Yi-Wen Chao — accepted AI-conference papers

2025

MMAR: A Challenging Benchmark for Deep Reasoning in Speech, Audio, Music, and Their Mix

Ziyang Ma, Yinghao Ma, Yanqiao Zhu, Chen Yang, Yi-Wen Chao, Ruiyang Xu +28

NeurIPS 2025poster

We introduce MMAR, a new benchmark designed to evaluate the deep reasoning capabilities of Audio-Language Models (ALMs) across massive multi-disciplinary tasks. MMAR comprises 1,000 meticulously curated audio-question-answer triplets, collected from real-world internet videos and refined through ite…

Cited by 0 Source ↗code ↗Scholar ↗

2025

Multi-band Frequency Reconstruction for Neural Psychoacoustic Coding

Dianwen Ng, Kun Zhou, Yi-Wen Chao, Zhiwei Xiong, Bin Ma, EngSiong Chng

ICML 2025poster

Achieving high-fidelity audio compression while preserving perceptual quality across diverse audio types remains a significant challenge in Neural Audio Coding (NAC). This paper introduces MUFFIN, a fully convolutional NAC framework that leverages psychoacoustically guided multi-band frequency recon…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