Audio Flamingo 3 introduces an open large audio-language model achieving new state-of-the-art results on over 20 audio understanding and reasoning benchmarks using a unified encoder and curriculum training on open data.
Yake Wei, Di Hu, Henghui Du, and Ji-Rong Wen
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
dataset 1
citation-polarity summary
roles
dataset 1polarities
use dataset 1representative citing papers
Survey of Music AVQA finds specialized input processing, dedicated spatial-temporal designs, and music-specific modeling are critical for strong performance.
citing papers explorer
-
Audio Flamingo 3: Advancing Audio Intelligence with Fully Open Large Audio Language Models
Audio Flamingo 3 introduces an open large audio-language model achieving new state-of-the-art results on over 20 audio understanding and reasoning benchmarks using a unified encoder and curriculum training on open data.
-
Music Audio-Visual Question Answering Requires Specialized Multimodal Designs
Survey of Music AVQA finds specialized input processing, dedicated spatial-temporal designs, and music-specific modeling are critical for strong performance.
- Topology-Aware Layer Pruning for Large Vision-Language Models