Zhengyi Zhao, Shubo Zhang, Yiming Du, Bin Liang, Baojun Wang, Zhongyang Li, Binyang Li, Kam-Fai Wong. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Zhengyi Zhao, Shubo Zhang, Zezhong Wang, Yuxi Zhang, Huimin Wang, Yutian Zhao, Yefeng Zheng, Binyang Li, Kam-Fai Wong, Xian Wu. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Abstract Large Reasoning Models (LRMs) have demonstrated impressive capabilities in many tasks, yet they struggle with reliably following multiple instructions, either by failing to satisfy individual constraints or by struggling to balance competing constraints simultaneously. We formalize this challenge as the Constraint Adherence Problem (CAP). This paper introduces a novel framework that addresses CAP by representing instructions as a structured knowledge graph of constraints. Our approach, Constraint Relationship Graph Completion (CRGC), explicitly models relationships between constraints, identifies adherence challenges, and discovers “bridge constraints” that help the model better focus on and reconcile requirements. Bridge constraints act as auxiliary instructions that make primary constraints more salient and compatible. Unlike existing approaches that enhance instruction following through general training methods, CRGC specifically improves constraint satisfaction by leveraging the model’s own knowledge to create better pathways for generation. Experiments across three popular instruction following datasets demonstrate that our approach reduces constraint violations by 39% compared to standard prompting while maintaining reasoning abilities of large reasoning models.

Zhengyi Zhao, Shubo Zhang, Zezhong Wang, Huimin Wang, Yutian Zhao, Bin Liang, Yefeng Zheng, Binyang Li, Kam-Fai Wong, Xian Wu. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.

Zhengyi Zhao, Shubo Zhang, Yuxi Zhang, Yanxi Zhao, Yifan Zhang, Zezhong Wang, Huimin Wang, Yutian Zhao, Bin Liang, Yefeng Zheng, Binyang Li, Kam-Fai Wong, Xian Wu. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.

Network entities have important asset mapping, vulnerability, and service delivery applications. In cyberspace, where the network structure is complex and the number of entities is large, effectively obtaining the relevant attributes of entities is a difficult task. Graph neural network-based approaches focus on target IP node messaging from neighboring nodes; however, the graph learning task ignores the heterophilous relationship of network entity identification (NEI) tasks in the graph structure and fails to effectively message from non-neighboring nodes. To address the limitations of the existing task, we propose a NEI model based on heterophilous graph learning (HpGraphNEI); HpGraphNEI converts heterophilous graphs under the NEI task into homophilous graphs and uses the graph learning mechanism to carry out attribute completion task for incomplete entity attributes. First, the acquired dataset is feature-extracted by network measurement, and the clustering algorithm is employed to divide the target nodes into communities. Second, the network topology graph is constructed to embed the node attribute information and neighborhood structure information into the graph in the form of feature vectors. Then, the global attention in the community is calculated according to the attention results, the edges with strong correlation in the network are filtered, the adjacency matrix is reconstructed, and then the updated node information is aggregated to complete the incomplete attribute completion. Fourth, the updated nodes are categorized to output network entity categories and construct network entity portraits based on the attribute completion nodes. We conducted a 2-month data collection in three real regions and successfully identified 6 types of network entities. Compared with the optimal baseline, all the metrics have significantly improved, with NEI accuracy above 93.74% and up to 96.28%, improved 2.27% to 2.69%.

Wireless sensor network (WSN) is communicating method with each other without the assistance of communication cable. The circular environment is an important application scenario in WSN. As a core technology, routing algorithm is the brain of WSN monitoring system. In this paper, we propose a new routing algorithm named Equal Area Partition Based Energy Efficient Multipath Algorithm (EAPEEM), which tries to exploit sector equal area model in node deployment, data transfer, and route maintenance. Existing algorithms, as compared to our existing models, do not fully match with routing and nodes. One attractive feature of our protocol is its balanced network transmission capacity and improved node energy utilization, which can reduce the possibility of system damage. Simulations show that EAPEEM can retain at least 28.6% of batteries and expand stability by more than 43%.

Due to the lightweight and flexible characteristics, containers have gradually been used for the application deployment and the basic unit for resource allocation in a cloud platform recently. Reinforcement learning (RL), as a classic algorithm, is widely used in virtual machine scheduling scenarios due to its advantages of adaptability and robustness. However, most RL methods have problems in container scheduling, such as untimely scheduling, lack of accuracy in decision-making and poor dynamics that will lead to a higher SLA violation rate. In order to solve the above problems, a predictive RL algorithm A-SARSA is proposed, which combines the ARIMA model and the neural network model. This algorithm not only ensures the predictability and accuracy of the scaling strategy, but also enables the scaling decisions to adapt to the changing workloads. Through a large number of experiments, the timeliness and effectiveness of the A-SARSA algorithm for container scheduling are verified, which can reduce the SLA violation rate dramatically while keeping the resource utilization rate at a good level.

For smartphone service providers, it is of vital importance to recognize characteristics of customers. The process of recognizing these characteristics is generally referred to as user profile, which provides knowledge basis for business decisions, enables intelligent services, and brings unique competitiveness. As a basic component of user profile, bedtime could reflect lifestyle, health condition, and occupation of people. This paper presents a flexible algorithm named BTP (Bedtime Prediction), which is designed for predicting wake time and bedtime by analysing screen status of smartphone. BTP first collects screen status log data of user’s smartphone and conducts preprocessing with a series of auxiliary user profiles. Then, it detects and records users’ wake time and bedtime of one day by searching and combining major screen extinguish periods in the past 24 hours. Finally, BTP predicts future bedtime by matching current screen status sequence with all historical records. By applying BTP, most of night and morning scenario‐based applications could provide more considerate services, rather than following fixed execution time like alarm clock. Experiments on practical applications prove that BTP can effectively predict wake time and bedtime without applying complicated machine learning algorithms or uploading data to server.