# Language Models Can See: Plugging Visual Controls in Text Generation

arXiv: https://arxiv.org/abs/2205.02655 · HTML: https://mlsanity.com/paper/2205.02655/

## Key facts

- Cited by 90 papers in the map (data through 14 Oct 2026).
- Builds on 78 of its 95 references that are in the map.
- First posted on arXiv 5 May 2022.

## Builds on (most cited first, 30 of 78)

- [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)
- [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)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [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)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [XLNet: Generalized Autoregressive Pretraining for Language Understanding](https://mlsanity.com/paper/1906.08237/) (2019)
- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [CLIPScore: A Reference-free Evaluation Metric for Image Captioning](https://mlsanity.com/paper/2104.08718/) (2021)
- [SimCSE: Simple Contrastive Learning of Sentence Embeddings](https://mlsanity.com/paper/2104.08821/) (2021)
- [CIDEr: Consensus-based Image Description Evaluation](https://mlsanity.com/paper/1411.5726/) (2014)
- [Show, Attend and Tell: Neural Image Caption Generation with Visual Attention](https://mlsanity.com/paper/1502.03044/) (2015)
- [Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models](https://mlsanity.com/paper/1505.04870/) (2015)
- [Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering](https://mlsanity.com/paper/1707.07998/) (2017)
- [Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks](https://mlsanity.com/paper/2004.06165/) (2020)
- [Hierarchical Neural Story Generation](https://mlsanity.com/paper/1805.04833/) (2018)
- [Alias-Free Generative Adversarial Networks](https://mlsanity.com/paper/2106.12423/) (2021)
- [StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery](https://mlsanity.com/paper/2103.17249/) (2021)

## Built on by (most cited first, 30 of 90)

- [NExT-GPT: Any-to-Any Multimodal LLM](https://mlsanity.com/paper/2309.05519/) (2023)
- [PandaGPT: One Model To Instruction-Follow Them All](https://mlsanity.com/paper/2305.16355/) (2023)
- [What does a platypus look like? Generating customized prompts for zero-shot image classification](https://mlsanity.com/paper/2209.03320/) (2022)
- [Macaw-LLM: Multi-Modal Language Modeling with Image, Audio, Video, and Text Integration](https://mlsanity.com/paper/2306.09093/) (2023)
- [DePlot: One-shot visual language reasoning by plot-to-table translation](https://mlsanity.com/paper/2212.10505/) (2022)
- [Language Models with Image Descriptors are Strong Few-Shot Video-Language Learners](https://mlsanity.com/paper/2205.10747/) (2022)
- [Vision-Language Pre-training: Basics, Recent Advances, and Future Trends](https://mlsanity.com/paper/2210.09263/) (2022)
- [Text-Only Training for Image Captioning using Noise-Injected CLIP](https://mlsanity.com/paper/2211.00575/) (2022)
- [Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?](https://mlsanity.com/paper/2301.00184/) (2022)
- [DeCap: Decoding CLIP Latents for Zero-Shot Captioning via Text-Only Training](https://mlsanity.com/paper/2303.03032/) (2023)
- [Grounded Decoding: Guiding Text Generation with Grounded Models for Embodied Agents](https://mlsanity.com/paper/2303.00855/) (2023)
- [Contrastive Search Is What You Need For Neural Text Generation](https://mlsanity.com/paper/2210.14140/) (2022)
- [Multimodal Reasoning with Multimodal Knowledge Graph](https://mlsanity.com/paper/2406.02030/) (2024)
- [Multimodal Procedural Planning via Dual Text-Image Prompting](https://mlsanity.com/paper/2305.01795/) (2023)
- [Test-Time Adaptation with CLIP Reward for Zero-Shot Generalization in Vision-Language Models](https://mlsanity.com/paper/2305.18010/) (2023)
- [MeaCap: Memory-Augmented Zero-shot Image Captioning](https://mlsanity.com/paper/2403.03715/) (2024)
- [Transferable Decoding with Visual Entities for Zero-Shot Image Captioning](https://mlsanity.com/paper/2307.16525/) (2023)
- [ConZIC: Controllable Zero-shot Image Captioning by Sampling-Based Polishing](https://mlsanity.com/paper/2303.02437/) (2023)
- [Visualize Before You Write: Imagination-Guided Open-Ended Text Generation](https://mlsanity.com/paper/2210.03765/) (2022)
- [Connect, Collapse, Corrupt: Learning Cross-Modal Tasks with Uni-Modal Data](https://mlsanity.com/paper/2401.08567/) (2024)
- [I Can't Believe There's No Images! Learning Visual Tasks Using only Language Supervision](https://mlsanity.com/paper/2211.09778/) (2022)
- [Zero-Shot Video Captioning with Evolving Pseudo-Tokens](https://mlsanity.com/paper/2207.11100/) (2022)
- [Visual Clues: Bridging Vision and Language Foundations for Image Paragraph Captioning](https://mlsanity.com/paper/2206.01843/) (2022)
- [Efficient Vision-Language Pretraining with Visual Concepts and Hierarchical Alignment](https://mlsanity.com/paper/2208.13628/) (2022)
- [Guiding Image Captioning Models Toward More Specific Captions](https://mlsanity.com/paper/2307.16686/) (2023)
- [An Empirical Study On Contrastive Search And Contrastive Decoding For Open-ended Text Generation](https://mlsanity.com/paper/2211.10797/) (2022)
- [MAGVLT: Masked Generative Vision-and-Language Transformer](https://mlsanity.com/paper/2303.12208/) (2023)
- [Improving Cross-modal Alignment with Synthetic Pairs for Text-only Image Captioning](https://mlsanity.com/paper/2312.08865/) (2023)
- [MultiCapCLIP: Auto-Encoding Prompts for Zero-Shot Multilingual Visual Captioning](https://mlsanity.com/paper/2308.13218/) (2023)
- [Learning Combinatorial Prompts for Universal Controllable Image Captioning](https://mlsanity.com/paper/2303.06338/) (2023)

## Abstract (arXiv)

Generative language models (LMs) such as GPT-2/3 can be prompted to generate text with remarkable quality. While they are designed for text-prompted generation, it remains an open question how the generation process could be guided by modalities beyond text such as images. In this work, we propose a training-free framework, called MAGIC (iMAge-Guided text generatIon with CLIP), for plugging in visual controls in the generation process and enabling LMs to perform multimodal tasks (e.g., image captioning) in a zero-shot manner. MAGIC is a simple yet efficient plug-and-play framework, which directly combines an off-the-shelf LM (i.e., GPT-2) and an image-text matching model (i.e., CLIP) for image-grounded text generation. During decoding, MAGIC influences the generation of the LM by introducing a CLIP-induced score, called magic score, which regularizes the generated result to be semantically related to a given image while being coherent to the previously generated context. Notably, the proposed decoding scheme does not involve any gradient update operation, therefore being computationally efficient. On the challenging task of zero-shot image captioning, MAGIC outperforms the state-of-the-art method by notable margins with a nearly 27 times decoding speedup. MAGIC is a flexible framework and is theoretically compatible with any text generation tasks that incorporate image grounding. In the experiments, we showcase that it is also capable of performing visually grounded story generation given both an image and a text prompt.