs due to hardware constraints, while cloud-centric deployment encounters resource congestion and considerable prompt communication overhead during peak periods. Model-cascading inference, though better suited for multi-tier networks, depends on static, manually-tuned thresholds that cannot adapt to dynamic network conditions or varying task complexities. To address these challenges, we propose RecServe, a recursive offloading framework tailored for LLM serving in multi-tier networks. RecServe introduces a task-specific hierarchical confidence evaluation mechanism that guides offloading decisions based on inferred task complexity in progressively scaled LLMs across device, edge, and cloud tiers. To further enable intelligent task routing across tiers, RecServe employs a sliding-window-based dynamic offloading strategy with quantile interpolation, enabling real-time tracking of historical confidence distributions and adaptive offloading threshold adjustments. This design allows inference tasks to be recursively offloaded to higher tiers only when necessary, optimizing heterogeneous resource utilization while reducing cross-tier communication with little compromise on service quality. Theoretical analysis provides distinct conditions under which RecServe is expected to achieve reduced communication burden and computational costs. Experiments on eight datasets demonstrate that RecServe outperforms CasServe in both service quality and communication efficiency, and reduces the communication burden by over 50% compared to centralized cloud-based serving.


  • Enhancing Robot Learning Through Cognitive Reasoning Trajectory Optimization Under Unknown Dynamics

    by Qingwei Dong, Tingting Wu, Peng Zeng, Chuanzhi Zang, Guangxi Wan, Shijie Cui

    In the domain of robot learning, equipping robots with the capability to swiftly acquire operational skills poses a significant challenge. Currently, reinforcement learning techniques are adept at addressing dynamic, unstructured problems involving rich contact scenarios. However, the convergence rate of these algorithms is often slow due to the high dimensionality of the robot state-action mapping space and the extensive initial policy search space. Meanwhile, advancements in large language models (LLMs) have endowed these models with a degree of logical reasoning ability, enabling them to take goal-oriented actions proactively during the initial phase of a robotic task. These models can implicitly generate features of states and uncover underlying patterns in trajectory generation. Yet, in complex manipulative tasks involving rich contact scenarios, LLMs still fall short. Thus, integrating the robust interactive capabilities of reinforcement learning with the strong logical reasoning of LLMs, and enhancing policy search with LLMs, could potentially accelerate the speed of policy searches significantly. In this paper, we introduce a Cognitive Reasoning Trajectory Optimization method. This approach utilizes Low-level Cognitive Control Tuning to enable LLMs with robust logical reasoning to make effective single-step decisions in Markov Decision Process (MDP) tasks. By fitting dynamic models with high-quality cognitive reasoning data and optimizing control strategies, this method constrains the policy search space and enhances the efficiency of trajectory optimization. Experimental results on various manipulative tasks using the Sawyer robot in the Mujoco simulator validate the effectiveness of the proposed algorithm.


  • Open Access

    Cloud–Edge Collaborative Strategy for Insulator Recognition and Defect Detection Model Using Drone-Captured Images

    by Pengpei Gao, Tingting Wu, Chunhe Song

    In modern power systems, drones are increasingly being utilized to monitor the condition of critical power equipment. However, limited computing capacity is a key factor limiting the application of drones. To optimize the computational load on drones, this paper proposes a cloud–edge collaborative intelligence strategy to be applied to insulator identification and defect detection scenarios. Firstly, a low-computation method deployed at the edge is proposed for determing whether insulator strings are present in the captured images. Secondly, an efficient insulator recognition and defect detection method, I-YOLO (Insulator-YOLO), is proposed for cloud deployment. In the neck network, we integrate an I-ECA (Insulator-Enhanced Channel Attention) mechanism based on insulator characteristics to more comprehensively fuse features. In addition, we incorporated the insulator feature cross fusion network (I-FCFN) to enhance the detection of small-sized insulator defects. Experimental results demonstrate that the cloud–edge collaborative intelligence strategy performs exceptionally well in insulator-related tasks. The edge algorithm achieved an accuracy of 97.9% with only 0.7 G FLOPs, meeting the inspection requirements of drones. Meanwhile, the cloud model achieved a mAP50 of 96.2%, accurately detecting insulators and their defects.


  • Resource-Aware Personalized Federated Learning Based on Reinforcement Learning

    by Tingting Wu, Xiao Li, Pengpei Gao, Wei Yu, Lun Xin, Manxue Guo

    Federated learning is an effective solution to protect data privacy, but the efficiency and performance of the entire federated system are challenging to balance due to the heterogeneity of client resources and data. To alleviate this dilemma, we propose a new training intensity allocation framework based on model structure. First, we design an optimization model that considers both time and energy consumption constraints, minimizing energy consumption under time constraints and accelerating the convergence of federated training. Then we construct a reinforcement learning-based model allocation strategy for realistic dynamic environments, automatically allocating appropriate model sizes to clients under complex communication conditions and heterogeneous computing resources. Finally, a large number of experiments demonstrate the feasibility and effectiveness of the proposed framework.