Visual Spatial Reasoning

Follow this topic Ask about this topic

Momentum

19 papers in the last four weeks, up 171% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28

Latest papers 165

All topics

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
GroundSet: A Cadastral-Grounded Dataset for Spatial Understanding with Vector Data
Mar 15, 2026Roger Ferrod, Maël Lecene, Krishna Sapkota +4VLM Evaluation Remote Sensing Image Understanding
Université Paris Cité, LIPADE, F-75006 Paris, France · Google Research
What if? Emulative Simulation with World Models for Situated Reasoning
Mar 6, 2026Ruiping Liu, Yufan Chen, Yuheng Zhang +8Visual Spatial Reasoning Video Reasoning
Karlsruhe Institute of Technology · Hunan University · ETH Zürich +2
ARK: A Dual-Axis Multimodal Retrieval Benchmark along Reasoning and Knowledge
Feb 10, 2026Yijie Lin, Guofeng Ding, Haochen Zhou +3Multimodal IR Visual Spatial Reasoning
College of Computer Science, Sichuan University, Chengdu, China · National Key Laboratory of Fundamental Algorithms and Models for Engineering Simulation, Sichuan University, China
Egocentric Bias in Vision-Language Models
Feb 10, 2026Maijunxian Wang, Yijiang Li, Bingyang Wang +6VLM Evaluation Visual Spatial Reasoning
Cognitive Science Program, University of California, Berkeley · Department of Electrical and Computer Engineering, University of California San Diego · School of Computer Science, Georgia Institute of Technology & Emory University +6
SpaRRTa: A Synthetic Benchmark for Evaluating Spatial Intelligence in Visual Foundation Models
Jan 16, 2026Turhan Can Kargin, Wojciech Jasiński, Adam Pardyl +2Spatial Reasoning Benchmarks Visual Spatial Reasoning
Faculty of Mathematics and Computer Science, Jagiellonian University, Kraków, Poland. · Doctoral School of Exact and Natural Sciences, Jagiellonian University, Kraków, Poland. · AGH University of Krakow, Kraków, Poland. +3
StereoVLA: Enhancing Vision-Language-Action Models with Stereo Vision
Dec 26, 2025Shengliang Deng, Mi Yan, Yixin Zheng +7Visual Spatial Reasoning Robotic Manipulation
Galbot · The University of Hong Kong · CFCS, School of CS, Peking University +3
Vision-Language Memory for Spatial Reasoning
Nov 25, 2025Zuntao Liu, Yi Du, Taimeng Fu +3Memory-Augmented VLMs Vision-Language Models
Spatial AI & Robotics (SAIR) Lab, University at Buffalo, USA · Stanford University, USA
MonoSR: Open-Vocabulary Spatial Reasoning from Monocular Images
Nov 24, 2025Qirui Wang, Jingyi He, Yining Pan +3Spatial Reasoning Benchmarks Visual Spatial Reasoning
Technical University of Munich, Germany · A*STAR Institute of Advanced Intelligence and Computing, Singapore · Singapore University of Technology and Design, Singapore +1
RoadBench: Benchmarking MLLMs on Fine-Grained Spatial Understanding and Reasoning under Urban Road Scenarios
Nov 22, 2025Jun Zhang, Xin Zhang, Jie Feng +5VLM Evaluation Spatial Reasoning Benchmarks
Department of Electronic Engineering, BNRist, Tsinghua University, Beijing, China · Zhongguancun Academy · Amap, Alibaba Group, Beijing, China
VisReason: A Large-Scale Dataset for Visual Chain-of-Thought Reasoning
Nov 21, 2025Lingxiao Li, Yifan Wang, Xinyan Gao +3Visual Spatial Reasoning Visual Reasoning
Boston University, Boston, MA, USA · Stony Brook University, Stony Brook, NY, USA · MMLab, The Chinese University of Hong Kong, Hong Kong SAR, China
IndustryNav: Exploring Spatial Reasoning of Embodied Agents in Dynamic Industrial Navigation
Nov 21, 2025Yifan Li, Lichi Li, Anh Dao +15Visual Spatial Reasoning Embodied Navigation
Michigan State University · Independent Researcher · University of California, Irvine +7
SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards
Nov 10, 2025Hunar Batra, Haoqin Tu, Hardy Chen +3Visual Question Answering Scene Graph Generation
University of Oxford · University of California, Santa Cruz
Seeing Isn't Orienting: A Cognitively Informed Hierarchical Benchmark for Object Orientation in MLLMs
May 27, 2025Nazia Tasnim, Keanu Nichols, Yuting Yan +4VLM Evaluation Visual Spatial Reasoning
Boston University · Work done while at Boston University; currently at Johns Hopkins University
Mem2Ego: Empowering Vision-Language Models with Global-to-Ego Memory for Long-Horizon Embodied Navigation
Feb 20, 2025Lingfeng Zhang, Yuecheng Liu, Zhanguang Zhang +19Visual Spatial Reasoning Embodied Navigation
Huawei Noah’s Ark Lab

Apr 10, 2026, cs.CVJ/K move · Enter open · S save

VisionFoundry: Teaching VLMs Visual Perception with Synthetic Images

Guanyu Zhou, Yida Yin, Wenhao Chai, Shengbang Tong+2

Princeton University · New York University

Visual Question Answering Synthetic Data Augmentation Vision-Language Models Visual Spatial Reasoning VLM Adaptation

Open paper AskPDF arXiv

Vision-language models (VLMs) still struggle with visual perception tasks such as spatial understanding and viewpoint recognition, largely because natural image datasets provide limited supervision for low-level visual skills. Can targeted synthetic supervision address these weaknesses without reference images or manual annotation? To investigate this, we introduce VisionFoundry, an automated pipeline that takes only a task name as input, uses LLMs to synthesize paired questions, answers, and text-to-image (T2I) prompts, generates images with T2I models, and filters samples via multimodal verification. With VisionFoundry, we construct VisionFoundry-10k, a synthetic VQA dataset spanning 10 perception tasks. Finetuning on VisionFoundry-10k consistently improves perception benchmarks across three open-source backbones (e.g., +6.7% on MMVP-pair and +10.5% on CV-Bench-3D for Qwen2.5-VL-3B-Instruct) while preserving broader capabilities and showing positive data scaling. The same synthetic supervision also yields consistent gains under reinforcement learning (RL) across all three backbones, and the framework remains effective under open-source synthesis and self-verification. Our findings demonstrate that automated synthetic supervision offers an effective and scalable path toward systematic VLM training.

Momentum

Related topics

Latest papers 165