# Multimodal Taxonomic Conditioning for Generative Plankton Imagery

arXiv: https://arxiv.org/abs/2609.11673 · HTML: https://mlsanity.com/paper/2609.11673/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 18 references that are in the map.
- First posted on arXiv 10 Sep 2026.

## Builds on (most cited first, 14 of 14)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [DINOv3](https://mlsanity.com/paper/2508.10104/) (2025)
- [BioCLIP: A Vision Foundation Model for the Tree of Life](https://mlsanity.com/paper/2311.18803/) (2023)
- [BioCLIP 2: Emergent Properties from Scaling Hierarchical Contrastive Learning](https://mlsanity.com/paper/2505.23883/) (2025)
- [Ranking Info Noise Contrastive Estimation: Boosting Contrastive Learning via Ranked Positives](https://mlsanity.com/paper/2201.11736/) (2022)
- [TaxaDiffusion: Progressively Trained Diffusion Model for Fine-Grained Species Generation](https://mlsanity.com/paper/2506.01923/) (2025)
- [FineDiffusion: Scaling up Diffusion Models for Fine-grained Image Generation with 10,000 Classes](https://mlsanity.com/paper/2402.18331/) (2024)
- [Self-Supervised Pretraining for Fine-Grained Plankton Recognition](https://mlsanity.com/paper/2503.11341/) (2025)
- [Planktonzilla: Multimodal dataset and models for understanding plankton ecosystems](https://mlsanity.com/paper/2606.00080/) (2026)

## Abstract (arXiv)

Automated plankton imaging produces severely long-tailed datasets, where the rare taxa of greatest ecological interest have too few images to train or evaluate classifiers reliably. We generate synthetic plankton imagery conditioned on taxonomy: a CLIP encoder is adapted on a large plankton corpus with a ranked contrastive objective extended to deep, ragged taxonomies, then frozen to condition a parameter-efficient diffusion transformer. We evaluate synthetic sample quality on distributional fidelity and downstream classifier utility.