# BioCLIP 2: Emergent Properties from Scaling Hierarchical Contrastive Learning

arXiv: https://arxiv.org/abs/2505.23883 · HTML: https://mlsanity.com/paper/2505.23883/

## Key facts

- Cited by 50 papers in the map (data through 14 Oct 2026).
- Builds on 38 of its 79 references that are in the map.
- First posted on arXiv 29 May 2025.

## Builds on (most cited first, 30 of 38)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [Emergent Abilities of Large Language Models](https://mlsanity.com/paper/2206.07682/) (2022)
- [iCaRL: Incremental Classifier and Representation Learning](https://mlsanity.com/paper/1611.07725/) (2016)
- [Experience Replay for Continual Learning](https://mlsanity.com/paper/1811.11682/) (2018)
- [Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks](https://mlsanity.com/paper/1604.02878/) (2016)
- [PaLI: A Jointly-Scaled Multilingual Language-Image Model](https://mlsanity.com/paper/2209.06794/) (2022)
- [Prevalence of Neural Collapse during the terminal phase of deep learning training](https://mlsanity.com/paper/2008.08186/) (2020)
- [Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Ugly](https://mlsanity.com/paper/1707.00600/) (2017)
- [GroupViT: Semantic Segmentation Emerges from Text Supervision](https://mlsanity.com/paper/2202.11094/) (2022)
- [A Geometric Analysis of Neural Collapse with Unconstrained Features](https://mlsanity.com/paper/2105.02375/) (2021)
- [Generalized Category Discovery](https://mlsanity.com/paper/2201.02609/) (2022)
- [SimpleShot: Revisiting Nearest-Neighbor Classification for Few-Shot Learning](https://mlsanity.com/paper/1911.04623/) (2019)
- [Benchmarking Representation Learning for Natural World Image Collections](https://mlsanity.com/paper/2103.16483/) (2021)
- [BioCLIP: A Vision Foundation Model for the Tree of Life](https://mlsanity.com/paper/2311.18803/) (2023)
- [Seeing biodiversity: perspectives in machine learning for wildlife conservation](https://mlsanity.com/paper/2110.12951/) (2021)
- [Neural Collapse: A Review on Modelling Principles and Generalization](https://mlsanity.com/paper/2206.04041/) (2022)
- [Are All Losses Created Equal: A Neural Collapse Perspective](https://mlsanity.com/paper/2210.02192/) (2022)
- [PlantDoc: A Dataset for Visual Plant Disease Detection](https://mlsanity.com/paper/1911.10317/) (2019)
- [AnomalyDINO: Boosting Patch-based Few-shot Anomaly Detection with DINOv2](https://mlsanity.com/paper/2405.14529/) (2024)
- [Emergent Abilities in Large Language Models: A Survey](https://mlsanity.com/paper/2503.05788/) (2025)
- [TaxaBind: A Unified Embedding Space for Ecological Applications](https://mlsanity.com/paper/2411.00683/) (2024)
- [INQUIRE: A Natural World Text-to-Image Retrieval Benchmark](https://mlsanity.com/paper/2411.02537/) (2024)
- [Meta-Album: Multi-domain Meta-Dataset for Few-Shot Image Classification](https://mlsanity.com/paper/2302.08909/) (2023)
- [A Step Towards Worldwide Biodiversity Assessment: The BIOSCAN-1M Insect Dataset](https://mlsanity.com/paper/2307.10455/) (2023)

