# O3SLM: Open Weight, Open Data, and Open Vocabulary Sketch-Language Model

arXiv: https://arxiv.org/abs/2511.14368 · HTML: https://mlsanity.com/paper/2511.14368/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in VLM benchmarks and visual reasoning, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 28 of its 48 references that are in the map.
- First posted on arXiv 18 Nov 2025.

## Placed in

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

## Builds on (most cited first, 28 of 28)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering](https://mlsanity.com/paper/1612.00837/) (2016)
- [Learning Robust Global Representations by Penalizing Local Predictive Power](https://mlsanity.com/paper/1905.13549/) (2019)
- [ShareGPT4V: Improving Large Multi-Modal Models with Better Captions](https://mlsanity.com/paper/2311.12793/) (2023)
- [SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehension](https://mlsanity.com/paper/2307.16125/) (2023)
- [DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding](https://mlsanity.com/paper/2412.10302/) (2024)
- [GeoChat: Grounded Large Vision-Language Model for Remote Sensing](https://mlsanity.com/paper/2311.15826/) (2023)
- [Zero-Shot Composed Image Retrieval with Textual Inversion](https://mlsanity.com/paper/2303.15247/) (2023)
- [Pic2Word: Mapping Pictures to Words for Zero-shot Composed Image Retrieval](https://mlsanity.com/paper/2302.03084/) (2023)
- [SVGDreamer: Text Guided SVG Generation with Diffusion Model](https://mlsanity.com/paper/2312.16476/) (2023)
- [Photo-Sketching: Inferring Contour Drawings from Images](https://mlsanity.com/paper/1901.00542/) (2019)
- [SketchyCOCO: Image Generation from Freehand Scene Sketches](https://mlsanity.com/paper/2003.02683/) (2020)
- [CLIPascene: Scene Sketching with Different Types and Levels of Abstraction](https://mlsanity.com/paper/2211.17256/) (2022)
- [Picture that Sketch: Photorealistic Image Generation from Abstract Sketches](https://mlsanity.com/paper/2303.11162/) (2023)
- [SceneTrilogy: On Human Scene-Sketch and its Complementarity with Photo and Text](https://mlsanity.com/paper/2204.11964/) (2022)
- [It's All About Your Sketch: Democratising Sketch Control in Diffusion Models](https://mlsanity.com/paper/2403.07234/) (2024)
- [Sketch-Guided Object Localization in Natural Images](https://mlsanity.com/paper/2008.06551/) (2020)
- [What Can Human Sketches Do for Object Detection?](https://mlsanity.com/paper/2303.15149/) (2023)
- [SketchVideo: Sketch-based Video Generation and Editing](https://mlsanity.com/paper/2503.23284/) (2025)
- [SwiftSketch: A Diffusion Model for Image-to-Vector Sketch Generation](https://mlsanity.com/paper/2502.08642/) (2025)
- [You'll Never Walk Alone: A Sketch and Text Duet for Fine-Grained Image Retrieval](https://mlsanity.com/paper/2403.07222/) (2024)
- [SketchGPT: Autoregressive Modeling for Sketch Generation and Recognition](https://mlsanity.com/paper/2405.03099/) (2024)
- [SketchFusion: Learning Universal Sketch Features through Fusing Foundation Models](https://mlsanity.com/paper/2503.14129/) (2025)
- [Query-guided Attention in Vision Transformers for Localizing Objects Using a Single Sketch](https://mlsanity.com/paper/2303.08784/) (2023)
- [SketchYourSeg: Mask-Free Subjective Image Segmentation via Freehand Sketches](https://mlsanity.com/paper/2501.16022/) (2025)

## Abstract (arXiv)

While Large Vision Language Models (LVLMs) are increasingly deployed in real-world applications, their ability to interpret abstract visual inputs remains limited. Specifically, they struggle to comprehend hand-drawn sketches, a modality that offers an intuitive means of expressing concepts that are difficult to describe textually. We identify the primary bottleneck as the absence of a large-scale dataset that jointly models sketches, photorealistic images, and corresponding natural language instructions. To address this, we present two key contributions: (1) a new, large-scale dataset of image-sketch-instruction triplets designed to facilitate both pretraining and instruction tuning, and (2) O3SLM, an LVLM trained on this dataset. Comprehensive evaluations on multiple sketch-based tasks: (a) object localization, (b) counting, (c) image retrieval i.e., (SBIR and fine-grained SBIR), and (d) visual question answering (VQA); while incorporating the three existing sketch datasets, namely QuickDraw!, Sketchy, and Tu Berlin, along with our generated SketchVCL dataset, show that O3SLM achieves state-of-the-art performance, substantially outperforming existing LVLMs in sketch comprehension and reasoning.