Yumeng Fu, Weitao Huang, Junjie Wu, Hao Teng, Shouduo Shang, Meishan Zhang, Bingquan Liu. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Emotion Recognition in Conversation (ERC), the task of identifying the emotion of each utterance in a conversation, is crucial for humanmachine interaction.Existing LLM-based ERC methods focus on standard prompting and slow thinking for emotion analysis.However, they suffer from the lack of human-like emotion reasoning and discrimination between similar emotions, thus limiting accurate emotion predictions.To this end, we present JoPR, jointing perception-curriculum learning and emotional reasoning for conversational emotion recognition.Specifically, we devise a multi-dimension curriculum with long CoT fine-tuning to clone human-like emotion reasoning.We further design an emotion-specific reward function in a novel reinforcement learning framework, thereby enhancing the discernment between similar emotions.We conduct extensive experiments on three widely used benchmark datasets, and the results demonstrate that our JoPR achieves consistent and significant improvements over baselines.

Attitude maneuvers of spacecraft inevitably introduce composite disturbances such as center of mass variations, structural flexible vibrations, and actuator uncertainties. These disturbances are strongly coupled with the system's states and control inputs, forming a composite disturbance profile that severely impacts attitude tracking and pointing accuracy. To address this challenge, a maneuvering control scheme based on composite disturbance learning is proposed. First, a deep coupled spacecraft attitude dynamics model is developed to capture the influence and transmission mechanisms of composite disturbances. Then, a composite controller incorporating a disturbance learning observer is designed to perform online modeling and real-time compensation of these disturbances. The effectiveness of the proposed approach is validated through experiment studies.

The safety and high-precision attitude control of launch vehicles are threatened by degradation fault and multiple disturbances (such as model uncertainty, uncertain inertia, and external disturbance) during the reentry stage. To address these challenges, an adaptive sliding mode observer (ASMO)-based composite control scheme is proposed in this article for launch vehicles to achieve simultaneous compensation and suppression of the degradation fault and multiple disturbances. Since the mismatched model uncertainty that coupled with the system state exhibits strong uncertainty, an ASMO is designed to estimate it by adaptively learning the upper bound of the derivative of the mismatched model uncertainty. In order to attenuate the effect of the degradation fault, uncertain inertia, and external disturbance, three adaptive laws are accordingly designed to identify them online. By combining the ASMO and the designed adaptive laws, a composite controller is constructed, and the degradation fault and multiple disturbances are simultaneously compensated and suppressed. The coordinated optimization performance and refinement of antidisturbance control and fault-tolerant control are effectively enhanced. Moreover, by introducing a prescribed performance function, the attitude tracking error response is constrained within a predefined range. Simulation and experiments validate the effectiveness of the proposed scheme.

Due to the harsh environment and energy limitation, maintaining efficient communication is crucial to the lifetime of Underwater Sensor Networks (UWSN). Named Data Networking (NDN), one of future network architectures, begins to be applied to UWSN. Although Underwater Named Data Networking (UNDN) performs well in data transmission, it still faces some security threats, such as the Denial-of-Service (DoS) attacks caused by Interest Flooding Attacks (IFAs). In this paper, we present a new type of DoS attacks, named as Synergetic Denial-of-Service (SDoS). Attackers synergize with each other, taking turns to reply to malicious interests as late as possible. SDoS attacks will damage the Pending Interest Table, Content Store, and Forwarding Information Base in routers with high concealment. Simulation results demonstrate that the SDoS attacks quadruple the increased network traffic compared with normal IFAs and the existing IFA detection algorithm in UNDN is completely invalid to SDoS attacks. In addition, we analyze the infection problem in UNDN and propose a defense method Trident based on carefully designed adaptive threshold, burst traffic detection, and attacker identification. Experiment results illustrate that Trident can effectively detect and resist both SDoS attacks and normal IFAs. Meanwhile, Trident can robustly undertake burst traffic and congestion.