# Patch-as-Decodable-Token: Towards Unified Multi-Modal Vision Tasks in MLLMs

arXiv: https://arxiv.org/abs/2510.01954 · HTML: https://mlsanity.com/paper/2510.01954/

## 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 62 of its 66 references that are in the map.
- First posted on arXiv 2 Oct 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 62)

- [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)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [LLaVA-OneVision: Easy Visual Task Transfer](https://mlsanity.com/paper/2408.03326/) (2024)
- [MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models](https://mlsanity.com/paper/2304.10592/) (2023)
- [FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning](https://mlsanity.com/paper/2307.08691/) (2023)
- [InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks](https://mlsanity.com/paper/2312.14238/) (2023)
- [InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models](https://mlsanity.com/paper/2504.10479/) (2025)
- [Video-LLaVA: Learning United Visual Representation by Alignment Before Projection](https://mlsanity.com/paper/2311.10122/) (2023)
- [Grounded Language-Image Pre-training](https://mlsanity.com/paper/2112.03857/) (2021)
- [Kosmos-2: Grounding Multimodal Large Language Models to the World](https://mlsanity.com/paper/2306.14824/) (2023)
- [Modeling Context in Referring Expressions](https://mlsanity.com/paper/1608.00272/) (2016)
- [mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality](https://mlsanity.com/paper/2304.14178/) (2023)
- [Chameleon: Mixed-Modal Early-Fusion Foundation Models](https://mlsanity.com/paper/2405.09818/) (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)
- [MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding](https://mlsanity.com/paper/2104.12763/) (2021)
- [Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation](https://mlsanity.com/paper/2406.06525/) (2024)

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

- [LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decoding](https://mlsanity.com/paper/2605.27365/) (2026)
- [MolmoPoint: Better Pointing for VLMs with Grounding Tokens](https://mlsanity.com/paper/2603.28069/) (2026)
- [WeDetect: Fast Open-Vocabulary Object Detection as Retrieval](https://mlsanity.com/paper/2512.12309/) (2025)
- [SAMTok: Representing Any Mask with Two Words](https://mlsanity.com/paper/2601.16093/) (2026)
- [PatchCue: Enhancing Vision-Language Model Reasoning with Patch-Based Visual Cues](https://mlsanity.com/paper/2603.05869/) (2026)
- [CrystaL: Spontaneous Emergence of Visual Latents in MLLMs](https://mlsanity.com/paper/2602.20980/) (2026)
- [LMMs Meet Object-Centric Vision: Understanding, Segmentation, Editing and Generation](https://mlsanity.com/paper/2604.11789/) (2026)
- [Thinking with Images as Continuous Actions: Numerical Visual Chain-of-Thought](https://mlsanity.com/paper/2602.23959/) (2026)
- [Towards Predictive, Aligned, and Scalable Robot Learning](https://mlsanity.com/paper/2607.11270/) (2026)
- [Grounding Everything in Tokens for Multimodal Large Language Models](https://mlsanity.com/paper/2512.10554/) (2025)
- [AG-VAS: Anchor-Guided Zero-Shot Visual Anomaly Segmentation with Large Multimodal Models](https://mlsanity.com/paper/2603.01305/) (2026)
- [Actor as Its Own Critic: Unifying Region Understanding and Localization via CycleGRPO](https://mlsanity.com/paper/2607.11581/) (2026)
- [RefBench-PRO: Perceptual and Reasoning Oriented Benchmark for Referring Expression Comprehension](https://mlsanity.com/paper/2512.06276/) (2025)
- [Perception-Aware Multimodal Spatial Reasoning from Monocular Images](https://mlsanity.com/paper/2603.06985/) (2026)
- [Parallelized Autoregressive Decoding for Omni-Modal Dense Video Captioning](https://mlsanity.com/paper/2607.02963/) (2026)
- [One Patch Is Enough: Reinforcement-Optimized Visual Token Grounding for MLLM-Based Scene Text Spotting](https://mlsanity.com/paper/2607.27902/) (2026)
- [PixVL: Self-Supervised Training of Pixel-Level MLLMs via a Unified Mask--Text Consistency Cycle](https://mlsanity.com/paper/2608.01354/) (2026)
- [Dynamic Resolution Routing for Efficient Egocentric Grounding](https://mlsanity.com/paper/2608.01638/) (2026)
- [PointRL: Learning Point-Level Vision-Language Grounding from Verifiable Annotation Evidence](https://mlsanity.com/paper/2608.25299/) (2026)
- [FocusDrive: Reasoning with Visual Focus for Autonomous Driving](https://mlsanity.com/paper/2609.33190/) (2026)

## Abstract (arXiv)

Multimodal large language models (MLLMs) have advanced rapidly in recent years. However, existing approaches for vision tasks often rely on indirect representations, such as generating coordinates as text for detection, which limits performance and prevents dense prediction tasks like segmentation. To overcome these challenges, we introduce Patch-as-Decodable Token (PaDT), a unified paradigm that enables MLLMs to directly generate both textual and diverse visual outputs. Central to PaDT are Visual Reference Tokens (VRTs), derived from visual patch embeddings of query images and interleaved seamlessly with LLM's output textual tokens. A lightweight decoder then transforms LLM's outputs into detection, segmentation, and grounding predictions. Unlike prior methods, PaDT processes VRTs independently at each forward pass and dynamically expands the embedding table, thus improving localization and differentiation among similar objects. We further tailor a training strategy for PaDT by randomly selecting VRTs for supervised fine-tuning and introducing a robust per-token cross-entropy loss. Our empirical studies across four visual perception and understanding tasks suggest PaDT consistently achieving state-of-the-art performance, even compared with significantly larger MLLM models. The code is available at https://github.com/Gorilla-Lab-SCUT/PaDT.