# Zipper: A Multi-Tower Decoder Architecture for Fusing Modalities

arXiv: https://arxiv.org/abs/2405.18669 · HTML: https://mlsanity.com/paper/2405.18669/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 37 of its 42 references that are in the map.
- First posted on arXiv 29 May 2024.

## Builds on (most cited first, 30 of 37)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [Decision Transformer: Reinforcement Learning via Sequence Modeling](https://mlsanity.com/paper/2106.01345/) (2021)
- [Scaling Autoregressive Models for Content-Rich Text-to-Image Generation](https://mlsanity.com/paper/2206.10789/) (2022)
- [CoCa: Contrastive Captioners are Image-Text Foundation Models](https://mlsanity.com/paper/2205.01917/) (2022)
- [Scaling Language Models: Methods, Analysis & Insights from Training Gopher](https://mlsanity.com/paper/2112.11446/) (2021)
- [PaLM 2 Technical Report](https://mlsanity.com/paper/2305.10403/) (2023)
- [SoundStream: An End-to-End Neural Audio Codec](https://mlsanity.com/paper/2107.03312/) (2021)
- [PaLI: A Jointly-Scaled Multilingual Language-Image Model](https://mlsanity.com/paper/2209.06794/) (2022)
- [LibriTTS: A Corpus Derived from LibriSpeech for Text-to-Speech](https://mlsanity.com/paper/1904.02882/) (2019)
- [Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation](https://mlsanity.com/paper/2310.05737/) (2023)
- [AudioLM: a Language Modeling Approach to Audio Generation](https://mlsanity.com/paper/2209.03143/) (2022)
- [VideoPoet: A Large Language Model for Zero-Shot Video Generation](https://mlsanity.com/paper/2312.14125/) (2023)
- [Libri-Light: A Benchmark for ASR with Limited or No Supervision](https://mlsanity.com/paper/1912.07875/) (2019)
- [W2v-BERT: Combining Contrastive Learning and Masked Language Modeling for Self-Supervised Speech Pre-Training](https://mlsanity.com/paper/2108.06209/) (2021)
- [AudioPaLM: A Large Language Model That Can Speak and Listen](https://mlsanity.com/paper/2306.12925/) (2023)
- [MoE-LLaVA: Mixture of Experts for Large Vision-Language Models](https://mlsanity.com/paper/2401.15947/) (2024)
- [Google USM: Scaling Automatic Speech Recognition Beyond 100 Languages](https://mlsanity.com/paper/2303.01037/) (2023)
- [Listen, Think, and Understand](https://mlsanity.com/paper/2305.10790/) (2023)
- [Translation between Molecules and Natural Language](https://mlsanity.com/paper/2204.11817/) (2022)
- [On decoder-only architecture for speech-to-text and large language model integration](https://mlsanity.com/paper/2307.03917/) (2023)
- [Unifying Vision, Text, and Layout for Universal Document Processing](https://mlsanity.com/paper/2212.02623/) (2022)
- [Scaling Laws for Generative Mixed-Modal Language Models](https://mlsanity.com/paper/2301.03728/) (2023)
- [Generative Spoken Dialogue Language Modeling](https://mlsanity.com/paper/2203.16502/) (2022)
- [SoundStorm: Efficient Parallel Audio Generation](https://mlsanity.com/paper/2305.09636/) (2023)

## Abstract (arXiv)

Integrating multiple generative foundation models, especially those trained on different modalities, into something greater than the sum of its parts poses significant challenges. Two key hurdles are the availability of aligned data (concepts that contain similar meaning but is expressed differently in different modalities), and effectively leveraging unimodal representations in cross-domain generative tasks, without compromising their original unimodal capabilities. We propose Zipper, a multi-tower decoder architecture that addresses these concerns by using cross-attention to flexibly compose multimodal generative models from independently pre-trained unimodal decoders. In our experiments fusing speech and text modalities, we show the proposed architecture performs very competitively in scenarios with limited aligned text-speech data. We also showcase the flexibility of our model to selectively maintain unimodal (e.g., text-to-text generation) generation performance by freezing the corresponding modal tower (e.g. text). In cross-modal tasks such as automatic speech recognition (ASR) where the output modality is text, we show that freezing the text backbone results in negligible performance degradation. In cross-modal tasks such as text-to-speech generation (TTS) where the output modality is speech, we show that using a pre-trained speech backbone results in superior performance to the baseline.