How Finely Can Vision-Language Models See Biology? Bio-VQA: A Benchmark for Taxonomic, Morphological, Spatial and Individual Reasoning
cs.CV, cs.AI
Submitted: 2026-11-03
Updated: 2026-11-03
Code: https://github.com/Imageomics/Bio-VQA
Terminology
Sources
- Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone
- Multimodal Foundation Models for Zero-shot Animal Species Recognition in Camera Trap Images
- Gemma 3 Technical Report
- The Llama 3 Herd of Models
- Pixtral 12B
- Multispecies Animal Re-ID Using a Large Community-Curated Dataset
- Qwen2.5-VL Technical Report
- Qwen3-VL Technical Report
- BeetleVerse: A Study on Taxonomic Classification of Ground Beetles
- A continental-scale dataset of ground beetles with high-resolution images and validated morphological trait measurements
- PlantExpertVQA: A Visual Question Answering Dataset for Benchmarking Vision-Language Models in Plant Science
- Evaluating Large Language Models for IUCN Red List Species Information
- InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency
- AgroCoT: A Chain-of-Thought Benchmark for Evaluating Reasoning in Vision-Language Models for Agriculture
- J-EDI QA: Benchmark for deep-sea organism-specific multimodal LLM
- InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs