# Towards Semantic Equivalence of Tokenization in Multimodal LLM

arXiv: https://arxiv.org/abs/2406.05127 · HTML: https://mlsanity.com/paper/2406.05127/

## Key facts

- Cited by 45 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 106 of its 127 references that are in the map.
- First posted on arXiv 7 Jun 2024.

## 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 106)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning](https://mlsanity.com/paper/2305.06500/) (2023)
- [MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models](https://mlsanity.com/paper/2304.10592/) (2023)
- [Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations](https://mlsanity.com/paper/1602.07332/) (2016)
- [InstructPix2Pix: Learning to Follow Image Editing Instructions](https://mlsanity.com/paper/2211.09800/) (2022)
- [Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering](https://mlsanity.com/paper/1612.00837/) (2016)
- [MMBench: Is Your Multi-modal Model an All-around Player?](https://mlsanity.com/paper/2307.06281/) (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)
- [LXMERT: Learning Cross-Modality Encoder Representations from Transformers](https://mlsanity.com/paper/1908.07490/) (2019)
- [Video-LLaVA: Learning United Visual Representation by Alignment Before Projection](https://mlsanity.com/paper/2311.10122/) (2023)

## Built on by (most cited first, 30 of 45)

- [OMG-LLaVA: Bridging Image-level, Object-level, Pixel-level Reasoning and Understanding](https://mlsanity.com/paper/2406.19389/) (2024)
- [SIDA: Social Media Image Deepfake Detection, Localization and Explanation with Large Multimodal Model](https://mlsanity.com/paper/2412.04292/) (2024)
- [Text4Seg: Reimagining Image Segmentation as Text Generation](https://mlsanity.com/paper/2410.09855/) (2024)
- [Token Reduction Should Go Beyond Efficiency in Generative Models -- From Vision, Language to Multimodality](https://mlsanity.com/paper/2505.18227/) (2025)
- [Vitron: A Unified Pixel-level Vision LLM for Understanding, Generating, Segmenting, Editing](https://mlsanity.com/paper/2412.19806/) (2024)
- [What Factors Affect Multi-Modal In-Context Learning? An In-Depth Exploration](https://mlsanity.com/paper/2410.20482/) (2024)
- [AToken: A Unified Tokenizer for Vision](https://mlsanity.com/paper/2509.14476/) (2025)
- [UniFlow: A Unified Pixel Flow Tokenizer for Visual Understanding and Generation](https://mlsanity.com/paper/2510.10575/) (2025)
- [MG-LLaVA: Towards Multi-Granularity Visual Instruction Tuning](https://mlsanity.com/paper/2406.17770/) (2024)
- [ST3: Accelerating Multimodal Large Language Model by Spatial-Temporal Visual Token Trimming](https://mlsanity.com/paper/2412.20105/) (2024)
- [Towards Unified Multimodal Editing with Enhanced Knowledge Collaboration](https://mlsanity.com/paper/2409.19872/) (2024)
- [Task-Oriented Feature Compression for Multimodal Understanding via Device-Edge Co-Inference](https://mlsanity.com/paper/2503.12926/) (2025)
- [Unified Generative and Discriminative Training for Multi-modal Large Language Models](https://mlsanity.com/paper/2411.00304/) (2024)
- [JavisGPT: A Unified Multi-modal LLM for Sounding-Video Comprehension and Generation](https://mlsanity.com/paper/2512.22905/) (2025)
- [Multi-Granular Multimodal Clue Fusion for Meme Understanding](https://mlsanity.com/paper/2503.12560/) (2025)
- [PanoSent: A Panoptic Sextuple Extraction Benchmark for Multimodal Conversational Aspect-based Sentiment Analysis](https://mlsanity.com/paper/2408.09481/) (2024)
- [Dr.V: A Hierarchical Perception-Temporal-Cognition Framework to Diagnose Video Hallucination by Fine-grained Spatial-Temporal Grounding](https://mlsanity.com/paper/2509.11866/) (2025)
- [RG-SAN: Rule-Guided Spatial Awareness Network for End-to-End 3D Referring Expression Segmentation](https://mlsanity.com/paper/2412.02402/) (2024)
- [Towards Unifying Understanding and Generation in the Era of Vision Foundation Models: A Survey from the Autoregression Perspective](https://mlsanity.com/paper/2410.22217/) (2024)
- [Combating Multimodal LLM Hallucination via Bottom-Up Holistic Reasoning](https://mlsanity.com/paper/2412.11124/) (2024)
- [Position: Foundation Models Need Digital Twin Representations](https://mlsanity.com/paper/2505.03798/) (2025)
- [Elevating Visual Perception in Multimodal LLMs with Visual Embedding Distillation](https://mlsanity.com/paper/2412.09585/) (2024)
- [NeedleInATable: Exploring Long-Context Capability of Large Language Models towards Long-Structured Tables](https://mlsanity.com/paper/2504.06560/) (2025)
- [Slot-MLLM: Object-Centric Visual Tokenization for Multimodal LLM](https://mlsanity.com/paper/2505.17726/) (2025)
- [Towards Pixel-Level VLM Perception via Simple Points Prediction](https://mlsanity.com/paper/2601.19228/) (2026)
- [Measuring Agreeableness Bias in Multimodal Models](https://mlsanity.com/paper/2408.09111/) (2024)
- [The Narrow Gate: Localized Image-Text Communication in Native Multimodal Models](https://mlsanity.com/paper/2412.06646/) (2024)
- [A More Word-like Image Tokenization for MLLMs](https://mlsanity.com/paper/2605.17954/) (2026)
- [V-RAE: Rethinking Video Latent Spaces for Generation](https://mlsanity.com/paper/2608.13556/) (2026)
- [QLIP: A Dynamic Quadtree Vision Prior Enhances MLLM Performance Without Retraining](https://mlsanity.com/paper/2505.23004/) (2025)

## Abstract (arXiv)

Multimodal Large Language Models (MLLMs) have demonstrated exceptional capabilities in processing vision-language tasks. One of the crux of MLLMs lies in vision tokenization, which involves efficiently transforming input visual signals into feature representations that are most beneficial for LLMs. However, existing vision tokenizers, essential for semantic alignment between vision and language, remain problematic. Existing methods aggressively fragment visual input, corrupting the visual semantic integrity. To address this, this paper proposes a novel dynamic Semantic-Equivalent Vision Tokenizer (SeTok), which groups visual features into semantic units via a dynamic clustering algorithm, flexibly determining the number of tokens based on image complexity. The resulting vision tokens effectively preserve semantic integrity and capture both low-frequency and high-frequency visual features. The proposed MLLM (Setokim) equipped with SeTok significantly demonstrates superior performance across various tasks, as evidenced by our experimental results. The project page is at https://chocowu.github.io/SeTok-web/.