mlsanityData to 14 Oct 2026

On Data Synthesis and Post-training for Visual Abstract Reasoning

arXiv 2504.01324 ↗First posted 2 Apr 2025cs.CV cs.AI cs.CLcited by 3

On the map: LLM reasoning → Multimodal reasoning

also in 2 more
Abstract (arXiv)

This paper is a pioneering work attempting to address abstract visual reasoning (AVR) problems for large vision-language models (VLMs). We make a common LLaVA-NeXT 7B model capable of perceiving and reasoning about specific AVR problems, surpassing both open-sourced (e.g., Qwen-2-VL-72B) and closed-sourced powerful VLMs (e.g., GPT-4o) with significant margin. This is a great breakthrough since almost all previous VLMs fail or show nearly random performance on representative AVR benchmarks. Our key success is our innovative data synthesis and post-training process, aiming to fully relieve the task difficulty and elicit the model to learn, step by step. Our 7B model is also shown to be behave well on AVR without sacrificing common multimodal comprehension abilities. We hope our paper could serve as an early effort in this area and would inspire further research in abstract visual reasoning.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Placed in Multimodal reasoning, one of 17 directions in LLM reasoning. Builds on 32 of its 36 references that are in the map. First posted on arXiv 2 Apr 2025.

Builds on

32 of 36 references.

Closest ancestors · 11

Same direction, newest first

  1. 2024Image-of-Thought Prompting for Visual Reasoning Refinement in Multimodal Large Language Models22 May
  2. 2024MARVEL: Multidimensional Abstraction and Reasoning through Visual Evaluation and Learning21 Apr
  3. 2024Plug-and-Play Grounding of Reasoning in Multimodal Large Language Models28 Mar
  4. 2024PuzzleVQA: Diagnosing Multimodal Reasoning Challenges of Language Models with Abstract Visual Patterns20 Mar
  5. 2024Measuring Multimodal Mathematical Reasoning with MATH-Vision Dataset22 Feb
  6. 2024The Curious Case of Nonverbal Abstract Reasoning with Multi-Modal Large Language Models22 Jan
  7. 2023Boosting the Power of Small Multimodal Reasoning Models to Match Larger Models with Self-Consistency Training23 Nov
  8. 2023MMBench: Is Your Multi-modal Model an All-around Player?12 Jul
  9. 2023Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Models8 Mar
  10. 2023Multimodal Chain-of-Thought Reasoning in Language Models2 Feb
  11. 2022Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering20 Sep

Other references · 21

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  2. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 9,379
  3. 2023BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Modelscited by 6,137
  4. 2025Qwen2.5-VL Technical Reportcited by 5,587
  5. 2023Improved Baselines with Visual Instruction Tuningcited by 4,418
  6. 2022Flamingo: a Visual Language Model for Few-Shot Learningcited by 4,386
  7. 2024Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolutioncited by 4,234
  8. 2023InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuningcited by 2,876
  9. 2023MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Modelscited by 2,711
  10. 2023Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyondcited by 2,224
  11. 2019Towards VQA Models That Can Readcited by 1,718
  12. 2021Multitask Prompted Training Enables Zero-Shot Task Generalizationcited by 1,470
9 more
  1. 2023MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilitiescited by 1,239
  2. 2022Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Taskscited by 1,076
  3. 2023ShareGPT4V: Improving Large Multi-Modal Models with Better Captionscited by 1,005
  4. 2023CogVLM: Visual Expert for Pretrained Language Modelscited by 708
  5. 2024Is DPO Superior to PPO for LLM Alignment? A Comprehensive Studycited by 262
  6. 2021GeoQA: A Geometric Question Answering Benchmark Towards Multimodal Numerical Reasoningcited by 228
  7. 2025Step-Video-T2V Technical Report: The Practice, Challenges, and Future of Video Foundation Modelcited by 168
  8. 2024Self-Supervised Visual Preference Alignmentcited by 31
  9. 2024Continual SFT Matches Multimodal RLHF with Negative Supervisioncited by 4

Built on by

Cited by year

Citing papers per year: 2025: 3.

3 papers.

  1. 2025Reinforcement Learning Meets Large Language Models: A Survey of Advancements and Applications Across the LLM Lifecyclecited by 35
  2. 2025Do AI Models Perform Human-like Abstract Reasoning Across Modalities?cited by 10
  3. 2025MARS2 2025 Challenge on Multimodal Reasoning: Datasets, Methods, Results, Discussion, and Outlookcited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2025Beyond Perception: Evaluating Abstract Visual Reasoning through Multi-Stage Task
  2. 2024From the Least to the Most: Building a Plug-and-Play Visual Reasoner via Data Synthesis
  3. 2026Learning Adaptive Reasoning Paths for Efficient Visual Reasoning
  4. 2025VisRes Bench: On Evaluating the Visual Reasoning Capabilities of VLMs
  5. 2025Beyond Task-Specific Reasoning: A Unified Conditional Generative Framework for Abstract Visual Reasoning
  6. 2024A Unified View of Abstract Visual Reasoning Problems
  7. 2025VisuRiddles: Fine-grained Perception is a Primary Bottleneck for Multimodal Large Language Models in Abstract Visual Reasoning
  8. 2025Diagnosing Visual Reasoning: Challenges, Insights, and a Path Forward