OpenCodePapers

audio-visual-question-answering-on-music-avqa

Audio Question AnsweringAudio-visual Question Answering
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
Click a sortable column header to sort.
PaperCodeAccModelNameReleaseDate
VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset✓ Link80.7VAST2023-05-29
Parameter-Efficient Adaptation for MLLMs via Implicit Modality Decomposition✓ Link80.13IMoD (Qwen3-8B) (extra data)2026-06-03
79.6CoQo(Internvideo2)
MAD: Modality-Adaptive Decoding for Mitigating Cross-Modal Hallucinations in Multimodal Large Language Models✓ Link79.1VideoLLaMA2-AV + MAD2026-01-29
VALOR: Vision-Audio-Language Omni-Perception Pretraining Model and Dataset✓ Link78.9VALOR2023-04-17
Querying as Prompt: Parameter-Efficient Learning for Multimodal Language Model✓ Link78.69QaP (Ours hf)2024-06-17
CAD -- Contextual Multi-modal Alignment for Dynamic AVQA78.26CAD2023-10-25
Q-TriM: Question-Guided Tri-Modal Attention for Audio–Visual Question Answering✓ Link77.68Q-TriM2026-07-04
Vision Transformers are Parameter-Efficient Audio-Visual Learners✓ Link77.08LAVISH2022-12-15
Learning to Answer Questions in Dynamic Audio-Visual Scenarios✓ Link71.52ST-AVQA2022-03-26
ChronusOmni: Improving Time Awareness of Omni-Modal Large Language Models66.0ChronusOmni2026-09-08
Check out how to contribute new results. Then edit this file on GitLab or GitHub.