Synthetic Data Generation for VLMs

VLM: Vision-Language Model

Follow this topic Ask about this topic

Latest papers

13 papers2 papers in the last four weeks, down 33% on the four weeks before. 0.0% of all new papers.

Learning to Read Braille: Benchmarking and Improving Braille Recognition Capabilities of VLMs
Oct 26, 2026Kartik Jangra, Atharva Gawane, Siddharth Pulipaka +2Synthetic Data Generation for VLMs VLM Evaluation
Nilekani Centre at AI4Bharat · Indian Institute of Technology, Madras
RoboReason: Boosting Robotics-Relevant VLM Reasoning Through Scalable Data Generation
Oct 24, 2026Sagnik Anupam, Utkarsh Lal, Aneesh Edara +5VLMs for Robotics Visual Reasoning
University of Pennsylvania
Instruction Mining From Images: Constructing a Synthetic Dataset for Multimodal Learning ILSP DCVLR Competition Submission
Oct 14, 2026Eleni E. Kasoura, Dimitrios Damianos, Georgios Paraskevopoulos +1Visual Instruction Tuning Synthetic Data Generation for VLMs
Institute of Language and Speech Processing Athena Research Center Athens, GR 151 25
PrismGPT: Proxy-Guided Learning for Region-Aware Photo Editing with Self-Synthesized Reasoning
Sep 21, 2026Ke Zhao, Hue Nguyen, Abhijith Punnappurath +3VLM Adaptation Synthetic Data Generation for VLMs
AI Center-Toronto, Samsung Electronics Toronto, Ontario, Canada
SpatialBlock: Enhancing Spatial Intelligence in LVLMs via Synthetic Block-Stacking Problem
Sep 7, 2026Soohyun Ryu, Sohee Kim, Eunho YangSynthetic Data Generation for VLMs Visual Spatial Reasoning
KAIST South Korea · KAIST & AITRICS South Korea
From Terminology to Diagrams: Visual-Instruction Generation for Scientific Diagram Understanding
Sep 1, 2026Raul Ortega, José Manuel Gómez-PérezSynthetic Data Generation for Language Models Synthetic Data Generation for VLMs
Language Technology Research Laboratory Expert.ai 17 Henri Dunant, 28036 Madrid, Spain
Trace: A Taxonomy-Guided Environment for Multidomain Visual Reasoning
Jul 22, 2026Md Tanvirul AlamSynthetic Data Generation Synthetic Data Generation for VLMs
Rochester Institute of Technology Rochester, NY, USA
Ryze: Evidence-Enriched Data Synthesis from Biomedical Papers
May 30, 2026Yeqi Huang, Yue Chen, Yanwei Ye +2VLM Adaptation Synthetic Data Generation
University of Edinburgh, United Kingdom
VisionFoundry: Teaching VLMs Visual Perception with Synthetic Images
Apr 10, 2026Guanyu Zhou, Yida Yin, Wenhao Chai +3Visual Question Answering Synthetic Data Augmentation
Princeton University · New York University
HopChain: Multi-Hop Data Synthesis for Generalizable Vision-Language Reasoning
Mar 17, 2026Shenzhi Wang, Shixuan Liu, Jing Zhou +8Reasoning for VLMs VLM Reasoning
Qwen Team, Alibaba Inc. · LeapLab, Tsinghua University
Feynman: Knowledge-Infused Diagramming Agent for Scalable Visual Designs
Mar 13, 2026Zixin Wen, Yifu Cai, Kyle Lee +5Synthetic Data Generation for VLMs Synthetic Data Generation
Carnegie Mellon University Pittsburgh, PA 15213, USA
DocDjinn: Controllable Synthetic Document Generation with VLMs and Handwriting Diffusion
Feb 25, 2026Marcel Lamott, Saifullah Saifullah, Nauman Riaz +11Synthetic Data Generation Synthetic Data Augmentation
RheinMain University of Applied Sciences, Wiesbaden, Germany · German Research Center for Artificial Intelligence, Kaiserslautern, Germany · DeepReader GmbH, Kaiserslautern, Germany +2
VisualSphinx: Large-Scale Synthetic Vision Logic Puzzles for RL
May 29, 2025Yichen Feng, Zhangchen Xu, Fengqing Jiang +5Synthetic Data Generation for VLMs Visual Reasoning
University of Washington · Western Washington University

Oct 26, 2026J/K move · Enter open · S save

Learning to Read Braille: Benchmarking and Improving Braille Recognition Capabilities of VLMs

Kartik Jangra, Atharva Gawane, Siddharth Pulipaka, Hemachandran Karah+1

Nilekani Centre at AI4Bharat · Indian Institute of Technology, Madras

Synthetic Data Generation for VLMs VLM Evaluation Synthetic Data Generation

Open paper AskPDF arXiv

Despite rapid progress in visual understanding and document transcription, modern vision-language models (VLMs) struggle with a fundamental accessibility task: reading Braille from images. We introduce BrailleBench, a manually curated benchmark of 259 real-world Grade-1 and Grade-2 Braille images. We evaluate proprietary, open-weight, OCR-specialized, and tool-assisted multimodal systems and find that standalone general-purpose models perform poorly at directly transcribing Braille images, whereas tool-assisted systems perform much better. We design a synthetic Braille generation pipeline with diverse layouts and image perturbations. A 2B VLM model trained on our synthetic data reaches 87% exact match on Grade-1 and 61% on Grade-2 BrailleBench, outperforming standalone VLMs and achieving the highest Grade-2 exact match score among the evaluated systems. We further show that high accuracy on synthetic validation data does not guarantee high accuracy on real photographs in our experiments: models trained on prior synthetic data reach up to 96% on their synthetic validation set but at most 3.26% on Grade-1 BrailleBench. Our results identify an accessibility-relevant capability gap in multimodal systems and show that targeted synthetic supervision can improve real-world Braille transcription.