Research map / Vision-language and multimodal / Human and embodied modeling
Machine Number Sense: A Dataset of Visual Arithmetic Problems for Abstract and Relational Reasoning
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Add geometric context information to symbolic search | Pure Symbolic Search · MNS | accuracy: 52.15% -> 56.70% | Helped |
| Add geometric context information to symbolic search | Pure Symbolic Search · Combination holistic | accuracy: 62.98% -> 64.38% | Helped |
| Add geometric context information to symbolic search | Pure Symbolic Search · Combination analytic | accuracy: 56.83% -> 56.08% | Hurt |
| Add geometric context information to symbolic search | Pure Symbolic Search · Composition holistic | accuracy: 22.17% -> 29.81% | Helped |
| Add geometric context information to symbolic search | Pure Symbolic Search · Composition analytic | accuracy: 53.73% -> 61.84% | Helped |
| Add geometric context information to symbolic search | Pure Symbolic Search · Partition holistic | accuracy: 51.29% -> 59.70% | Helped |
| Add geometric context information to symbolic search | Pure Symbolic Search · Partition analytic | accuracy: 71.60% -> 67.59% | Hurt |
| Use a ResNet-18 visual backbone rather than the other tested neural-network models | Neural-network baselines · MNS | accuracy: 25.29% | Helped |
Closest papers by meaning
- DARR: A Dual-Branch Arithmetic Regression Reasoning Framework for Solving Machine Number Reasoning (AAAI 2025 · similarity 0.90)
- MV-MATH: Evaluating Multimodal Math Reasoning in Multi-Visual Contexts (CVPR 2025 · similarity 0.88)
- CogFlow: Bridging Perception and Reasoning through Knowledge Internalization for Visual Mathematical Problem Solving (ICLR 2026 · similarity 0.88)
- DynaMath: A Dynamic Visual Benchmark for Evaluating Mathematical Reasoning Robustness of Vision Language Models (ICLR 2025 · similarity 0.88)
- We-Math 2.0: A Versatile MathBook System for Incentivizing Visual Mathematical Reasoning (ICLR 2026 · similarity 0.88)
- Measuring Multimodal Mathematical Reasoning with MATH-Vision Dataset (NeurIPS 2024 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.