# Bongard-RWR+: Real-World Representations of Fine-Grained Concepts in Bongard Problems

arXiv: https://arxiv.org/abs/2508.12026 · HTML: https://mlsanity.com/paper/2508.12026/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 49 of its 83 references that are in the map.
- First posted on arXiv 16 Aug 2025.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)

## Builds on (most cited first, 30 of 49)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [Training Compute-Optimal Large Language Models](https://mlsanity.com/paper/2203.15556/) (2022)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks](https://mlsanity.com/paper/2312.14238/) (2023)
- [Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond](https://mlsanity.com/paper/2308.12966/) (2023)
- [DeBERTa: Decoding-enhanced BERT with Disentangled Attention](https://mlsanity.com/paper/2006.03654/) (2020)
- [Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling](https://mlsanity.com/paper/2412.05271/) (2024)
- [MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers](https://mlsanity.com/paper/2002.10957/) (2020)
- [MiniCPM-V: A GPT-4V Level MLLM on Your Phone](https://mlsanity.com/paper/2408.01800/) (2024)
- [Effective Data Augmentation With Diffusion Models](https://mlsanity.com/paper/2302.07944/) (2023)
- [RAVEN: A Dataset for Relational and Analogical Visual rEasoNing](https://mlsanity.com/paper/1903.02741/) (2019)
- [Meta-Baseline: Exploring Simple Meta-Learning for Few-Shot Learning](https://mlsanity.com/paper/2003.04390/) (2020)
- [StableRep: Synthetic Images from Text-to-Image Models Make Strong Visual Representation Learners](https://mlsanity.com/paper/2306.00984/) (2023)
- [Fake it till you make it: Learning transferable representations from synthetic ImageNet clones](https://mlsanity.com/paper/2212.08420/) (2022)
- [Measuring abstract reasoning in neural networks](https://mlsanity.com/paper/1807.04225/) (2018)
- [Classification Accuracy Score for Conditional Generative Models](https://mlsanity.com/paper/1905.10887/) (2019)
- [RLAIF-V: Open-Source AI Feedback Leads to Super GPT-4V Trustworthiness](https://mlsanity.com/paper/2405.17220/) (2024)
- [Scaling Laws of Synthetic Images for Model Training ... for Now](https://mlsanity.com/paper/2312.04567/) (2023)
- [Generative Models as a Data Source for Multiview Representation Learning](https://mlsanity.com/paper/2106.05258/) (2021)
- [Abstraction and Analogy-Making in Artificial Intelligence](https://mlsanity.com/paper/2102.10717/) (2021)
- [Learning Vision from Models Rivals Learning Vision from Data](https://mlsanity.com/paper/2312.17742/) (2023)
- [Bongard-LOGO: A New Benchmark for Human-Level Concept Learning and Reasoning](https://mlsanity.com/paper/2010.00763/) (2020)
- [Learning to Make Analogies by Contrasting Abstract Relational Structure](https://mlsanity.com/paper/1902.00120/) (2019)
- [Deep Learning Methods for Abstract Visual Reasoning: A Survey on Raven's Progressive Matrices](https://mlsanity.com/paper/2201.12382/) (2022)
- [Learning Representations that Support Extrapolation](https://mlsanity.com/paper/2007.05059/) (2020)

## Built on by (most cited first, 7 of 7)

- [Do AI Models Perform Human-like Abstract Reasoning Across Modalities?](https://mlsanity.com/paper/2510.02125/) (2025)
- [Toward Cognitive Supersensing in Multimodal Large Language Model](https://mlsanity.com/paper/2602.01541/) (2026)
- [Synthesizing Visual Concepts as Vision-Language Programs](https://mlsanity.com/paper/2511.18964/) (2025)
- [Reasoning or Pattern Matching? Probing Large Vision-Language Models with Visual Puzzles](https://mlsanity.com/paper/2601.13705/) (2026)
- [Playing ZendoWorld: Challenging AI Agents on Active Visual Concept Induction](https://mlsanity.com/paper/2607.08233/) (2026)
- [Thinking in Pictures: A Systematic Benchmark for Reasoning-driven Image Generation](https://mlsanity.com/paper/2609.02864/) (2026)
- [World-Time Compute with Verified Code World Models](https://mlsanity.com/paper/2609.09163/) (2026)

## Abstract (arXiv)

Bongard Problems (BPs) provide a challenging testbed for abstract visual reasoning (AVR), requiring models to identify visual concepts fromjust a few examples and describe them in natural language. Early BP benchmarks featured synthetic black-and-white drawings, which might not fully capture the complexity of real-world scenes. Subsequent BP datasets employed real-world images, albeit the represented concepts are identifiable from high-level image features, reducing the task complexity. Differently, the recently released Bongard-RWR dataset aimed at representing abstract concepts formulated in the original BPs using fine-grained real-world images. Its manual construction, however, limited the dataset size to just 60 instances, constraining evaluation robustness. In this work, we introduce Bongard-RWR+, a BP dataset composed of 5,400 instances that represent original BP abstract concepts using real-world-like images generated via a vision language model (VLM) pipeline. Building on Bongard-RWR, we employ Pixtral-12B to describe manually curated images and generate new descriptions aligned with the underlying concepts, use Flux.1-dev to synthesize images from these descriptions, and manually verify that the generated images faithfully reflect the intended concepts. We evaluate state-of-the-art VLMs across diverse BP formulations, including binary and multiclass classification, as well as textual answer generation. Our findings reveal that while VLMs can recognize coarse-grained visual concepts, they consistently struggle with discerning fine-grained concepts, highlighting limitations in their reasoning capabilities.