Vela: Scalable Embeddings with Voice Large Language Models for Multimodal Retrieval

June 17, 2025 Β· Declared Dead Β· πŸ› Interspeech

πŸ‘» CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Ruofan Hu, Yan Xia, Minjie Hong, Jieming Zhu, Bo Chen, Xiaoda Yang, Minghui Fang, Tao Jin arXiv ID 2506.14445 Category cs.IR: Information Retrieval Citations 2 Venue Interspeech Last Checked 4 months ago
Abstract
Multimodal large language models (MLLMs) have seen substantial progress in recent years. However, their ability to represent multimodal information in the acoustic domain remains underexplored. In this work, we introduce Vela, a novel framework designed to adapt MLLMs for the generation of universal multimodal embeddings. By leveraging MLLMs with specially crafted prompts and selected in-context learning examples, Vela effectively bridges the modality gap across various modalities. We then propose a single-modality training approach, where the model is trained exclusively on text pairs. Our experiments show that Vela outperforms traditional CLAP models in standard text-audio retrieval tasks. Furthermore, we introduce new benchmarks that expose CLAP models' limitations in handling long texts and complex retrieval tasks. In contrast, Vela, by harnessing the capabilities of MLLMs, demonstrates robust performance in these scenarios. Our code will soon be available.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

πŸ“œ Similar Papers

In the same crypt β€” Information Retrieval

Died the same way β€” πŸ‘» Ghosted