Multilingual sentence encoders (MSEs) are commonly obtained by training multilingual language models to map sentences from different languages into a shared semantic space.As such, they are subject to curse of multilinguality, a loss of monolingual representational accuracy due to parameter sharing.Another limitation of MSEs is the trade-off between different task performance: cross-lingual alignment training distorts the optimal monolingual structure of semantic spaces of individual languages, harming the utility of sentence embeddings in monolingual tasks; cross-lingual tasks, such as cross-lingual semantic similarity and zero-shot transfer for sentence classification, may also require conflicting cross-lingual alignment strategies.In this work, we address both issues by means of modular training of sentence encoders.We first train language-specific monolingual modules to mitigate negative interference between languages (i.e., the curse).We then align all non-English sentence embeddings to the English by training cross-lingual alignment adapters, preventing interference with monolingual specialization from the first step.We train the cross-lingual adapters with two different types of data to resolve the conflicting requirements of different cross-lingual tasks.Monolingual and cross-lingual results on semantic text similarity and relatedness, bitext mining and sentence classification show that our modular solution achieves better and more balanced performance across all the tasks compared to full-parameter training of monolithic multilingual sentence encoders, especially benefiting low-resource languages.1

We introduce NotaGen, a symbolic music generation model aiming to explore the potential of producing high-quality classical sheet music. Inspired by the success of Large Language Models (LLMs), NotaGen adopts pre-training, fine-tuning, and reinforcement learning paradigms (henceforth referred to as the LLM training paradigms). It is pre-trained on 1.6M pieces of music in ABC notation, and then fine-tuned on approximately 9K high-quality classical compositions conditioned on "period-composer-instrumentation" prompts. For reinforcement learning, we propose the CLaMP-DPO method, which further enhances generation quality and controllability without requiring human annotations or predefined rewards. Our experiments demonstrate the efficacy of CLaMP-DPO in symbolic music generation models with different architectures and encoding schemes. Furthermore, subjective A/B tests show that NotaGen outperforms baseline models against human compositions, greatly advancing musical aesthetics in symbolic music generation.

Recent work has found that few-shot sentence classification based on pre-trained Sentence Encoders (SEs) is efficient, robust, and effective.In this work, we investigate strategies for domain-specialization in the context of fewshot sentence classification with SEs.We first establish that unsupervised Domain-Adaptive Pre-Training (DAPT) of a base Pre-trained Language Model (PLM) (i.e., not an SE) substantially improves the accuracy of few-shot sentence classification by up to 8.4 points.However, applying DAPT on SEs, on the one hand, disrupts the effects of their (general-domain) Sentence Embedding Pre-Training (SEPT).On the other hand, applying general-domain SEPT on top of a domain-adapted base PLM (i.e., after DAPT) is effective but inefficient, since the computationally expensive SEPT needs to be executed on top of a DAPT-ed PLM of each domain.As a solution, we propose AdaSent, which decouples SEPT from DAPT by training a SEPT adapter on the base PLM.The adapter can be inserted into DAPT-ed PLMs from any domain.We demonstrate AdaSent's effectiveness in extensive experiments on 17 different few-shot sentence classification datasets.AdaSent matches or surpasses the performance of full SEPT on DAPT-ed PLM, while substantially reducing the training costs.The code for AdaSent is available 1 .

In this paper, a two-dimensional weighted fractional Fourier transform (2DWFRFT) based secure spatial modulation (SM) scheme is proposed to enhance the physical layer security (PLS) of the wireless communication system. In the proposed scheme, 2DWFRFT is implemented as the security kernel for PLS provision. The invertibility and uniqueness of the 2DWFRFT effectively protect the confidential messages from being intercepted by the eavesdroppers while imposing no performance degradation on the legitimate receiver. Both the signal generation strategy and the ergodic secrecy rate analysis under discrete-input continuous-output memoryless (DCMC) channel have been elaborated to depict the security mechanism of the proposed scheme. The maximum likelihood (ML) detector and the separate detection (SD) algorithm are formulated to correctly recover the received signal of our system. Simulation results demonstrate that the proposed scheme can achieve a much higher secrecy capacity than artificial noise schemes without requiring additional jamming power consumption.