# VisualTrans: A Benchmark for Real-World Visual Transformation Reasoning

arXiv: https://arxiv.org/abs/2508.04043 · HTML: https://mlsanity.com/paper/2508.04043/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning.
- Builds on 20 of its 58 references that are in the map.
- First posted on arXiv 6 Aug 2025.

## Placed in

- LLM reasoning / [Spatial and embodied reasoning](https://mlsanity.com/lr/spatial-and-embodied-reasoning/)
- Multimodal LLMs / vision-language models / [Embodied and 3D vision-language models](https://mlsanity.com/mllm/embodied-and-3d-vision-language-models/)

## Builds on (most cited first, 20 of 20)

- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models](https://mlsanity.com/paper/2504.10479/) (2025)
- [Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs](https://mlsanity.com/paper/2503.01743/) (2025)
- [GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning](https://mlsanity.com/paper/2507.01006/) (2025)
- [Kimi-VL Technical Report](https://mlsanity.com/paper/2504.07491/) (2025)
- [EgoDex: Learning Dexterous Manipulation from Large-Scale Egocentric Video](https://mlsanity.com/paper/2505.11709/) (2025)
- [Pixtral 12B](https://mlsanity.com/paper/2410.07073/) (2024)
- [RoboRefer: Towards Spatial Referring with Reasoning in Vision-Language Models for Robotics](https://mlsanity.com/paper/2506.04308/) (2025)
- [Reason-RFT: Reinforcement Fine-Tuning for Visual Reasoning of Vision Language Models](https://mlsanity.com/paper/2503.20752/) (2025)
- [RoboBrain 2.0 Technical Report](https://mlsanity.com/paper/2507.02029/) (2025)
- [MapNav: A Novel Memory Representation via Annotated Semantic Maps for Vision-and-Language Navigation](https://mlsanity.com/paper/2502.13451/) (2025)
- [VTLA: Vision-Tactile-Language-Action Model with Preference Learning for Insertion Manipulation](https://mlsanity.com/paper/2505.09577/) (2025)
- [TLA: Tactile-Language-Action Model for Contact-Rich Manipulation](https://mlsanity.com/paper/2503.08548/) (2025)
- [GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning](https://mlsanity.com/paper/2505.11049/) (2025)
- [RoboOS: A Hierarchical Embodied Framework for Cross-Embodiment and Multi-Agent Collaboration](https://mlsanity.com/paper/2505.03673/) (2025)
- [AffordGrasp: In-Context Affordance Reasoning for Open-Vocabulary Task-Oriented Grasping in Clutter](https://mlsanity.com/paper/2503.00778/) (2025)
- [What Foundation Models can Bring for Robot Learning in Manipulation : A Survey](https://mlsanity.com/paper/2404.18201/) (2024)
- [EgoPrompt: Prompt Learning for Egocentric Action Recognition](https://mlsanity.com/paper/2508.03266/) (2025)
- [Training-free Generation of Temporally Consistent Rewards from VLMs](https://mlsanity.com/paper/2507.04789/) (2025)

## Built on by (most cited first, 12 of 12)

- [Holistic Evaluation of Multimodal LLMs on Spatial Intelligence](https://mlsanity.com/paper/2508.13142/) (2025)
- [TIGeR: Tool-Integrated Geometric Reasoning in Vision-Language Models for Robotics](https://mlsanity.com/paper/2510.07181/) (2025)
- [Towards Cross-View Point Correspondence in Vision-Language Models](https://mlsanity.com/paper/2512.04686/) (2025)
- [Scaling Up AI-Generated Image Detection with Generator-Aware Prototypes](https://mlsanity.com/paper/2512.12982/) (2025)
- [PRM-as-a-Judge: A Dense Evaluation Paradigm for Fine-Grained Robotic Auditing](https://mlsanity.com/paper/2603.21669/) (2026)
- [MathSticks: A Benchmark for Visual Symbolic Compositional Reasoning with Matchstick Puzzles](https://mlsanity.com/paper/2510.00483/) (2025)
- [Action-Sketcher: From Reasoning to Action via Visual Sketches for Long-Horizon Robotic Manipulation](https://mlsanity.com/paper/2601.01618/) (2026)
- [PReD: An LLM-based Foundation Multimodal Model for Electromagnetic Perception, Recognition, and Decision](https://mlsanity.com/paper/2603.28183/) (2026)
- [M3-Verse: A "Spot the Difference" Challenge for Large Multimodal Models](https://mlsanity.com/paper/2512.18735/) (2025)
- [SARFusion: Scene-Aware Routing Fusion for Robust Camera-LiDAR 3D Object Detection](https://mlsanity.com/paper/2609.29235/) (2026)
- [Genesis: Visual Augmentation Primitives for Multimodal Chain-of-Thought Reasoning](https://mlsanity.com/paper/2610.15565/) (2026)
- [Game2Real-Bench: Do Toy Games Reveal and Transfer to Real-World Visual Reasoning?](https://mlsanity.com/paper/2610.18834/) (2026)

## Abstract (arXiv)

Visual transformation reasoning (VTR) is a vital cognitive capability that empowers intelligent agents to understand dynamic scenes, model causal relationships, and predict future states, and thereby guiding actions and laying the foundation for advanced intelligent systems. However, existing benchmarks suffer from a sim-to-real gap, limited task complexity, and incomplete reasoning coverage, limiting their practical use in real-world scenarios. To address these limitations, we introduce VisualTrans, the first comprehensive benchmark specifically designed for VTR in real-world human-object interaction scenarios. VisualTrans encompasses 12 semantically diverse manipulation tasks and systematically evaluates three essential reasoning dimensions - spatial, procedural, and quantitative - through 6 well-defined subtask types. The benchmark features 472 high-quality question-answer pairs in various formats, including multiple-choice, open-ended counting, and target enumeration. We introduce a scalable data construction pipeline built upon first-person manipulation videos, which integrates task selection, image pair extraction, automated metadata annotation with large multimodal models, and structured question generation. Human verification ensures the final benchmark is both high-quality and interpretable. Evaluations of various state-of-the-art vision-language models show strong performance in static spatial tasks. However, they reveal notable shortcomings in dynamic, multi-step reasoning scenarios, particularly in areas like intermediate state recognition and transformation sequence planning. These findings highlight fundamental weaknesses in temporal modeling and causal reasoning, providing clear directions for future research aimed at developing more capable and generalizable VTR systems. The dataset and code are available at https://github.com/WangYipu2002/VisualTrans.