Visual Program Synthesis

Follow this topic Ask about this topic

Latest papers

9 papers1 paper in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.

VisualCoding: Learning Executable Skills for Reliable Visual Reasoning
Oct 9, 2026Liu Jiaqi, Jin Ruinan, Li XiaoxiaoVisual Program Synthesis Visually Grounded Reasoning
Department of Electrical and Computer Engineering, University of British Columbia · Vector Institute
FoldingAgent: Inferring Parametric Origami Procedures from Demonstration Videos
Aug 31, 2026Maya Moriya, Sigal Raab, Yael Vinker +1Tool-Using Vision-Language Agents Video Reasoning
Weizmann Institute of Science, Rehovot, Israel · MIT, Boston, USA
CommerceVibe: Learning to Design E-Commerce Creatives as Executable Visual Code via Dual-Feedback Reinforcement Learning
Aug 28, 2026Yajiao Xu, Jin Zhang, Jiangbo Ai +4Visual Program Synthesis RL for Generative Models
Tongji University · Alibaba Group
MentalThink: Shaping Thoughts in Mental SVG World
Jul 3, 2026Kangheng Lin, Jisheng Yin, Dingming Li +11Visual Spatial Reasoning Latent Visual Reasoning
State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications · University of Chinese Academy of Sciences · StepFun
Bridging the Sim-to-Real Gap in Semiconductor Visual Program Synthesis via Input Binarization
Jun 1, 2026Yusuke Ohtsubo, Kota Dohi, Koichiro Yawata +2Synthetic-to-Real Domain Adaptation Industrial Inspection
Hitachi, Ltd. R&D Group, Tokyo, Japan
ShapeCodeBench: A Renewable Benchmark for Perception-to-Program Reconstruction of Synthetic Shape Scenes
May 12, 2026Shivam KumarSynthetic Benchmark Generation Visual Program Synthesis
Independent Researcher
Prospective Compression in Human Abstraction Learning
May 11, 2026Leonardo Hernandez Cano, Ivan Zareski, Luisa El Amouri +6Program Synthesis Visual Program Synthesis
1Massachusetts Institute of Technology · 2Dalhousie University · University of Edinburgh +1
Visual Set Program Synthesizer
Mar 16, 2026Zehua Cheng, Wei Dai, Wenhu Zhang +2Visual Program Synthesis Visual Reasoning
Department of Computer Science, University of Oxford · Department of Computer Science and Engineering, Hong Kong University of Science and Technology · Institute of Logic and Computation, TU Wien
pySpatial: Generating 3D Visual Programs for Zero-Shot Spatial Reasoning
Mar 1, 2026Zhanpeng Luo, Ce Zhang, Silong Yong +6Visual Program Synthesis 3D Spatial Reasoning
Carnegie Mellon University · University of Pittsburgh · University of Michigan

Oct 9, 2026J/K move · Enter open · S save

VisualCoding: Learning Executable Skills for Reliable Visual Reasoning

Liu Jiaqi, Jin Ruinan, Li Xiaoxiao

Department of Electrical and Computer Engineering, University of British Columbia · Vector Institute

Visual Program Synthesis Visually Grounded Reasoning

Open paper AskPDF arXiv

Learning reusable skills can improve visual reasoning agents, yet applying a skill still requires the agent to implement or invoke a procedure and produce the final answer. Errors and hallucinations at these steps can prevent acquired experience from translating into reliable single-run performance. We propose VisualCoding, which combines execution-guided acquisition of reusable visual programs with direct adoption of their answers on applicable inputs. Execution-Guided Program Acquisition composes visual primitives and additional code into family-level solvers, then iteratively tests and revises them on labeled training instances. Scope-Aware Direct Execution runs a retained solver and returns its valid in-scope answer. We evaluate VisualCoding on four models across four benchmarks spanning 69 task families. VisualCoding exceeds the strongest evaluated baseline in mean accuracy by 4.45 percentage points with Gemini-3.1-Pro and by 14.78 points when reusing the frozen Pro-acquired artifacts with Flash-Lite. Ablations support execution-guided acquisition and show that direct execution outperforms textual or callable reuse of the same programs. Code is available at https://github.com/jiaq-liu/VisualCoding.