activity
20242026
collaborators
Showing cs.SDShow all

9 papers · 1 filter

cs.SD2026

Improving Text-to-Music Generation with Human Preference Rewards

Yonghyun Kim, Junwon Lee, Haiwen Xia +2

We describe our entry to the efficiency track of the Academic Text-to-Music (ATTM) Grand Challenge at ICME 2026. Beyond the challenge protocol's FAD-CLAP and CLAP score, we add a l…

cs.SD2026

TuneJury: An Open Metric for Improving Music Generation Preference Alignment

Yonghyun Kim, Junwon Lee, Haiwen Xia +5

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. The released che…

cs.SD2026

CMI-RewardBench: Evaluating Music Reward Models with Compositional Multimodal Instruction

Yinghao Ma, Haiwen Xia, Hewei Gao +9

While music generation models have evolved to handle complex multimodal inputs mixing text, lyrics, and reference audio, evaluation mechanisms have lagged behind. In this paper, we…

cs.SD2026

Audio-FLAN: An Instruction-Following Dataset for Unified Audio Understanding and Generation of Speech, Music, and Sound

Liumeng Xue, Ziya Zhou, Jiahao Pan +20

Recent advancements in audio tokenization have significantly enhanced the integration of audio capabilities into large language models (LLMs). However, audio understanding and gene…

cs.SD2026

AVMeme Exam: A Multimodal Multilingual Multicultural Benchmark for LLMs' Contextual and Cultural Knowledge and Thinking

Xilin Jiang, Qiaolin Wang, Junkai Wu +30

Internet audio-visual clips convey meaning through time-varying sound and motion, which extend beyond what text alone can represent. To examine whether AI models can understand suc…

cs.SD2025

SAR-LM: Symbolic Audio Reasoning with Large Language Models

Termeh Taheri, Yinghao Ma, Emmanouil Benetos

Large language models (LLMs) have advanced in text and vision, but their reasoning on audio remains limited. Most existing methods rely on dense audio embeddings, which are difficu…