Convergent Emergence of In-Context Learning Across Modalities

Papers

arxiv:2609.14011

Published on Sep 12

· Submitted by

Daniel Khashabi on Sep 16

· Center for Language and Speech Processing @ JHU

Upvote

3

Authors:

Nathan Breslow ,

,

,

,

,

Abstract

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.

View arXiv page View PDF Add to collection

Community

danyaljj

Paper submitter 7 days ago

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 nexttoken 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.

librarian-bot

6 days ago

This is an automated message from the Librarian Bot. I found the following papers similar to this paper.

The following papers were recommended by the Semantic Scholar API

• TwinICL: Diagnosing Multimodal In-Context Learning through Paired Counterfactuals (2026)

• In-Context Collapse in Vision-Language Models and How to Mitigate it? (2026)

• AudioICL-Bench: A Benchmark for Large Audio Language Model In-Context Learning (2026)

• Information Abundance Paradox: Long-Context Training Undermines Parametric Knowledge (2026)

• The Illusion of Replacement: Rethinking Specialized Machine Learning Models in the Foundation Model Era (2026)

• Attention Sensitivity Is Not Enough: Dissociating Attention-Level and Behavioural In-Context Learning under Fine-Tuning (2026)

• Seeing or Knowing? Visual Context Sensitivity in Multimodal Large Language Models (2026)

Please give a thumbs up to this comment if you found it helpful!

If you want recommendations for any Paper on HF Mirror checkout this Space

You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: @librarian-bot recommend

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment

Upvote

3

Get this paper in your agent:

hf papers read 2609.14011

Don't have the latest CLI?

curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2609.14011 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2609.14011 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2609.14011 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.