Amine Ouasfi
Research Subjects
Research Interests
Amine Ouasfi has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Adnane Boukhayma
Univ Rennes Inria CNRS IRISA M2S France
1 shared publication - François Leduc-Primeau
Department of Electrical Engineering Polytechnique Montréal H3C 3A7 Montréal QC Canada
1 shared publication - Ilyass Moummad
INRIA Montpellier
1 shared publication - Reda Bensaid1 shared publication
- Vincent Gripon
IMT Atlantique, Lab-STICC, UMR CNRS 6285
1 shared publication - Yassir Bendou1 shared publication
Latest Publications
- Open Access
MUKA: Multi Kernel Audio Adaptation Of Audio-Language Models
Multimodal foundation models have demonstrated impressive generalization capabilities, yet efficiently adapting them to new tasks in a few-shot setting remains a critical challenge. In this work, we investigate the few-shot adaptation of Large Audio-Language Models (ALMs) through both training-based and training-free approaches. We introduce MUKA, a multi-kernel adaptation framework that combines the fine-grained, context-dependent representations of instruction-tuning based models like Pengi with the global semantic representations of contrastive pretraining methods like CLAP. By constructing a product kernel that aligns local similarity with global semantics, MUKA enhances representational power while preserving the theoretical guarantees of kernel methods and avoiding additional training. Extensive experiments across 11 diverse audio datasets demonstrate that MUKA achieves state-of-the-art performance among training-free methods and even surpasses training-based adapters in several scenarios, offering a compelling balance between adaptability and efficiency.
Open AccessMUKA: Multi Kernel Audio Adaptation Of Audio-Language Models
Multimodal foundation models have demonstrated impressive generalization capabilities, yet efficiently adapting them to new tasks in a few-shot setting remains a critical challenge. In this work, we investigate the few-shot adaptation of Large Audio-Language Models (ALMs) through both training-based and training-free approaches. We introduce MUKA, a multi-kernel adaptation framework that combines the fine-grained, context-dependent representations of instruction-tuning based models like Pengi with the global semantic representations of contrastive pretraining methods like CLAP. By constructing a product kernel that aligns local similarity with global semantics, MUKA enhances representational power while preserving the theoretical guarantees of kernel methods and avoiding additional training. Extensive experiments across 11 diverse audio datasets demonstrate that MUKA achieves state-of-the-art performance among training-free methods and even surpasses training-based adapters in several scenarios, offering a compelling balance between adaptability and efficiency.