# NAVER LABS Europe Submission to the Instruction-following Track

arXiv: https://arxiv.org/abs/2506.01808 · HTML: https://mlsanity.com/paper/2506.01808/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 29 references that are in the map.
- First posted on arXiv 2 Jun 2025.

## Builds on (most cited first, 23 of 23)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [PaLM-E: An Embodied Multimodal Language Model](https://mlsanity.com/paper/2303.03378/) (2023)
- [Mixtral of Experts](https://mlsanity.com/paper/2401.04088/) (2024)
- [A Call for Clarity in Reporting BLEU Scores](https://mlsanity.com/paper/1804.08771/) (2018)
- [Moshi: a speech-text foundation model for real-time dialogue](https://mlsanity.com/paper/2410.00037/) (2024)
- [SALMONN: Towards Generic Hearing Abilities for Large Language Models](https://mlsanity.com/paper/2310.13289/) (2023)
- [Scaling Speech Technology to 1,000+ Languages](https://mlsanity.com/paper/2305.13516/) (2023)
- [AudioPaLM: A Large Language Model That Can Speak and Listen](https://mlsanity.com/paper/2306.12925/) (2023)
- [What matters when building vision-language models?](https://mlsanity.com/paper/2405.02246/) (2024)
- [AudioGPT: Understanding and Generating Speech, Music, Sound, and Talking Head](https://mlsanity.com/paper/2304.12995/) (2023)
- [Tower: An Open Multilingual Large Language Model for Translation-Related Tasks](https://mlsanity.com/paper/2402.17733/) (2024)
- [Spirit LM: Interleaved Spoken and Written Language Model](https://mlsanity.com/paper/2402.05755/) (2024)
- [SeamlessM4T: Massively Multilingual & Multimodal Machine Translation](https://mlsanity.com/paper/2308.11596/) (2023)
- [Europarl-ST: A Multilingual Corpus For Speech Translation Of Parliamentary Debates](https://mlsanity.com/paper/1911.03167/) (2019)
- [WavLLM: Towards Robust and Adaptive Speech Large Language Model](https://mlsanity.com/paper/2404.00656/) (2024)
- [EuroLLM: Multilingual Language Models for Europe](https://mlsanity.com/paper/2409.16235/) (2024)
- [Spoken SQuAD: A Study of Mitigating the Impact of Speech Recognition Errors on Listening Comprehension](https://mlsanity.com/paper/1804.00320/) (2018)
- [CoVoST 2 and Massively Multilingual Speech-to-Text Translation](https://mlsanity.com/paper/2007.10310/) (2020)
- [BERGEN: A Benchmarking Library for Retrieval-Augmented Generation](https://mlsanity.com/paper/2407.01102/) (2024)
- [From TOWER to SPIRE: Adding the Speech Modality to a Translation-Specialist LLM](https://mlsanity.com/paper/2503.10620/) (2025)
- [Breaking Language Barriers in Visual Language Models via Multilingual Textual Regularization](https://mlsanity.com/paper/2503.22577/) (2025)

## Built on by (most cited first, 5 of 5)

- [SpeechMapper: Speech-to-text Embedding Projector for LLMs](https://mlsanity.com/paper/2601.20417/) (2026)
- [MEUSLI: a Multilingual Projector for LLM-based ASR and Beyond](https://mlsanity.com/paper/2607.22100/) (2026)
- [FBK's Long-form SpeechLLMs for IWSLT 2026 Instruction Following](https://mlsanity.com/paper/2606.26819/) (2026)
- [NAVER LABS Europe Submission to the Instruction-following 2026 Short Track](https://mlsanity.com/paper/2607.01960/) (2026)
- [NAVER LABS System Re-implementation for the IWSLT 2026 Instruction-Following Task](https://mlsanity.com/paper/2607.05623/) (2026)

## Abstract (arXiv)

In this paper we describe NAVER LABS Europe submission to the instruction-following speech processing short track at IWSLT 2025. We participate in the constrained settings, developing systems that can simultaneously perform ASR, ST, and SQA tasks from English speech input into the following target languages: Chinese, Italian, and German. Our solution leverages two pretrained modules: (1) a speech-to-LLM embedding projector trained using representations from the SeamlessM4T-v2-large speech encoder; and (2) LoRA adapters trained on text data on top of a Llama-3.1-8B-Instruct. These modules are jointly loaded and further instruction-tuned for 1K steps on multilingual and multimodal data to form our final system submitted for evaluation.