# Benchmarking Vision-Language Models on Synapse Detection and Proofreading in Connectomics

arXiv: https://arxiv.org/abs/2609.36492 · HTML: https://mlsanity.com/paper/2609.36492/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in VLM benchmarks and visual reasoning, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 15 of its 25 references that are in the map.
- First posted on arXiv 29 Sep 2026.

## Placed in

- Multimodal LLMs / vision-language models / [VLM benchmarks and visual reasoning](https://mlsanity.com/mllm/vlm-benchmarks-and-visual-reasoning/)

## Builds on (most cited first, 15 of 15)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models](https://mlsanity.com/paper/2504.10479/) (2025)
- [Gemma 4 Technical Report](https://mlsanity.com/paper/2607.02770/) (2026)
- [Superhuman Accuracy on the SNEMI3D Connectomics Challenge](https://mlsanity.com/paper/1706.00120/) (2017)
- [Synaptic Cleft Segmentation in Non-Isotropic Volume Electron Microscopy of the Complete Drosophila Brain](https://mlsanity.com/paper/1805.02718/) (2018)
- [Guided Proofreading of Automatic Segmentations for Connectomics](https://mlsanity.com/paper/1704.00848/) (2017)
- [Synaptic Partner Assignment Using Attentional Voxel Association Networks](https://mlsanity.com/paper/1904.09947/) (2019)
- [ConnectomeBench: Can LLMs Proofread the Connectome?](https://mlsanity.com/paper/2511.05542/) (2025)
- [X-Ray2EM: Uncertainty-Aware Cross-Modality Image Reconstruction from X-Ray to Electron Microscopy in Connectomics](https://mlsanity.com/paper/2303.00882/) (2023)
- [ConnectomeBench2: A Unified Benchmark for Automated Connectomic Proofreading](https://mlsanity.com/paper/2606.21116/) (2026)

## Abstract (arXiv)

We benchmarked vision-language models (VLMs) on the decisions annotators take when inspecting electron microscopy images in connectomics: synapse detection (presence and polarity) and proofreading (split errors and merge errors). For synapse detection, we evaluated 19 open and 2 closed models across various architectures and sizes under zero-shot, four-shot in-context learning and LoRA settings, against specialist models, on datasets constructed by us using public resources. For proofreading, we evaluated 3 open and 2 closed models on the ConnectomeBench2 dataset, with cross-species transfer from fly and mouse to human and zebrafish. Most models were at chance zero-shot; a few examples helped mainly the closed and largest open ones. LoRA on a few thousand labels brought open models level with specialist models. When evaluated on unseen species, the best adapted VLMs outperformed specialist models trained on the same data in identifying merge errors. The project will be publicly available upon acceptance.