# HiMTok: Learning Hierarchical Mask Tokens for Image Segmentation with Large Multimodal Model

arXiv: https://arxiv.org/abs/2503.13026 · HTML: https://mlsanity.com/paper/2503.13026/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- Placed in Visual token pruning and efficiency, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 77 of its 88 references that are in the map.
- First posted on arXiv 17 Mar 2025.

## Placed in

- Multimodal LLMs / vision-language models / [Visual token pruning and efficiency](https://mlsanity.com/mllm/visual-token-pruning-and-efficiency/)

## Builds on (most cited first, 30 of 77)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks](https://mlsanity.com/paper/2312.14238/) (2023)
- [Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering](https://mlsanity.com/paper/1612.00837/) (2016)
- [Masked-attention Mask Transformer for Universal Image Segmentation](https://mlsanity.com/paper/2112.01527/) (2021)
- [Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond](https://mlsanity.com/paper/2308.12966/) (2023)
- [Evaluating Object Hallucination in Large Vision-Language Models](https://mlsanity.com/paper/2305.10355/) (2023)
- [MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models](https://mlsanity.com/paper/2306.13394/) (2023)
- [Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling](https://mlsanity.com/paper/2412.05271/) (2024)
- [Generating Diverse High-Fidelity Images with VQ-VAE-2](https://mlsanity.com/paper/1906.00446/) (2019)
- [Scaling Autoregressive Models for Content-Rich Text-to-Image Generation](https://mlsanity.com/paper/2206.10789/) (2022)
- [MiniCPM-V: A GPT-4V Level MLLM on Your Phone](https://mlsanity.com/paper/2408.01800/) (2024)
- [Semantic Understanding of Scenes through the ADE20K Dataset](https://mlsanity.com/paper/1608.05442/) (2016)
- [Modeling Context in Referring Expressions](https://mlsanity.com/paper/1608.00272/) (2016)
- [How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites](https://mlsanity.com/paper/2404.16821/) (2024)
- [Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction](https://mlsanity.com/paper/2404.02905/) (2024)
- [Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic](https://mlsanity.com/paper/2306.15195/) (2023)
- [Generation and Comprehension of Unambiguous Object Descriptions](https://mlsanity.com/paper/1511.02283/) (2015)
- [COCO-Stuff: Thing and Stuff Classes in Context](https://mlsanity.com/paper/1612.03716/) (2016)
- [A Diagram Is Worth A Dozen Images](https://mlsanity.com/paper/1603.07396/) (2016)
- [LISA: Reasoning Segmentation via Large Language Model](https://mlsanity.com/paper/2308.00692/) (2023)
- [OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework](https://mlsanity.com/paper/2202.03052/) (2022)

## Built on by (most cited first, 20 of 20)

- [SAMTok: Representing Any Mask with Two Words](https://mlsanity.com/paper/2601.16093/) (2026)
- [Text4Seg++: Advancing Image Segmentation via Generative Language Modeling](https://mlsanity.com/paper/2509.06321/) (2025)
- [Percept-WAM: Perception-Enhanced World-Awareness-Action Model for Robust End-to-End Autonomous Driving](https://mlsanity.com/paper/2511.19221/) (2025)
- [Discrete Tokenization for Multimodal LLMs: A Comprehensive Survey](https://mlsanity.com/paper/2507.22920/) (2025)
- [Unlocking the Potential of MLLMs in Referring Expression Segmentation via a Light-weight Mask Decoder](https://mlsanity.com/paper/2508.04107/) (2025)
- [ALTo: Adaptive-Length Tokenizer for Autoregressive Mask Generation](https://mlsanity.com/paper/2505.16495/) (2025)
- [LMMs Meet Object-Centric Vision: Understanding, Segmentation, Editing and Generation](https://mlsanity.com/paper/2604.11789/) (2026)
- [ARGenSeg: Image Segmentation with Autoregressive Image Generation Model](https://mlsanity.com/paper/2510.20803/) (2025)
- [LlamaSeg: Image Segmentation via Autoregressive Mask Generation](https://mlsanity.com/paper/2505.19422/) (2025)
- [SegCompass: Exploring Interpretable Alignment with Sparse Autoencoders for Enhanced Reasoning Segmentation](https://mlsanity.com/paper/2605.22658/) (2026)
- [Encode Once, Decode Never: Reusing Audio LM Internals for Efficient Temporal Localization](https://mlsanity.com/paper/2602.10230/) (2026)
- [PixelEyes: Decoupling Perception and Reasoning for Pinpoint Visual Evidence Seeking](https://mlsanity.com/paper/2607.00115/) (2026)
- [Actor as Its Own Critic: Unifying Region Understanding and Localization via CycleGRPO](https://mlsanity.com/paper/2607.11581/) (2026)
- [Learning Visual Affordance from Audio](https://mlsanity.com/paper/2512.02005/) (2025)
- [ForensicsTok: Forensics-Guided Tokenized Modeling for Image Tampering Localization](https://mlsanity.com/paper/2606.24538/) (2026)
- [From Structure to Synergy: A Survey of Vision-Language Perception Paradigm Evolution in Multimodal Large Language Models](https://mlsanity.com/paper/2606.26196/) (2026)
- [InstanceControl: Controllable Complex Image Generation without Instance Labeling](https://mlsanity.com/paper/2606.31924/) (2026)
- [Goal-oriented Navigation Instruction Generation with Tour Video Priors](https://mlsanity.com/paper/2608.08596/) (2026)
- [PANORAMA: Panoptic Grounded Captioning via Mask Proposal Selection](https://mlsanity.com/paper/2609.19143/) (2026)
- [Segment Where You Look: Attention as the Interface Between Language Models and Segmenters](https://mlsanity.com/paper/2610.18729/) (2026)

## Abstract (arXiv)

The remarkable performance of large multimodal models (LMMs) has attracted significant interest from the image segmentation community. To align with the next-token-prediction paradigm, current LMM-driven segmentation methods either use object boundary points to represent masks or introduce special segmentation tokens, whose hidden states are decoded by a segmentation model requiring the original image as input. However, these approaches often suffer from inadequate mask representation and complex architectures, limiting the potential of LMMs. In this work, we propose the Hierarchical Mask Tokenizer (HiMTok), which represents segmentation masks with up to 32 tokens and eliminates the need for the original image during mask de-tokenization. HiMTok allows for compact and coarse-to-fine mask representations, aligning well with the LLM next-token-prediction paradigm and facilitating the direct acquisition of segmentation capabilities. We develop a 3-stage training recipe for progressive learning of segmentation and visual capabilities, featuring a hierarchical mask loss for effective coarse-to-fine learning. Additionally, we enable bidirectional information flow, allowing conversion between bounding boxes and mask tokens to fully leverage multi-task training potential. Extensive experiments demonstrate that our method achieves state-of-the-art performance across various segmentation tasks,while also enhancing visual grounding and maintaining overall visual understanding.