SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2103.03457 · ICLR · 2021

IOT: Instance-wise Layer Reordering for Transformer Structures

Jinhua Zhu, Yingce Xia, Lijun Wu, Tao Qin, Wengang Zhou, Houqiang Li, Tie-Yan Liu, Shufang Xie

arXiv · PDF · Open in the Atlas

Code that ran

3 of 5 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (3 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 2 failures of our instrument; 2 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/2103.03457.json · badge: /api/ran/2103.03457.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
instance-wise-ordered-transformer/iot canonical (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
instance-wise-ordered-transformer/IOT marked official in Papers with Code
Papers with Code archive
1 ran · 2 no recorded run
FunctionStatusWhere it lives
Embedding Ran
ran; our contract draft was wrong, not the code · constructed an object; no result was computed
instance-wise-ordered-transformer/iot/fairseq/models/transformer.py
pointer only (licence: NOASSERTION) · get_code("96cbb5e9ca5b6be0")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, instance-wise-ordered-transformer/iot (NOASSERTION). 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.

LayerNorm Ran
ran on a synthesized input · constructed an object; no result was computed
instance-wise-ordered-transformer/IOT/fairseq/modules/transformer_sentence_encoder_layer.py
pointer only (licence: NOASSERTION) · get_code("e994de3ecaaa1676")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, instance-wise-ordered-transformer/IOT (NOASSERTION). 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.

Linear Ran
ran; our contract draft was wrong, not the code · constructed an object; no result was computed
instance-wise-ordered-transformer/iot/fairseq/models/transformer.py
pointer only (licence: NOASSERTION) · get_code("8cd8cb0d1e9e63e4")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, instance-wise-ordered-transformer/iot (NOASSERTION). 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.

MultiheadAttention Not yet run
unverified (harvested, no recorded run)
instance-wise-ordered-transformer/IOT/fairseq/modules/transformer_sentence_encoder_layer.py
pointer only (licence: NOASSERTION) · get_code("b4aacbb45af4df12")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, instance-wise-ordered-transformer/IOT (NOASSERTION). 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.

TransformerSentenceEncoderLayer Not yet run
unverified (harvested, no recorded run)
instance-wise-ordered-transformer/IOT/fairseq/modules/transformer_sentence_encoder_layer.py
pointer only (licence: NOASSERTION) · get_code("b628e17c1c82b491")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, instance-wise-ordered-transformer/IOT (NOASSERTION). 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 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 3 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 3 later) and 2 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
Linear 58 other papers
14 dated earlier, 44 later · 5 only as an assembly brick
1409.0473 (2014-09)
Neural Machine Translation by Jointly Learning to Align and Translate
1706.03762 (2017-06)
Attention Is All You Need
1904.01681 (2019-04)
Augmented Neural ODEs
and 55 more not named here
Embedding 29 other papers
9 dated earlier, 20 later
1904.01681 (2019-04)
Augmented Neural ODEs
1906.12183 (2019-06)
Neural ODEs as the Deep Limit of ResNets with constant weights
2002.03184 (2020-02)
Time-aware Large Kernel Convolutions
and 26 more not named here
LayerNorm
brick of this paper's assembly: helper
4 other papers
4 later
2104.06022 (2021-04)
Lessons on Parameter Sharing across Layers in Transformers
2202.13277 (2022-02)
Learning the Beauty in Songs: Neural Singing Voice Beautifier
2205.07211 (2022-05)
GenerSpeech: Towards Style Transfer for Generalizable Out-Of-Domain Text-to-Speech
and 1 more not named here

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

With sequentially stacked self-attention, (optional) encoder-decoder attention, and feed-forward layers, Transformer achieves big success in natural language processing (NLP), and many variants have been proposed. Currently, almost all these models assume that the layer order is fixed and kept the same across data samples. We observe that different data samples actually favor different orders of the layers. Based on this observation, in this work, we break the assumption of the fixed layer order in Transformer and introduce instance-wise layer reordering into model structure. Our Instance-wise Ordered Transformer (IOT) can model variant functions by reordered layers, which enables each sample to select the better one to improve the model performance under the constraint of almost same number of parameters. To achieve this, we introduce a light predictor with negligible parameter and inference cost to decide the most capable and favorable layer order for any input sequence. Experiments on 3 tasks (neural machine translation, abstractive summarization, and code generation) and 9 datasets demonstrate consistent improvements of our method. We further show that our method can also be applied to other architectures beyond Transformer. Our code is released at Github 1 .

For agents

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

get_harvested_code_for_paper("2103.03457")
get_code_for_paper("2103.03457")
have("2103.03457")

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

curl https://syntology.ai/api/ran/2103.03457.json

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

[![Syntology run record](https://syntology.ai/api/ran/2103.03457.svg)](https://syntology.ai/paper/2103.03457)

Connect an agent — have() is free.