AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

Benchmarking Vision-Language Models for Microscopic Plant Image Understanding

Tianqi Wei, Xin Yu, Zhi Chen, Scott C Chapman, Zi Helen Huang

ECCV 2026 · Vision-language and multimodal › Multimodal LLMs · approach: Multimodal LLM benchmarks · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add three-step chain-of-thought prompting (ablation)Gemini 2.5-Pro · PlantMicro identificationmacro accuracy: 62.93 -> 61.28Hurt
add three-step chain-of-thought prompting (ablation)QwenVLM-7B · PlantMicro identificationmacro accuracy: 51.98 -> 57.99Improved
add 1-shot in-context example (ablation)GPT-5 · PlantMicro localizationmAP@0.5: 56.66 -> 53.73Hurt
add 1-shot in-context example (ablation)QwenVLM-7B · PlantMicro localizationmAP@0.5: 65.05 -> 62.79Hurt
add 1-shot in-context example (ablation)QwenVLM-7B · PlantMicro countingMAE: 3.38 -> 3.11Improved
add 1-shot in-context example (ablation)GPT-5 · PlantMicro countingMAE: 2.07 -> 2.28Hurt
add retrieval-augmented most-similar demonstration (ablation)QwenVLM-7B · PlantMicro identificationmacro accuracy: 51.98 -> 68.63Improved
add retrieval-augmented demonstration (ablation)LLaVA-13B · PlantMicro identificationmacro accuracy: 37.24 -> 57.75Improved
add retrieval-augmented demonstration (ablation)LLaVA-Next-13B · PlantMicro identificationmacro accuracy: 41.20 -> 58.18Improved
closed-source vs open-source VLMsVLMs · PlantMicro identificationmacro accuracy: 51.98 (QwenVLM-7B) -> 63.08 (Gemini 2.5-Flash)Improved
closed-source vs open-source on localizationVLMs · PlantMicro localizationmAP@0.5: GPT-5 56.66 vs QwenVLM-7B 65.05Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy