Search arXiv⌕ Search
Home/Archive/arXiv

arXiv · 2610.14508

PAG-Agent: Zero-Shot Personalized Music Album Generation via Aesthetic Profile Distillation

Yifeng Mao·Ziye Wang·Yutong Shen·Feiran Liu·Wenjuan Han
View original source ↗Read source document ↗Export metadata ↓

Abstract

Large Music Models (LMMs) can synthesize high-fidelity audio and support increasingly flexible prompt control, yet modeling the subjective preferences of an individual listener remains underexplored. We present PAG-Agent, a zero-shot multimodal framework that uses an explicit Personal Aesthetic Profile to bridge user preference inference and music generation control. A multimodal LLM distills favorite-song audio and contextual user information into this structured representation, which a planning LLM translates into generation instructions for existing music synthesizers. We further introduce PA-Eval, which evaluates personalization through the Aesthetic Consistency Score (ACS) for target-user alignment and the Aesthetic Specificity Index (ASI) for cross-user specificity. Experiments with Personal-100 on multiple MLLM and music-generation backbones show consistent improvements over generic and direct conditioning. A 50-participant follow-up study further shows a correlation $r=0.64$ between ACS and subjective preference.

Explore related subjects

cs.MMcs.SD

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Yifeng Mao, Ziye Wang, Yutong Shen, Feiran Liu, Wenjuan Han. 2026-10-10. PAG-Agent: Zero-Shot Personalized Music Album Generation via Aesthetic Profile Distillation. https://arxiv.org/abs/2610.14508

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

EmoGavel: Grounding-Aware Reinforcement Learning with Verifiable Rewards for Multimodal Emotion Preference Learning

Multimodal emotion preference learning uses pairwise comparisons to identify which open-ended emotion descriptions align more closely with human judgments. However, existing methods primarily focus on the final preference decision and provide little explicit supervision for localizing and correcting erroneous content. To address this limitation, we propose EmoGavel, a Grounding-Aware reinforcement learning framework with Verifiable rewards for multimodal Emotion preference Learning. We first introduce grounded supervised fine-tuning (Grounded SFT), which exploits controlled-error construction information to jointly learn preference prediction, error localization, repair, and missing-evidence recovery. We then optimize these verifiable outcomes with grounding-aware group relative policy optimization (GA-GRPO), combining preference-gated grounding rewards with dynamic zero-variance rescue to prioritize preference correctness and recover learning signals from all-wrong groups. Experiments on EmoPrefer and controlled-error evaluation sets show that EmoGavel improves both natural preference prediction and controlled-error discrimination while maintaining strong error-grounding performance. Our code and model checkpoints will be released once the paper is accepted.

cs.MM↗
arXiv2026

DIA: A Deep Reinforcement Learning-Based Interest-Aware ABR Scheme for Cloud Gaming

The continuous evolution of cloud gaming has enabled users to play high-quality cloud games on thin clients, such as smartphones and tablets. However, how to effectively transmit the gameplay frames with high resolution and low latency, especially over wireless networks, remains a significant challenge. To address this challenge, we propose a Deep Reinforcement Learning (DRL)-based Interest-Aware Adaptive Bitrate (ABR) scheme, called DIA, that guarantees the quality of perceptually key objects in each frame, while dynamically allocating lower resolutions for non-key objects to conserve bandwidth under constrained network conditions. By leveraging an off-the-shelf semantic segmentation model, the proposed DIA scheme can adjust the bitrate at the object-level. We also design a transformer-based feature extractor and an interest-aware reward function to enable the proposed DIA scheme to identify key objects and dynamically adjust their bitrates. This adaptation is guided by users' in-game movement speed, object features, and prevailing network conditions and operates without requiring additional hardware, such as gaze trackers. Extensive experiments show that the proposed DIA scheme outperforms existing ABR schemes in dynamic wireless network environments. Notably, DIA achieves at least a 20% higher normalized average Quality of Experience (QoE) than the State-Of-The-Art (SOTA) ABR algorithms in 5G scenarios.

cs.MM↗
arXiv2026

Mechanisms of Multimodal Synchronization: Insights from Decoder-Based Video-Text-to-Speech Synthesis

Unified decoder-only transformers have shown promise for multimodal generation, yet how sequence design affects synchronization across modalities with heterogeneous sampling rates remains underexplored. We investigate this through video-text-to-speech (VTTS) synthesis, a controlled task requiring fine-grained temporal alignment between sparse text, video, and continuous speech. Using Visatronic, a unified decoder-only transformer trained on VoxCeleb2, we examine complementary modality contributions, positional encoding strategies, the effects of modality ordering on in-domain performance and cross-domain transfer, and phoneme-level timing errors. Global sequential indexing, which assigns position IDs in concatenation order, and co-temporal ordered indexing, which assigns identical IDs to temporally corresponding video and speech tokens, achieve comparable in-domain synchronization. Under domain shift, however, synchronization depends on the interaction between token ordering and position-ID design. Text-first co-temporal indexing transfers most robustly among the evaluated variants without requiring explicit timestamp metadata. Text and video provide complementary signals: text supports intelligibility, while video contributes temporal cues and emotional expressiveness. Modality ordering also introduces a trade-off: video-first ordering achieves stronger in-domain performance, whereas text-first ordering generalizes more robustly among the timestamp-informed prefix variants. Training on diverse, in-the-wild data is associated with more transferable behavior, although isolating its contribution requires targeted ablations. We introduce TimeSync, a phoneme-level synchronization metric that reveals temporal misalignments overlooked by frame-level metrics. Together, these findings establish VTTS as a testbed for understanding temporal synchronization in unified multimodal decoders.

cs.MM↗