# Towards More Unified In-context Visual Understanding

arXiv: https://arxiv.org/abs/2312.02520 · HTML: https://mlsanity.com/paper/2312.02520/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 51 of its 60 references that are in the map.
- First posted on arXiv 5 Dec 2023.

## Builds on (most cited first, 30 of 51)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity](https://mlsanity.com/paper/2101.03961/) (2021)
- [MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models](https://mlsanity.com/paper/2304.10592/) (2023)
- [GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding](https://mlsanity.com/paper/2006.16668/) (2020)
- [ImageBind: One Embedding Space To Bind Them All](https://mlsanity.com/paper/2305.05665/) (2023)
- [Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivity](https://mlsanity.com/paper/2104.08786/) (2021)
- [mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality](https://mlsanity.com/paper/2304.14178/) (2023)
- [GLaM: Efficient Scaling of Language Models with Mixture-of-Experts](https://mlsanity.com/paper/2112.06905/) (2021)
- [Scaling Vision with Sparse Mixture of Experts](https://mlsanity.com/paper/2106.05974/) (2021)
- [Multimodal Few-Shot Learning with Frozen Language Models](https://mlsanity.com/paper/2106.13884/) (2021)
- [NExT-GPT: Any-to-Any Multimodal LLM](https://mlsanity.com/paper/2309.05519/) (2023)
- [OpenFlamingo: An Open-Source Framework for Training Large Autoregressive Vision-Language Models](https://mlsanity.com/paper/2308.01390/) (2023)
- [Otter: A Multi-Modal Model with In-Context Instruction Tuning](https://mlsanity.com/paper/2305.03726/) (2023)
- [Language Is Not All You Need: Aligning Perception with Language Models](https://mlsanity.com/paper/2302.14045/) (2023)
- [Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language Tasks](https://mlsanity.com/paper/2208.10442/) (2022)
- [VisionLLM: Large Language Model is also an Open-Ended Decoder for Vision-Centric Tasks](https://mlsanity.com/paper/2305.11175/) (2023)
- [MetaICL: Learning to Learn In Context](https://mlsanity.com/paper/2110.15943/) (2021)
- [ST-MoE: Designing Stable and Transferable Sparse Expert Models](https://mlsanity.com/paper/2202.08906/) (2022)
- [Images Speak in Images: A Generalist Painter for In-Context Visual Learning](https://mlsanity.com/paper/2212.02499/) (2022)
- [Generating Images with Multimodal Language Models](https://mlsanity.com/paper/2305.17216/) (2023)
- [Visual Prompting via Image Inpainting](https://mlsanity.com/paper/2209.00647/) (2022)

## Built on by (most cited first, 10 of 10)

- [Number it: Temporal Grounding Videos like Flipping Manga](https://mlsanity.com/paper/2411.10332/) (2024)
- [Visual Prompting in Multimodal Large Language Models: A Survey](https://mlsanity.com/paper/2409.15310/) (2024)
- [VisualCloze: A Universal Image Generation Framework via Visual In-Context Learning](https://mlsanity.com/paper/2504.07960/) (2025)
- [Image Segmentation in Foundation Model Era: A Survey](https://mlsanity.com/paper/2408.12957/) (2024)
- [Next Token Prediction Towards Multimodal Intelligence: A Comprehensive Survey](https://mlsanity.com/paper/2412.18619/) (2024)
- [Unleashing In-context Learning of Autoregressive Models for Few-shot Image Manipulation](https://mlsanity.com/paper/2412.01027/) (2024)
- [ContextNav: Towards Agentic Multimodal In-Context Learning](https://mlsanity.com/paper/2510.04560/) (2025)
- [Context-Aware Weakly Supervised Image Manipulation Localization with SAM Refinement](https://mlsanity.com/paper/2503.20294/) (2025)
- [Learning to Focus and Precise Cropping: A Reinforcement Learning Framework with Information Gaps and Grounding Loss for MLLMs](https://mlsanity.com/paper/2603.27494/) (2026)
- [Personalized Object Identification and Localization via In-Context Inference with Vision-Language Models](https://mlsanity.com/paper/2607.00357/) (2026)

## Abstract (arXiv)

The rapid advancement of large language models (LLMs) has accelerated the emergence of in-context learning (ICL) as a cutting-edge approach in the natural language processing domain. Recently, ICL has been employed in visual understanding tasks, such as semantic segmentation and image captioning, yielding promising results. However, existing visual ICL framework can not enable producing content across multiple modalities, which limits their potential usage scenarios. To address this issue, we present a new ICL framework for visual understanding with multi-modal output enabled. First, we quantize and embed both text and visual prompt into a unified representational space, structured as interleaved in-context sequences. Then a decoder-only sparse transformer architecture is employed to perform generative modeling on them, facilitating in-context learning. Thanks to this design, the model is capable of handling in-context vision understanding tasks with multimodal output in a unified pipeline.Experimental results demonstrate that our model achieves competitive performance compared with specialized models and previous ICL baselines. Overall, our research takes a further step toward unified multimodal in-context learning.