We lifted 4 functions out of this paper's own repositories and ran 4 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| ey242/kiva | canonical | 4 of 4 |
| Function | Status | Where it lives |
|---|---|---|
| crop | Ran | ey242/kiva/transformation/Transformations-KiVA.py code served (permissive licence) · get_code("c211e3bc1baf40e2") |
| reflect_image | Ran | ey242/kiva/transformation/Transformations-KiVA.py code served (permissive licence) · get_code("b6382991a62b952c") |
| selector | Ran | ey242/kiva/transformation/Transformations-KiVA.py code served (permissive licence) · get_code("72dce48fc6c09eb5") |
| update_concept_result | Ran | ey242/kiva/chat_systems/chat_system_single_image_kiva.py code served (permissive licence) · get_code("d4fc91a99ea03ee3") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
This paper investigates visual analogical reasoning in large multimodal models (LMMs) compared to human adults and children. A "visual analogy" is an abstract rule inferred from one image and applied to another. While benchmarks exist for testing visual reasoning in LMMs, they require advanced skills and omit basic visual analogies that even young children can make. Inspired by developmental psychology, we propose a new benchmark of 4,300 visual transformations of everyday objects to test LMMs on visual analogical reasoning and compare them to children (ages three to five) and to adults. We structure the evaluation into three stages: identifying what changed (e.g., color, number, etc.), how it changed (e.g., added one object), and applying the rule to new scenarios. Our findings show that while GPT-o1, GPT-4V, LLaVA-1.5, and MANTIS identify the "what" effectively, they struggle with quantifying the "how" and extrapolating this rule to new objects. In contrast, children and adults exhibit much stronger analogical reasoning at all three stages. Additionally, the strongest tested model, GPT-o1, performs better in tasks involving simple surface-level visual attributes like color and size, correlating with quicker human adult response times. Conversely, more complex tasks such as number, rotation, and reflection, which necessitate extensive cognitive processing and understanding of extrinsic spatial properties in the physical world, present more significant challenges. Altogether, these findings highlight the limitations of training models on data that primarily consists of 2D images and text.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2407.17773")
get_code_for_paper("2407.17773")
have("2407.17773")
Connect an agent — have() is free.