More info:
📄 Paper: arxiv.org/abs/2511.08512
🗂️ Data: huggingface.co/datasets/bos...
💻 Code: github.com/visipedia/cl...
🌐 Project website: cleverbirds-benchmark.github.io

5/5

Even strong sequence models struggle here, predicting how recognition evolves is genuinely hard.
CleverBirds sets a new challenge for understanding visual learning dynamics.
4/5

Collected in collaboration with #eBird, CleverBirds spans 10K+ species and 40K learners across six years.

It’s one of the largest datasets for visual expertise, tracking how people build recognition ability over time.

3/5

In CleverBirds, ML models have to predict human learning: inferring skills form past answers to anticipate future recognition.

2/5