SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2404.11225 · 2024

In-Context Learning State Vector with Inner and Momentum Optimization

arXiv · PDF · Open in the Atlas

Code that ran

5 of 6 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 4 failures of our instrument; 1 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2404.11225.json · badge: /api/ran/2404.11225.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
hitsz-tmg/icl-state-vector canonical (classifier label)
classifier basis: census
5 ran · 1 no recorded run
FunctionStatusWhere it lives
get_data_layers Ran
ran; our contract draft was wrong, not the code
hitsz-tmg/icl-state-vector/selected_layers.py
pointer only (licence: NONE); the stored copy get_code serves, from HITsz-TMG/ICL-State-Vector, is pointer only (licence: NONE) · get_code("7fa4c0d4e9cee1af")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hitsz-tmg/icl-state-vector when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

metric_average Ran
ran, honoured the contract we drafted
hitsz-tmg/icl-state-vector/utils.py
pointer only (licence: NONE); the stored copy get_code serves, from HITsz-TMG/ICL-State-Vector, is pointer only (licence: NONE) · get_code("dc25dfef6f90b386")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hitsz-tmg/icl-state-vector when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

sea_born Ran
ran; our contract draft was wrong, not the code
hitsz-tmg/icl-state-vector/utils.py
pointer only (licence: NONE); the stored copy get_code serves, from HITsz-TMG/ICL-State-Vector, is pointer only (licence: NONE) · get_code("85ac527a9dce9de6")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hitsz-tmg/icl-state-vector when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

shuffle_train Ran
ran; our contract draft was wrong, not the code
hitsz-tmg/icl-state-vector/utils.py
pointer only (licence: NONE); the stored copy get_code serves, from HITsz-TMG/ICL-State-Vector, is pointer only (licence: NONE) · get_code("f4d8b3796ddaccdf")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hitsz-tmg/icl-state-vector when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

str2list Ran
ran; our contract draft was wrong, not the code
hitsz-tmg/icl-state-vector/state_vector_optimize.py
pointer only (licence: NONE); the stored copy get_code serves, from HITsz-TMG/ICL-State-Vector, is pointer only (licence: NONE) · get_code("3b34facc51914c48")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hitsz-tmg/icl-state-vector when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_optimizers Not yet run
unverified (harvested, no recorded run)
hitsz-tmg/icl-state-vector/optimizer.py
pointer only (licence: NONE); the stored copy get_code serves, from HITsz-TMG/ICL-State-Vector, is pointer only (licence: NONE) · get_code("f5d8f58d3af60f15")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hitsz-tmg/icl-state-vector when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 6 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 6 later) and 0 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
get_data_layers 1 other paper
1 later
2605.20730 (2026-05)
Distributional Alignment as a Criterion for Designing Task Vectors in In-Context Learning
get_optimizers 1 other paper
1 later
2605.20730 (2026-05)
Distributional Alignment as a Criterion for Designing Task Vectors in In-Context Learning
metric_average 1 other paper
1 later
2605.20730 (2026-05)
Distributional Alignment as a Criterion for Designing Task Vectors in In-Context Learning
sea_born 1 other paper
1 later
2605.20730 (2026-05)
Distributional Alignment as a Criterion for Designing Task Vectors in In-Context Learning
shuffle_train 1 other paper
1 later
2605.20730 (2026-05)
Distributional Alignment as a Criterion for Designing Task Vectors in In-Context Learning
str2list 1 other paper
1 later
2605.20730 (2026-05)
Distributional Alignment as a Criterion for Designing Task Vectors in In-Context Learning

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Large Language Models (LLMs) have exhibited an impressive ability to perform In-Context Learning (ICL) from only a few examples. Recent works have indicated that the functions learned by ICL can be represented through compressed vectors derived from the transformer. However, the working mechanisms and optimization of these vectors are yet to be thoroughly explored. In this paper, we address this gap by presenting a comprehensive analysis of these compressed vectors, drawing parallels to the parameters trained with gradient descent, and introduce the concept of state vector. Inspired by the works on model soup and momentum-based gradient descent, we propose inner and momentum optimization methods that are applied to refine the state vector progressively as test-time adaptation. Moreover, we simulate state vector aggregation in the multiple example setting, where demonstrations comprising numerous examples are usually too lengthy for regular ICL, and further propose a divide-and-conquer aggregation method to address this challenge. We conduct extensive experiments using Llama-2 and GPT-J in both zero-shot setting and few-shot setting. The experimental results show that our optimization method effectively enhances the state vector and achieves the state-of-the-art performance on diverse tasks. Code is available at https://github.com/HITsz-TMG/ICL-State-Vector

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2404.11225")
get_code_for_paper("2404.11225")
have("2404.11225")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2404.11225.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2404.11225.svg)](https://syntology.ai/paper/2404.11225)

Connect an agent — have() is free.