# ClawMachine: Learning to Fetch Visual Tokens for Referential Comprehension

arXiv: https://arxiv.org/abs/2406.11327 · HTML: https://mlsanity.com/paper/2406.11327/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in VLM benchmarks and visual reasoning, one of 16 directions in Multimodal LLMs / vision-language models.
- First posted on arXiv 17 Jun 2024.

## Placed in

- Multimodal LLMs / vision-language models / [VLM benchmarks and visual reasoning](https://mlsanity.com/mllm/vlm-benchmarks-and-visual-reasoning/)

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

- [Patch-as-Decodable-Token: Towards Unified Multi-Modal Vision Tasks in MLLMs](https://mlsanity.com/paper/2510.01954/) (2025)
- [Discrete Tokenization for Multimodal LLMs: A Comprehensive Survey](https://mlsanity.com/paper/2507.22920/) (2025)
- [Grounding Everything in Tokens for Multimodal Large Language Models](https://mlsanity.com/paper/2512.10554/) (2025)
- [From Structure to Synergy: A Survey of Vision-Language Perception Paradigm Evolution in Multimodal Large Language Models](https://mlsanity.com/paper/2606.26196/) (2026)
- [One Patch Is Enough: Reinforcement-Optimized Visual Token Grounding for MLLM-Based Scene Text Spotting](https://mlsanity.com/paper/2607.27902/) (2026)
- [Pay More Attention To Text In High-Resolution MLLMs](https://mlsanity.com/paper/2609.23495/) (2026)

## Abstract (arXiv)

Aligning vision and language concepts at a finer level remains an essential topic of multimodal large language models (MLLMs), particularly for tasks such as referring and grounding. Existing methods, such as proxy encoding and geometry encoding, incorporate additional syntax to encode spatial information, imposing extra burdens when communicating between language and vision modules. In this study, we propose ClawMachine, offering a new methodology that explicitly notates each entity using token collectives groups of visual tokens that collaboratively represent higher level semantics. A hybrid perception mechanism is also explored to perceive and understand scenes from both discrete and continuous spaces. Our method unifies the prompt and answer of visual referential tasks without using additional syntax. By leveraging a joint vision-language vocabulary, ClawMachine further integrates referring and grounding in an auto-regressive manner, demonstrating great potential with scaled-up pre-training data. Experiments show that ClawMachine achieves superior performance on scene-level and referential understanding tasks with higher efficiency. It also exhibits the potential to integrate multi-source information for complex visual reasoning, which is beyond the capability of many MLLMs. Our code is available at github.com/martian422/ClawMachine.