Interlingual subtitling, which translates subtitles of visual media into a target language, is essential for entertainment localization but has not yet been explored in machine translation. Although Large Language Models (LLMs) have significantly advanced the general capabilities of machine translation, the distinctive characteristics of subtitle texts pose persistent challenges in interlingual subtitling, particularly regarding semantic coherence, pronoun and terminology translation, and translation expressiveness. To address these issues, we present Hermes, an LLM-based automated subtitling framework. Hermes integrates three modules: Speaker Diarization, Terminology Identification, and Expressiveness Enhancement, which effectively tackle the above challenges. Experiments demonstrate that Hermes achieves state-of-the-art diarization performance and generates expressive, contextually coherent translations, thereby advancing research in interlingual subtitling.

Chaoqun Cui, Liangbin Huang, Shijing Wang, Zhe Tong, Zhaolong Huang, Xiao Zeng, Xiaofeng Liu. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

Ultra-Dense Network (UDN) is foreseen as one of the promising technologies in 5G to meet the ever-increasing mobile traffic demands. However, with existing cell discovery mechanisms, such massive deployment of access points (APs) would lead to a considerable increase in energy consumption and a significant reduction in offloading opportunity. To solve those problems, a User Location Prediction based Cell Discovery (ULPCD) scheme for User-centric Ultra-Dense Network (UUDN) is proposed. In the scheme, the network deployment information is sent to the user equipment (UE) the first time user enters in the range of cells. Then, with the aid of positioning information, the probability of a user entering into a new cell is calculated. Using the probability, UE can predict whether to send a connection request to activate an idle AP before entering in the AP's cell range. Simulation results demonstrate that our proposed scheme reduces over 60% energy consumption of UE and saves at least 20% working time of APs compared with state-of-the-art schemes. Meanwhile, our scheme provides higher detection probability, shorter access delay, and more offloading opportunity.

Due to the flexible deployment, in-band wireless backhaul solutions are preferred to the small cells in the ultradense networks (UDN). This paper manages the scheduling issues of in-band wireless backhaul in UDN by jointly considering the effect of access-backhaul link constraint, the interference and the minimum user data rate requirement. The scheduling problem that aims at maximizing the system throughput is formulated, whose solution is NP-hard. To reduce the calculation complexity and obtain a practical scheduling solution, A scheme named as coloring based access-backhaul scheduling (CBABS) is proposed. In CBABS, the minimum data rate requirements are satisfied by a QoS guarantee algorithm, the interference is managed by coloring algorithm (CA), the matching is done by ensuring the same data rate on access and backhaul link. Simulation results show that 98% of users' minimum downlink data rate requirements and 99% of users' minimum uplink data rate requirements are satisfied. The RB utility ratio is improved by 30% in CBABS compared to traditional scheduling scheme.