CVSDSep 26, 2025

WAVE: Learning Unified & Versatile Audio-Visual Embeddings with Multimodal LLM

arXiv:2509.21990v14 citationsh-index: 11Has Code
Originality Highly original
AI Analysis

This addresses the need for versatile cross-modal representations in AI applications, offering a novel approach with broad potential, though it builds on existing multimodal LLM frameworks.

The paper tackles the problem of creating unified embeddings for text, audio, and video using multimodal LLMs, achieving state-of-the-art results on benchmarks like MMEB-v2 and superior performance in cross-modal retrieval and question answering.

While embeddings from multimodal large language models (LLMs) excel as general-purpose representations, their application to dynamic modalities like audio and video remains underexplored. We introduce WAVE (\textbf{u}nified \& \textbf{v}ersatile \textbf{a}udio-\textbf{v}isual \textbf{e}mbeddings), the first LLM-based embedding that creates a unified representation space for text, audio, and video modalities. WAVE employs a novel hierarchical feature fusion strategy and a joint multi-modal, multi-task training approach to enable two key capabilities: any-to-any cross-modal retrieval and the generation of prompt-aware embeddings tailored to user instructions. Experimentally, WAVE sets a new state-of-the-art on the MMEB-v2 video benchmark and achieves superior results in audio and video-to-audio retrieval. Its prompt-aware nature also yields remarkable performance in multimodal question answering, significantly outperforming existing embedding models. Ablation studies validate our joint training strategy, demonstrating improved performance across all modalities. With a newly introduced benchmark for versatile audio-visual learning, WAVE opens up broad possibilities for cross-modal, any-to-any applications. Our code, checkpoints, and data will be released.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes