# UGround: Towards Unified Visual Grounding with Unrolled Transformers

arXiv: https://arxiv.org/abs/2510.03853 · HTML: https://mlsanity.com/paper/2510.03853/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 50 of its 56 references that are in the map.
- First posted on arXiv 4 Oct 2025.

## Builds on (most cited first, 30 of 50)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (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)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models](https://mlsanity.com/paper/2304.10592/) (2023)
- [Masked-attention Mask Transformer for Universal Image Segmentation](https://mlsanity.com/paper/2112.01527/) (2021)
- [SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation](https://mlsanity.com/paper/1511.00561/) (2015)
- [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)
- [Generation and Comprehension of Unambiguous Object Descriptions](https://mlsanity.com/paper/1511.02283/) (2015)
- [Panoptic Segmentation](https://mlsanity.com/paper/1801.00868/) (2018)
- [Path Aggregation Network for Instance Segmentation](https://mlsanity.com/paper/1803.01534/) (2018)
- [LISA: Reasoning Segmentation via Large Language Model](https://mlsanity.com/paper/2308.00692/) (2023)
- [Panoptic Feature Pyramid Networks](https://mlsanity.com/paper/1901.02446/) (2019)
- [Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP](https://mlsanity.com/paper/2210.04150/) (2022)
- [Otter: A Multi-Modal Model with In-Context Instruction Tuning](https://mlsanity.com/paper/2305.03726/) (2023)
- [Segment Everything Everywhere All at Once](https://mlsanity.com/paper/2304.06718/) (2023)
- [VisionLLM: Large Language Model is also an Open-Ended Decoder for Vision-Centric Tasks](https://mlsanity.com/paper/2305.11175/) (2023)
- [GLaMM: Pixel Grounding Large Multimodal Model](https://mlsanity.com/paper/2311.03356/) (2023)
- [MAttNet: Modular Attention Network for Referring Expression Comprehension](https://mlsanity.com/paper/1801.08186/) (2018)
- [CRIS: CLIP-Driven Referring Image Segmentation](https://mlsanity.com/paper/2111.15174/) (2021)
- [LAVT: Language-Aware Vision Transformer for Referring Image Segmentation](https://mlsanity.com/paper/2112.02244/) (2021)

## Built on by (most cited first, 14 of 14)

- [MolmoWeb: Open Visual Web Agent and Open Data for the Open Web](https://mlsanity.com/paper/2604.08516/) (2026)
- [OmegaUse: Building a General-Purpose GUI Agent for Autonomous Task Execution](https://mlsanity.com/paper/2601.20380/) (2026)
- [MagicGUI-RMS: A Multi-Agent Reward Model System for Self-Evolving GUI Agents via Automated Feedback Reflux](https://mlsanity.com/paper/2601.13060/) (2026)
- [SE-GA: Memory-Augmented Self-Evolution for GUI Agents](https://mlsanity.com/paper/2605.16883/) (2026)
- [VISTAQA: Benchmarking Joint Visual Question Answering and Pixel-Level Evidence](https://mlsanity.com/paper/2605.20676/) (2026)
- [GUI-CEval: A Hierarchical and Comprehensive Chinese Benchmark for Mobile GUI Agents](https://mlsanity.com/paper/2603.15039/) (2026)
- [From Off-Policy to On-Policy: Enhancing GUI Agents via Bi-level Expert-to-Policy Assimilation](https://mlsanity.com/paper/2601.05787/) (2026)
- [Towards Scalable Lightweight GUI Agents via Multi-role Orchestration](https://mlsanity.com/paper/2604.13488/) (2026)
- [ScaleWoB: Guiding GUI Agents with Coding Agents via Large-Scale Environmental Synthesis](https://mlsanity.com/paper/2605.25160/) (2026)
- [Skill-Guided Continuation Distillation for GUI Agents](https://mlsanity.com/paper/2606.18890/) (2026)
- [MacAgentBench: Benchmarking AI Agents on Real-World macOS Desktop](https://mlsanity.com/paper/2606.22557/) (2026)
- [One Forward Beats Two: InnerZoom for Accurate and Efficient GUI Grounding](https://mlsanity.com/paper/2606.30084/) (2026)
- [Covering Human Action Space for Computer Use: Data Synthesis and Benchmark](https://mlsanity.com/paper/2605.12501/) (2026)
- [DeCo: Efficient Decouple-to-Couple Learning for Multi-Task Visual Grounding](https://mlsanity.com/paper/2609.24409/) (2026)

## Abstract (arXiv)

We present UGround, a Unified visual Grounding paradigm that dynamically selects intermediate layers across Unrolled transformers as ``mask as prompt,'' diverging from the prevailing pipeline that leverages the fixed last hidden layer as ``texttt<SEG> as prompt.'' UGround addresses two primary challenges posed by the prevailing paradigm: (1) its reliance on the fixed last hidden layer, which sequentially amplifies cumulative errors arising from layer-by-layer propagation without intermediate correction, and (2) its use of texttt<SEG> as a prompt, which implicitly projects textual embeddings into visual space without explicit spatial cues (e.g., coordinates). Central to UGround is Policy-Prompted Masking, which comprises two key components: Stochastic Skip Connection (SSC) and Mask as Prompt (MasP). SSC is a reinforcement learning policy that, via stochastic sampling, allows each texttt<SEG> token to slide across unrolled transformer layers, enabling dynamic layer selection at which it connects to the vision model (e.g., SAM) in a skip-connection fashion. Given the selected hidden layer, MasP uses the similarity map derived from the texttt<SEG> token and image tokens as a soft logit mask to prompt SAM for mask generation, offering explicit spatial cues through its activation regions. To validate the effectiveness of UGround, we, for the first time, have unified visual grounding within a single framework from an attribute perspective, spanning from traditional refer expression segmentation to newly proposed reasoning segmentation, single-target to multi-target, positive query to false premise (empty target). All code and models are publicly available at https://github.com/rui-qian/UGround.