Related papers: On Text Style Transfer via Style Masked Language M…

Text-style transfer aims to convert text given in one domain into another by paraphrasing the sentence or substituting the keywords without altering the content. By necessity, state-of-the-art methods have evolved to accommodate nonparallel…

We introduce DRESS, a novel approach for generating stylized large language model (LLM) responses through representation editing. Existing methods like prompting and fine-tuning are either insufficient for complex style adaptation or…

Large Language Models (LLMs) have showcased impressive capabilities in text comprehension and generation, prompting research efforts towards video LLMs to facilitate human-AI interaction at the video level. However, how to effectively…

Multimodal Large Language Models (MLLMs) have achieved notable success in enhancing translation performance by integrating multimodal information. However, existing research primarily focuses on image-guided methods, whose applicability is…

Streaming speech translation (StreamST) requires determining appropriate timing, known as policy, to generate translations while continuously receiving source speech inputs, balancing low latency with high translation quality. However,…

In spoken dialogue, even if two current turns are the same sentence, their responses might still differ when they are spoken in different styles. The spoken styles, containing paralinguistic and prosodic information, mark the most…

Equipping a conversational search engine with strategies regarding when to ask clarification questions is becoming increasingly important across various domains. Attributing to the context understanding capability of LLMs and their access…

Specialized reasoning language models (RLMs) have demonstrated that scaling test-time computation through detailed reasoning traces significantly enhances performance. Although these traces effectively facilitate knowledge distillation into…

Simultaneous machine translation (SMT) takes streaming input utterances and incrementally produces target text. Existing SMT methods mainly use the partial utterance that has already arrived at the input and the generated hypothesis.…

Speech-aware language models (LMs) have demonstrated capabilities in understanding spoken language while generating text-based responses. However, enabling them to produce speech output efficiently and effectively remains a challenge. In…

Conventional spoken language translation (SLT) systems are pipeline based systems, where we have an Automatic Speech Recognition (ASR) system to convert the modality of source from speech to text and a Machine Translation (MT) systems to…

Speech-to-speech translation (S2ST) aims to convert spoken input in one language to spoken output in another, typically focusing on either language translation or accent adaptation. However, effective cross-cultural communication requires…

Machine Translation is one of the major oldest and the most active research area in Natural Language Processing. Currently, Statistical Machine Translation (SMT) dominates the Machine Translation research. Statistical Machine Translation is…

Text-guided molecule generation is a task where molecules are generated to match specific textual descriptions. Recently, most existing SMILES-based molecule generation methods rely on an autoregressive architecture. In this work, we…

Perfect machine translation (MT) would render cross-lingual transfer (XLT) by means of multilingual language models (mLMs) superfluous. Given, on the one hand, the large body of work on improving XLT with mLMs and, on the other hand, recent…

Recent advancement of large language models (LLMs) has led to significant breakthroughs across various tasks, laying the foundation for the development of LLM-based speech translation systems. Existing methods primarily focus on aligning…

We present a joint Speech and Language Model (SLM), a multitask, multilingual, and dual-modal model that takes advantage of pretrained foundational speech and language models. SLM freezes the pretrained foundation models to maximally…

The rapid development of large-scale text-to-speech (TTS) models has led to significant advancements in modeling diverse speaker prosody and voices. However, these models often face issues such as slow inference speeds, reliance on complex…

Source code can be parsed into the abstract syntax tree (AST) based on defined syntax rules. However, in pre-training, little work has considered the incorporation of tree structure into the learning process. In this paper, we present…

Large language models (LLMs) are pretrained on corpora containing trillions of tokens and, therefore, inevitably memorize sensitive information. Locate-then-edit methods, as a mainstream paradigm of model editing, offer a promising solution…