mlsanityData to 7 Oct 2026

SITUATE -- Synthetic Object Counting Dataset for VLM training

arXiv 2602.00108 ↗First posted 26 Jan 2026cs.CV cs.AIcited by 2

On the map: Multimodal LLMs / vision-language models → VLM benchmarks and visual reasoning

Abstract (arXiv)

We present SITUATE, a novel dataset designed for training and evaluating Vision Language Models on counting tasks with spatial constraints. The dataset bridges the gap between simple 2D datasets like VLMCountBench and often ambiguous real-life datasets like TallyQA, which lack control over occlusions and spatial composition. Experiments show that our dataset helps to improve generalization for out-of-distribution images, since a finetune of Qwen VL 2.5 7B on SITUATE improves accuracy on the Pixmo count test data, but not vice versa. We cross validate this by comparing the model performance across established other counting benchmarks and against an equally sized fine-tuning set derived from Pixmo count.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Placed in VLM benchmarks and visual reasoning, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 17 of its 24 references that are in the map. First posted on arXiv 26 Jan 2026.

Builds on

17 of 24 references.

Closest ancestors · 10

Same direction, newest first

  1. 2025Your Vision-Language Model Can't Even Count to 20: Exposing the Failures of VLMs in Compositional Counting6 Oct
  2. 2025VLM@school -- Evaluation of AI image understanding on German middle school knowledge13 Jun
  3. 2025SDVPT: Semantic-Driven Visual Prompt Tuning for Open-World Object Counting24 Apr
  4. 2025Benchmarking Vision Language Models on German Factual Data15 Apr
  5. 2024LVLM-COUNT: Enhancing the Counting Ability of Large Vision-Language Models1 Dec
  6. 2024Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Models25 Sep
  7. 2024RelationVLM: Making Large Vision-Language Models Understand Visual Relations19 Mar
  8. 2024PIN: Positional Insert Unlocks Object Localisation Abilities in VLMs13 Feb
  9. 2023CLIP-Count: Towards Text-Guided Zero-Shot Object Counting12 May
  10. 2023Teaching CLIP to Count to Ten23 Feb

Other references · 7

  1. 2025Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAscited by 491
  2. 2018TallyQA: Answering Complex Counting Questionscited by 152
  3. 2024Good at captioning, bad at counting: Benchmarking GPT-4V on Earth observation datacited by 39
  4. 2025Synthetic Data is an Elegant GIFT for Continual Vision-Language Modelscited by 21
  5. 2025CrowdVLM-R1: Expanding R1 Ability to Vision Language Model for Crowd Counting using Fuzzy Group Relative Policy Rewardcited by 15
  6. 2023Zero-Shot Object Counting with Language-Vision Modelscited by 9
  7. 2024Synthetic Data Generation with Large Language Models for Personalized Community Question Answeringcited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026The MixCount Dataset: Bridging the Data Gap for Open-Vocabulary Object Countingcited by 1
  2. 2026Object Counting Across Modalities: Taxonomies, Benchmarks, Applications, and Open Challengescited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026The Count Is There, but Misaligned: Understanding and Correcting Counting Failures in VLMs
  2. 2025Assessing the Visual Enumeration Abilities of Specialized Counting Architectures and Vision-Language Models
  3. 2025[De|Re]constructing VLMs' Reasoning in Counting
  4. 2026HoloCount: A Holistic Visual Counting Benchmark for MLLMs
  5. 2025Can Current AI Models Count What We Mean, Not What They See? A Benchmark and Systematic Evaluation
  6. 2026Counting Circuits: Mechanistic Interpretability of Visual Reasoning in Large Vision-Language Models
  7. 2025CountQA: How Well Do MLLMs Count in the Wild?
  8. 2025Object Counting with GPT-4o and GPT-5: A Comparative Study