arXiv:2606. 17006v1 Announce Type: cross Abstract: We introduce TuneJury, an open, instance-level pairwise reward model for text-to-music that predicts a music preference score from a text prompt and an audio clip.
arXiv:2603. 00610v3 Announce Type: replace-cross Abstract: While music generation models have evolved to handle complex multimodal inputs mixing text, lyrics, and reference audio, evaluation mechanisms have lagged behind.
arXiv:2604. 17415v3 Announce Type: replace-cross Abstract: Reward-based fine-tuning steers a pretrained diffusion or flow-based generative model toward higher-reward samples while remaining close to the pretrained model.
arXiv:2606. 07387v1 Announce Type: new Abstract: State-of-the-art text-to-music generation systems rely on massive proprietary datasets and industrial-scale compute, making it impossible to disentangle architectural contributions from resource advantages.
arXiv:2606. 10010v1 Announce Type: cross Abstract: Evaluating text-to-music (TTM) systems remains expensive because music impression (MI) and text alignment (TA) scores rely on human mean opinion scores (MOS).
arXiv:2606. 03116v1 Announce Type: cross Abstract: The rapid advancement of instruction-guided audio generation has highlighted the critical need for robust alignment evaluation.
arXiv:2605. 03395v2 Announce Type: replace-cross Abstract: Music popularity prediction has attracted growing research interest, with relevance to artists, platforms, and recommendation systems.
Mitigating social bias in Large Language Models (LLMs) presents a distinct alignment challenge: unlike verifiable tasks, bias lacks a single ground truth, creating a high-variance, subjective reward landscape. Previous preference-based fine-tuning methods have major trade-offs: Direct Preference Optimization (DPO) is limited by the lack of exploration inherent in offline training, while Proximal Policy Optimization (PPO) can lead to training instability due to potentially unreliable critic estimates.
arXiv:2606. 04807v1 Announce Type: new Abstract: Mitigating social bias in Large Language Models (LLMs) presents a distinct alignment challenge: unlike verifiable tasks, bias lacks a single ground truth, creating a high-variance, subjective reward landscape.
arXiv:2602. 17658v3 Announce Type: replace-cross Abstract: Reward modeling is central to alignment pipelines such as RLHF, RLAIF, and PPO-based policy optimization, yet its reliability is constrained by limited and heterogeneous human preference data that are expensive to collect at scale.
One-step text-to-image generators are attractive for deployment because they generate an image with a single forward pass, but preference finetuning them remains difficult: standard alignment methods often rely on policy likelihoods, denoising trajectories, differentiable reward gradients, or test-time optimization. We propose Drifting Preference Optimization (DrPO), an online preference-finetuning method for deterministic one-step generators.
arXiv:2607. 16240v1 Announce Type: cross Abstract: Direct Alignment Algorithms (DAAs) such as DPO have become a common way to post-train and align LLMs with human preferences.
arXiv:2510. 26707v2 Announce Type: replace-cross Abstract: As LLMs occupy an increasingly important role in society, they are more and more confronted with questions that require them not only to draw on their general knowledge but also to align with certain human value systems.