相关论文: Direct Preference Optimization for Speech Autoregr…

In this paper, we propose to utilise diffusion models for data augmentation in speech emotion recognition (SER). In particular, we present an effective approach to utilise improved denoising diffusion probabilistic models (IDDPM) to…

Optimizing discrete diffusion model (DDM) with rewards remains a challenge: the non-autoregressive paradigm makes importance sampling intractable and rollout complex, puzzling reinforcement learning methods such as Group Relative Policy…

Discrete diffusion models have emerged as powerful tools for high-quality data generation. Despite their success in discrete spaces, such as text generation tasks, the acceleration of discrete diffusion models remains under-explored. In…

Our goal is to enable large language models (LLMs) to balance multiple human preference dimensions; such as helpfulness, safety, and verbosity, through principled and controllable alignment. Existing preference optimization methods,…

Diffusion language models have recently emerged as a competitive alternative to autoregressive language models. Beyond next-token generation, they are more efficient and flexible by enabling parallel and any-order token generation. However,…

Direct Preference Optimization (DPO) has gained attention as an efficient alternative to reinforcement learning from human feedback (RLHF) for aligning large language models (LLMs) with human preferences. Despite its advantages, DPO suffers…

Diffusion-based generative models (DGMs) have recently attracted attention in speech enhancement research (SE) as previous works showed a remarkable generalization capability. However, DGMs are also computationally intensive, as they…

Offline reinforcement learning (RL) aims to learn optimal policies from previously collected datasets. Recently, due to their powerful representational capabilities, diffusion models have shown significant potential as policy models for…

Inspired by recent developments in neural speech coding and diffusion-based language modeling, we tackle speech enhancement by modeling the conditional distribution of clean speech codes given noisy speech codes using absorbing discrete…

Generating realistic 3D head motion for dyadic interactions is a significant challenge in virtual human synthesis. While recent methods achieve impressive results with speaking heads, they frequently suffer from the `Regression-to-the-Mean'…

Recent advances in diffusion models have enabled high-quality synthesis of specific subjects, such as identities or objects. This capability, while unlocking new possibilities in content creation, also introduces significant privacy risks,…

Language Model (LM)-based speech enhancement (SE) has recently emerged as a promising direction, but existing approaches predominantly rely on token-level likelihood objectives that weakly reflect human perception. This mismatch limits…

While likelihood-based generative models, particularly diffusion and autoregressive models, have achieved remarkable fidelity in visual generation, the maximum likelihood estimation (MLE) objective, which minimizes the forward KL…

Diffusion models have achieved remarkable success in conditional image generation, yet their outputs often remain misaligned with human preferences. To address this, recent work has applied Direct Preference Optimization (DPO) to diffusion…

Direct Preference Optimization (DPO) simplifies reinforcement learning from human feedback (RLHF) for large language models (LLMs) by directly optimizing human preferences without an explicit reward model. We find that during DPO training,…

Modern zero-shot text-to-speech (TTS) systems, despite using extensive pre-training, often struggle in challenging scenarios such as tongue twisters, repeated words, code-switching, and cross-lingual synthesis, leading to intelligibility…

Direct alignment methods typically train large language models (LLMs) by contrasting the likelihoods of preferred and dispreferred responses. While effective at capturing relative preferences, these methods are widely observed to suppress…

Direct Preference Optimization (DPO) has emerged as an effective approach for aligning large language models (LLMs) with human preferences. However, its performance is highly dependent on the quality of the underlying human preference data.…

In recent years, automatic speech recognition (ASR) models greatly improved transcription performance both in clean, low noise, acoustic conditions and in reverberant environments. However, all these systems rely on the availability of…

Direct Preference Optimization (DPO) has been widely adopted for large language model alignment due to its simple training procedure and lack of an explicit reward model. However, in iterative DPO, when the policy model from the previous…