## Built on by (most cited first, 30 of 50)

- [The LLM Bottleneck: Why Open-Source Vision LLMs Struggle with Hierarchical Visual Recognition](https://mlsanity.com/paper/2505.24840/) (2025)
- [AVA-Bench: Atomic Visual Ability Benchmark for Vision Foundation Models](https://mlsanity.com/paper/2506.09082/) (2025)
- [X-MoGen: Unified Motion Generation across Humans and Animals](https://mlsanity.com/paper/2508.05162/) (2025)
- [Taxonomy-Aware Representation Alignment for Hierarchical Visual Recognition with Large Multimodal Models](https://mlsanity.com/paper/2603.00431/) (2026)
- [BioCAP: Exploiting Synthetic Captions Beyond Labels in Biological Foundation Models](https://mlsanity.com/paper/2510.20095/) (2025)
- [Modality Alignment across Trees on Heterogeneous Hyperbolic Manifolds](https://mlsanity.com/paper/2510.27391/) (2025)
- [Future of Edge AI in biodiversity monitoring](https://mlsanity.com/paper/2602.13496/) (2026)
- [Lessons and Open Questions from a Unified Study of Camera-Trap Species Recognition Over Time](https://mlsanity.com/paper/2603.20509/) (2026)
- [TaxaAdapter: Vision Taxonomy Models are Key to Fine-grained Image Generation over the Tree of Life](https://mlsanity.com/paper/2603.26128/) (2026)
- [Finer-Personalization Rank: Fine-Grained Retrieval Examines Identity Preservation for Personalized Generation](https://mlsanity.com/paper/2512.19026/) (2025)
- [Plant Taxonomy Meets Plant Counting: A Fine-Grained, Taxonomic Dataset for Counting Hundreds of Plant Species](https://mlsanity.com/paper/2603.21229/) (2026)
- [ReefNet: A Large-Scale Dataset and Benchmark for Fine-Grained Coral Reef Recognition](https://mlsanity.com/paper/2510.16822/) (2025)
- [Nearest-Class Mean and Logits Agreement for Wildlife Open-Set Recognition](https://mlsanity.com/paper/2510.17338/) (2025)
- [Towards Open-Ended Visual Scientific Discovery with Sparse Autoencoders](https://mlsanity.com/paper/2511.17735/) (2025)
- [CHIPS: Efficient CLIP Adaptation via Curvature-aware Hybrid Influence-based Data Selection](https://mlsanity.com/paper/2511.18519/) (2025)
- [BarcodeMamba+: Advancing State-Space Models for Fungal Biodiversity Research](https://mlsanity.com/paper/2512.15931/) (2025)
- [Leveraging Data to Say No: Memory Augmented Plug-and-Play Selective Prediction](https://mlsanity.com/paper/2601.22570/) (2026)
- [Energy-Efficient Plant Monitoring via Knowledge Distillation](https://mlsanity.com/paper/2604.27178/) (2026)
- [Planktonzilla: Multimodal dataset and models for understanding plankton ecosystems](https://mlsanity.com/paper/2606.00080/) (2026)
- [PRIMA: Boosting Animal Mesh Recovery with Biological Priors and Test-Time Adaptation](https://mlsanity.com/paper/2606.02366/) (2026)
- [MoE-ViE: Mixture of Experts Vision Encoder for Efficient Image and Video Understanding](https://mlsanity.com/paper/2608.17402/) (2026)
- [From Images to Insights: Explainable Biodiversity Monitoring with Plain Language Habitat Explanations](https://mlsanity.com/paper/2506.10559/) (2025)
- [MARVIS: Modality Adaptive Reasoning over VISualizations](https://mlsanity.com/paper/2507.01544/) (2025)
- [Hyperbolic Multimodal Representation Learning for Biological Taxonomies](https://mlsanity.com/paper/2508.16744/) (2025)
- [Bridging Domain Gaps for Fine-Grained Moth Classification Through Expert-Informed Adaptation and Foundation Model Priors](https://mlsanity.com/paper/2508.20089/) (2025)
- [BioAutoML-NAS: An End-to-End AutoML Framework for Multimodal Insect Classification via Neural Architecture Search on Large-Scale Biodiversity Data](https://mlsanity.com/paper/2510.05888/) (2025)
- [Visual Species Recognition with Large Multimodal Models as Post-Hoc Correctors](https://mlsanity.com/paper/2512.15748/) (2025)
- [A Geolocation-Aware Multimodal Approach for Ecological Prediction](https://mlsanity.com/paper/2601.08750/) (2026)
- [Expert Knowledge-Guided Decision Calibration for Accurate Fine-Grained Tree Species Classification](https://mlsanity.com/paper/2601.16498/) (2026)
- [Compact Hypercube Embeddings for Fast Text-based Wildlife Observation Retrieval](https://mlsanity.com/paper/2601.22783/) (2026)

## Abstract (arXiv)

Foundation models trained at scale exhibit remarkable emergent behaviors, learning new capabilities beyond their initial training objectives. We find such emergent behaviors in biological vision models via large-scale contrastive vision-language training. To achieve this, we first curate TreeOfLife-200M, comprising 214 million images of living organisms, the largest and most diverse biological organism image dataset to date. We then train BioCLIP 2 on TreeOfLife-200M to distinguish different species. Despite the narrow training objective, BioCLIP 2 yields extraordinary accuracy when applied to various biological visual tasks such as habitat classification and trait prediction. We identify emergent properties in the learned embedding space of BioCLIP 2. At the inter-species level, the embedding distribution of different species aligns closely with functional and ecological meanings (e.g., beak sizes and habitats). At the intra-species level, instead of being diminished, the intra-species variations (e.g., life stages and sexes) are preserved and better separated in subspaces orthogonal to inter-species distinctions. We provide formal proof and analyses to explain why hierarchical supervision and contrastive objectives encourage these emergent properties. Crucially, our results reveal that these properties become increasingly significant with larger-scale training data, leading to a biologically meaningful embedding space.