Convergent Emergence of In-Context Learning Across Modalities
Controlled experiments show few-shot in-context learning emerges across six modalities including language, genomes, images, and proteins, partially supporting a convergence hypothesis.
The paper tests the Convergent Emergence Hypothesis: that few-shot in-context learning, when it emerges, shares a common cross-modality difficulty profile. A controlled framework instantiated the same task suite across six modalities: language, genome, integer sequences, time series, images, and proteins. Paired-mapping ICL emerged in all six modalities, surpassed controlled baselines, and showed correlated per-task effects in five of them, providing partial support for the hypothesis.
- Same few-shot ICL task suite instantiated in six modalities for controlled comparison
- Paired-mapping ICL emerged in all six modalities and beat controlled baselines
- Per-task difficulty effects correlated across five of six modalities
- Extends prior ICL findings from language models to autoregressive genomic models
Full article175 words · extracted from huggingface.co · click to collapse
Few-shot in-context learning (ICL), the capacity of a model to infer abstract patterns from input-output examples provided in its prompt and apply them to new inputs, has been extensively studied in large language models trained for next-token prediction on human text. Recently, few-shot ICL has been demonstrated in autoregressive genomic models as well. This raises a question: does ICL emerge broadly across domains, and if so, what common structure is shared? To address both, we develop a controlled cross-modality framework that instantiates the same task suite in a variety of modalities to test what we call the Convergent Emergence Hypothesis: the idea that few-shot ICL, when it emerges, shares a common cross-modality difficulty profile - i.e., tasks that benefit from ICL in one modality tend to benefit in others. We show that paired-mapping ICL emerges across six modalities (language, genome, integer sequences, time series, images, and proteins), surpasses controlled baselines, and has correlated per-task effects across five of them. Together, these results provide support for the Convergent Emergence Hypothesis in some modalities, but not all.
Text extracted automatically; images, tables and formatting may be missing. Original: https://huggingface.co/papers/2609.14011