MMSU

[ICLR 2026] MMSU: A Massive Multi-task Spoken Language Understanding and Reasoning Benchmark Overview of MMSU MMSU (Massive Multi-task Spoken Language Understanding and Reasoning Benchmark) is a comprehensive benchmark for evaluating fine-grained spoken language understanding and reasoning in multimodal models. It syst

Papers using MMSU (7)

DIFFA-2: A Practical Diffusion Large Language Model for General Audio Understanding2026ALARM: Audio-Language Alignment for Reasoning Models2026Closing the Modality Reasoning Gap for Speech Large Language Models2026MiMo-Audio: Audio Language Models are Few-Shot Learners2025TASU: Text-Only Alignment for Speech Understanding2025AQA-TTRL: Self-Adaptation in Audio Question Answering with Test-Time Reinforcement Learning2025DIFFA: Large Language Diffusion Models Can Listen and Understand2025