# PaCE: Unified Multi-modal Dialogue Pre-training with Progressive and Compositional Experts

arXiv: https://arxiv.org/abs/2305.14839 · HTML: https://mlsanity.com/paper/2305.14839/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Builds on 42 of its 70 references that are in the map.
- First posted on arXiv 24 May 2023.

## Builds on (most cited first, 30 of 42)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity](https://mlsanity.com/paper/2101.03961/) (2021)
- [ALBERT: A Lite BERT for Self-supervised Learning of Language Representations](https://mlsanity.com/paper/1909.11942/) (2019)
- [Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations](https://mlsanity.com/paper/1602.07332/) (2016)
- [ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks](https://mlsanity.com/paper/1908.02265/) (2019)
- [CoCa: Contrastive Captioners are Image-Text Foundation Models](https://mlsanity.com/paper/2205.01917/) (2022)
- [ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision](https://mlsanity.com/paper/2102.03334/) (2021)
- [GLaM: Efficient Scaling of Language Models with Mixture-of-Experts](https://mlsanity.com/paper/2112.06905/) (2021)
- [Florence: A New Foundation Model for Computer Vision](https://mlsanity.com/paper/2111.11432/) (2021)
- [OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework](https://mlsanity.com/paper/2202.03052/) (2022)
- [SimVLM: Simple Visual Language Model Pretraining with Weak Supervision](https://mlsanity.com/paper/2108.10904/) (2021)
- [VLMo: Unified Vision-Language Pre-Training with Mixture-of-Modality-Experts](https://mlsanity.com/paper/2111.02358/) (2021)
- [Stacked Cross Attention for Image-Text Matching](https://mlsanity.com/paper/1803.08024/) (2018)
- [Unifying Vision-and-Language Tasks via Text Generation](https://mlsanity.com/paper/2102.02779/) (2021)
- [Visual Dialog](https://mlsanity.com/paper/1611.08669/) (2016)
- [A Simple Language Model for Task-Oriented Dialogue](https://mlsanity.com/paper/2005.00796/) (2020)
- [GALAXY: A Generative Pre-trained Model for Task-Oriented Dialog with Semi-Supervised Learning and Explicit Policy Injection](https://mlsanity.com/paper/2111.14592/) (2021)
- [Image Chat: Engaging Grounded Conversations](https://mlsanity.com/paper/1811.00945/) (2018)
- [Find or Classify? Dual Strategy for Slot-Value Predictions on Multi-Domain Dialog State Tracking](https://mlsanity.com/paper/1910.03544/) (2019)
- [Two Causal Principles for Improving Visual Dialog](https://mlsanity.com/paper/1911.10496/) (2019)
- [Image-Grounded Conversations: Multimodal Context for Natural Question and Response Generation](https://mlsanity.com/paper/1701.08251/) (2017)

## Built on by (most cited first, 19 of 19)

- [MoE-LLaVA: Mixture of Experts for Large Vision-Language Models](https://mlsanity.com/paper/2401.15947/) (2024)
- [MMICL: Empowering Vision-language Model with Multi-Modal In-Context Learning](https://mlsanity.com/paper/2309.07915/) (2023)
- [A Survey on Agentic Multimodal Large Language Models](https://mlsanity.com/paper/2510.10991/) (2025)
- [Routing Experts: Learning to Route Dynamic Experts in Multi-modal Large Language Models](https://mlsanity.com/paper/2407.14093/) (2024)
- [Solving Token Gradient Conflict in Mixture-of-Experts for Large Vision-Language Model](https://mlsanity.com/paper/2406.19905/) (2024)
- [Eve: Efficient Multimodal Vision Language Models with Elastic Visual Experts](https://mlsanity.com/paper/2501.04322/) (2025)
- [Mining Clues from Incomplete Utterance: A Query-enhanced Network for Incomplete Utterance Rewriting](https://mlsanity.com/paper/2307.00866/) (2023)
- [BI-MDRG: Bridging Image History in Multimodal Dialogue Response Generation](https://mlsanity.com/paper/2408.05926/) (2024)
- [Large Language Models can Share Images, Too!](https://mlsanity.com/paper/2310.14804/) (2023)
- [MoHAVE: Mixture of Hierarchical Audio-Visual Experts for Robust Speech Recognition](https://mlsanity.com/paper/2502.10447/) (2025)
- [Multi-Modal Video Dialog State Tracking in the Wild](https://mlsanity.com/paper/2407.02218/) (2024)
- [Enabling Chatbots with Eyes and Ears: An Immersive Multimodal Conversation System for Dynamic Interactions](https://mlsanity.com/paper/2506.00421/) (2025)
- [MoQE: Improve Quantization Model performance via Mixture of Quantization Experts](https://mlsanity.com/paper/2508.09204/) (2025)
- [DialCLIP: Empowering CLIP as Multi-Modal Dialog Retriever](https://mlsanity.com/paper/2401.01076/) (2024)
- [Adapting 2D Multi-Modal Large Language Model for 3D CT Image Analysis](https://mlsanity.com/paper/2604.10233/) (2026)
- [VDialogUE: A Unified Evaluation Benchmark for Visually-grounded Dialogue](https://mlsanity.com/paper/2309.07387/) (2023)
- [Towards Spoken Language Understanding via Multi-level Multi-grained Contrastive Learning](https://mlsanity.com/paper/2405.20852/) (2024)
- [CogniRoute: Learning to Route Social Evidence in Omni-Modal Models](https://mlsanity.com/paper/2606.20970/) (2026)
- [FineWeb-CLaR: Culture, Language, and Region Annotations for Benchmark-Aligned Corpus Auditing](https://mlsanity.com/paper/2609.25298/) (2026)

## Abstract (arXiv)

Perceiving multi-modal information and fulfilling dialogues with humans is a long-term goal of artificial intelligence. Pre-training is commonly regarded as an effective approach for multi-modal dialogue. However, due to the limited availability of multi-modal dialogue data, there is still scarce research on multi-modal dialogue pre-training. Yet another intriguing challenge emerges from the encompassing nature of multi-modal dialogue, which involves various modalities and tasks. Moreover, new forms of tasks may arise at unpredictable points in the future. Hence, it is essential for designed multi-modal dialogue models to possess sufficient flexibility to adapt to such scenarios. This paper proposes PaCE, a unified, structured, compositional multi-modal dialogue pre-training framework. It utilizes a combination of several fundamental experts to accommodate multiple dialogue-related tasks and can be pre-trained using limited dialogue and extensive non-dialogue multi-modal data. Furthermore, we propose a progressive training method where old experts from the past can assist new experts, facilitating the expansion of their capabilities. Experimental results demonstrate that PaCE achieves state-of-the-art results on eight multi-modal dialog benchmarks.