Related papers: Distilling Text Style Transfer With Self-Explanati…

Knowledge distillation, the technique of transferring knowledge from large, complex models to smaller ones, marks a pivotal step towards efficient AI deployment. Distilling Step-by-Step~(DSS), a novel method utilizing chain-of-thought~(CoT)…

Computational stylometry studies writing style through quantitative textual patterns, enabling applications such as authorship attribution, identity linking, and plagiarism detection. Existing supervised and contrastive approaches often…

Standard Knowledge Distillation (KD) compresses Large Language Models (LLMs) by optimizing final outputs, yet it typically treats the teacher's intermediate layer's thought process as a black box. While feature-based distillation attempts…

Distilling large language models (LLMs) typically involves transferring the teacher model's responses through supervised fine-tuning (SFT). However, this approach neglects the potential to distill both data (output content) and reward…

Software version migration and program translation are an important and costly part of the lifecycle of large codebases. Traditional machine translation relies on parallel corpora for supervised translation, which is not feasible for…

While explicit Chain-of-Thought (CoT) equips Large Language Models (LLMs) with strong reasoning capabilities, it requires models to verbalize every intermediate step in text tokens, constraining the model thoughts to the discrete vocabulary…

Temporal Logic (TL), especially Signal Temporal Logic (STL), enables precise formal specification, making it widely used in cyber-physical systems such as autonomous driving and robotics. Automatically transforming NL into STL is an…

Text style transfer, an important research direction in natural language processing, aims to adapt the text to various preferences but often faces challenges with limited resources. In this work, we introduce a novel method termed Style…

End-to-end speech translation (ST), which directly translates from source language speech into target language text, has attracted intensive attentions in recent years. Compared to conventional pipeline systems, end-to-end ST models have…

Text style transfer refers to the task of rephrasing a given text in a different style. While various methods have been proposed to advance the state of the art, they often assume the transfer output follows a delta distribution, and thus…

Sequential recommender systems have achieved significant success in modeling temporal user behavior but remain limited in capturing rich user semantics beyond interaction patterns. Large Language Models (LLMs) present opportunities to…

With the rise of deep learning, large datasets and complex models have become common, requiring significant computing power. To address this, data distillation has emerged as a technique to quickly train models with lower memory and time…

The artistic style within a painting is the means of expression, which includes not only the painting material, colors, and brushstrokes, but also the high-level attributes including semantic elements, object shapes, etc. Previous arbitrary…

Since the advent of reasoning-based large language models, many have found great success from distilling reasoning capabilities into student models. Such techniques have significantly bridged the gap between reasoning and standard LLMs on…

Over the past year, the emergence of transfer learning with large-scale language models (LM) has led to dramatic performance improvements across a broad range of natural language understanding tasks. However, the size and memory footprint…

Diffusion language models (DLMs) have emerged as a promising alternative to autoregressive models for faster inference via parallel token generation. We provide a rigorous foundation for this advantage by formalizing a model of parallel…

Style is an integral component of a sentence indicated by the choice of words a person makes. Different people have different ways of expressing themselves, however, they adjust their speaking and writing style to a social context, an…

Existing text style transfer (TST) methods rely on style classifiers to disentangle the text's content and style attributes for text style transfer. While the style classifier plays a critical role in existing TST methods, there is no known…

In this paper, we present StyleTTS 2, a text-to-speech (TTS) model that leverages style diffusion and adversarial training with large speech language models (SLMs) to achieve human-level TTS synthesis. StyleTTS 2 differs from its…

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…