DailyOmni

The 'DailyOmni' dataset/benchmark contains high-quality audio-visual reasoning data and is used to evaluate the performance of models in multimodal reasoning tasks.

Papers using DailyOmni (3)

AVRT: Audio-Visual Reasoning Transfer through Single-Modality Teachers2026Omnivinci: Enhancing Architecture And Data For Omni-modal Understanding LLM2025Daily-Omni: Towards Audio-Visual Reasoning with Temporal Alignment across Modalities2025