Related papers: Emo-DPO: Controllable Emotional Speech Synthesis t…

While alignment algorithms are now commonly used to tune pre-trained language models towards a user's preferences, we lack explanations for the underlying mechanisms in which models become ``aligned'', thus making it difficult to explain…

To enhance controllability in text-to-image generation, ControlNet introduces image-based control signals, while ControlNet++ improves pixel-level cycle consistency between generated images and the input control signal. To avoid the…

Machine-generated speech is characterized by its limited or unnatural emotional variation. Current text to speech systems generates speech with either a flat emotion, emotion selected from a predefined set, average variation learned from…

For aligning large language models (LLMs), prior work has leveraged reinforcement learning via human feedback (RLHF) or variations of direct preference optimization (DPO). While DPO offers a simpler framework based on maximum likelihood…

Direct Preference Optimization (DPO) guides large language models (LLMs) to generate recommendations aligned with user historical behavior distributions by minimizing preference alignment loss. However, our systematic empirical research and…

Large Language Models (LLMs) have demonstrated remarkable potential in automating software development tasks. While recent advances leverage Supervised Fine-Tuning (SFT) and Direct Preference Optimization (DPO) to align models with human…

Emotional text-to-speech (TTS) systems sturggle to capture the full spectrum of human emotions due to the inherent complexity of emotional expressions and the limited coverage of existing emotion labels. To address this, we propose a…

We often verbally express emotions in a multifaceted manner, they may vary in their intensities and may be expressed not just as a single but as a mixture of emotions. This wide spectrum of emotions is well-studied in the structural model…

Large Language Models (LLMs) have become increasingly popular due to their ability to process and generate natural language. However, as they are trained on massive datasets of text, LLMs can inherit harmful biases and produce outputs that…

Direct Preference Optimization (DPO) has been successfully used to align large language models (LLMs) according to human preferences, and more recently it has also been applied to improving the quality of text-to-image diffusion models.…

Emotion embedding space learned from references is a straightforward approach for emotion transfer in encoder-decoder structured emotional text to speech (TTS) systems. However, the transferred emotion in the synthetic speech is not…

The rapid growth of autonomous driving datasets has enabled the scaling of powerful motion forecasting models. While large-scale pretraining provides strong performance, the standard imitation objective may not fully capture the complex…

Aligning large language models (LLMs) with human intent is critical for enhancing their performance across a variety of tasks. Standard alignment techniques, such as Direct Preference Optimization (DPO), often rely on the binary…

Automatic text simplification (ATS) aims to enhance language accessibility for various target groups, particularly persons with intellectual disabilities. Recent advancements in generative AI, especially large language models (LLMs), have…

Aligning text-to-speech (TTS) system outputs with human feedback through preference optimization has been shown to effectively improve the robustness and naturalness of language model-based TTS models. Current approaches primarily require…

We investigate hierarchical emotion distribution (ED) for achieving multi-level quantitative control of emotion rendering in text-to-speech synthesis (TTS). We introduce a novel multi-step hierarchical ED prediction module that quantifies…

Aligning large language models (LLMs) with human preferences is essential for safe and useful LLMs. Previous works mainly adopt reinforcement learning (RLHF) and direct preference optimization (DPO) with human feedback for alignment.…

Learning from human preference is a paradigm used in large-scale language model (LLM) fine-tuning step to better align pretrained LLM to human preference for downstream task. In the past it uses reinforcement learning from human feedback…

Direct Preference Optimization (DPO) has emerged as a cornerstone of reinforcement learning from human feedback (RLHF) due to its simplicity and efficiency. However, existing DPO-based methods typically treat all preference pairs equally,…

While the performance of cross-lingual TTS based on monolingual corpora has been significantly improved recently, generating cross-lingual speech still suffers from the foreign accent problem, leading to limited naturalness. Besides,…