JHU study finds in-context learning emerges across language, genome, protein and image models alike
DanielKhashabi · x · 2026-09-16
New research from JHU CLSP, "Convergent Emergence of In-Context Learning Across Modalities," shows that models trained on language, genome, protein, image, timeseries, and integer sequences all exhibit few-shot in-context learning.
Notably, their ICL performance is highly correlated across modalities, suggesting ICL is a convergent emergent phenomenon rather than something unique to language models.
Related event: JHU study finds in-context learning emerges across six modalities(4 posts)→
More from Research
- Asynchronous Flow Map Language Models Generate All Tokens in a Single Forward Pass — kalyan_kpl · 2026-11-02
- NVIDIA's Kumo Is a Family of Four Tabular Foundation Models, Not Just One — pandeyparul · 2026-11-02
- Economist Aaroth: fast agreement dynamics survive without Bayesian updates or accurate priors — Aaroth · 2026-11-02
- ELLIS names 160 new ML Fellows and Scholars for 2025–2026 — JJitsev · 2026-11-02
- Meme turn 50: Aumann's 'Agreeing to Disagree' paper anniversary — Aaroth · 2026-11-02
- Anthropic: analysts unknowingly adopted their agent's secret lean 86% of the time — shoumikgoswami · 2026-11-02