# SPRING: Situated Conversation Agent Pretrained with Multimodal Questions from Incremental Layout Graph

arXiv: https://arxiv.org/abs/2301.01949 · HTML: https://mlsanity.com/paper/2301.01949/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 49 references that are in the map.
- First posted on arXiv 5 Jan 2023.

## Builds on (most cited first, 27 of 27)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks](https://mlsanity.com/paper/1908.02265/) (2019)
- [CIDEr: Consensus-based Image Description Evaluation](https://mlsanity.com/paper/1411.5726/) (2014)
- [LXMERT: Learning Cross-Modality Encoder Representations from Transformers](https://mlsanity.com/paper/1908.07490/) (2019)
- [OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework](https://mlsanity.com/paper/2202.03052/) (2022)
- [Unifying Vision-and-Language Tasks via Text Generation](https://mlsanity.com/paper/2102.02779/) (2021)
- [Visual Dialog](https://mlsanity.com/paper/1611.08669/) (2016)
- [UNIMO: Towards Unified-Modal Understanding and Generation via Cross-Modal Contrastive Learning](https://mlsanity.com/paper/2012.15409/) (2020)
- [Seeing Out of tHe bOx: End-to-End Pre-training for Vision-Language Representation Learning](https://mlsanity.com/paper/2104.03135/) (2021)
- [GuessWhat?! Visual object discovery through multi-modal dialogue](https://mlsanity.com/paper/1611.08481/) (2016)
- [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)
- [SIMMC 2.0: A Task-oriented Dialog Dataset for Immersive Multimodal Conversations](https://mlsanity.com/paper/2104.08667/) (2021)
- [Multimodal Transformer Networks for End-to-End Video-Grounded Dialogue Systems](https://mlsanity.com/paper/1907.01166/) (2019)
- [S2SQL: Injecting Syntax to Question-Schema Interaction Graph Encoder for Text-to-SQL Parsers](https://mlsanity.com/paper/2203.06958/) (2022)
- [Situated and Interactive Multimodal Conversations](https://mlsanity.com/paper/2006.01460/) (2020)
- [Proton: Probing Schema Linking Information from Pre-trained Language Models for Text-to-SQL Parsing](https://mlsanity.com/paper/2206.14017/) (2022)
- [SPACE-2: Tree-Structured Semi-Supervised Contrastive Pre-training for Task-Oriented Dialog Understanding](https://mlsanity.com/paper/2209.06638/) (2022)
- [Evaluating Visual Conversational Agents via Cooperative Human-AI Games](https://mlsanity.com/paper/1708.05122/) (2017)
- [Towards Socially Intelligent Agents with Mental State Transition and Human Utility](https://mlsanity.com/paper/2103.07011/) (2021)
- [SocAoG: Incremental Graph Parsing for Social Relation Inference in Dialogues](https://mlsanity.com/paper/2106.01006/) (2021)
- [Multimodal Interactions Using Pretrained Unimodal Models for SIMMC 2.0](https://mlsanity.com/paper/2112.05328/) (2021)

## Built on by (most cited first, 6 of 6)

- [PaCE: Unified Multi-modal Dialogue Pre-training with Progressive and Compositional Experts](https://mlsanity.com/paper/2305.14839/) (2023)
- [Evaluating Scene-based In-Situ Item Labeling for Immersive Conversational Recommendation](https://mlsanity.com/paper/2604.09698/) (2026)
- [MCF-VC: Mitigate Catastrophic Forgetting in Class-Incremental Learning for Multimodal Video Captioning](https://mlsanity.com/paper/2402.17680/) (2024)
- [Extended to Reality: Prompt Injection in 3D Environments](https://mlsanity.com/paper/2602.07104/) (2026)
- [AMATA: Adaptive Multi-Agent Trajectory Alignment for Knowledge-Intensive Question Answering](https://mlsanity.com/paper/2605.17352/) (2026)
- [Multimodal Recommendation Dialog with Subjective Preference: A New Challenge and Benchmark](https://mlsanity.com/paper/2305.18212/) (2023)

## Abstract (arXiv)

Existing multimodal conversation agents have shown impressive abilities to locate absolute positions or retrieve attributes in simple scenarios, but they fail to perform well when complex relative positions and information alignments are involved, which poses a bottleneck in response quality. In this paper, we propose a Situated Conversation Agent Petrained with Multimodal Questions from INcremental Layout Graph (SPRING) with abilities of reasoning multi-hops spatial relations and connecting them with visual attributes in crowded situated scenarios. Specifically, we design two types of Multimodal Question Answering (MQA) tasks to pretrain the agent. All QA pairs utilized during pretraining are generated from novel Incremental Layout Graphs (ILG). QA pair difficulty labels automatically annotated by ILG are used to promote MQA-based Curriculum Learning. Experimental results verify the SPRING's effectiveness, showing that it significantly outperforms state-of-the-art approaches on both SIMMC 1.0 and SIMMC 2.0 datasets.