SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2310.00258 · 2023

NAYER: Noisy Layer Data Generation for Efficient and Effective Data-free Knowledge Distillation

arXiv · PDF · Open in the Atlas

Code that ran

7 of 10 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; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 7 failures of our instrument; 3 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/2310.00258.json · badge: /api/ran/2310.00258.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
tmtuan1307/nayer canonical (classifier label)
classifier basis: census
7 ran · 3 no recorded run
FunctionStatusWhere it lives
cross_entropy Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
tmtuan1307/nayer/datafree/criterions.py
pointer only (licence: NONE); the stored copy get_code serves, from liqiiiii/encapsulating-knowledge-in-one-prompt, is pointer only (licence: NONE) · get_code("5116e4067eb03c3e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, tmtuan1307/nayer 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.

custom_cross_entropy Ran
ran; our contract draft was wrong, not the code
tmtuan1307/nayer/datafree/synthesis/nayer.py
pointer only (licence: NONE) · get_code("9e49766535e8f9e0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, tmtuan1307/nayer 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.

find_classes Ran
ran; our contract draft was wrong, not the code
tmtuan1307/nayer/datafree/datasets/tiny_imagenet.py
pointer only (licence: NONE) · get_code("403277d0bfbb477b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, tmtuan1307/nayer 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.

jsdiv Ran
ran; our contract draft was wrong, not the code
tmtuan1307/nayer/datafree/criterions.py
pointer only (licence: NONE); the stored copy get_code serves, from liqiiiii/encapsulating-knowledge-in-one-prompt, is pointer only (licence: NONE) · get_code("f8610aafc779832f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, tmtuan1307/nayer 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.

kldiv Ran
ran; our contract draft was wrong, not the code
tmtuan1307/nayer/datafree/criterions.py
pointer only (licence: NONE); the stored copy get_code serves, from zj-jayzhang/DENSE, is pointer only (licence: NONE) · get_code("5418e150a16eff01")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, tmtuan1307/nayer 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.

make_dataset Ran
ran; our contract draft was wrong, not the code
tmtuan1307/nayer/datafree/datasets/tiny_imagenet.py
pointer only (licence: NONE) · get_code("5ded0879a886f3c4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, tmtuan1307/nayer 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.

register_hooks Ran
ran; our contract draft was wrong, not the code
tmtuan1307/nayer/datafree/hooks.py
pointer only (licence: NONE); the stored copy get_code serves, from liqiiiii/encapsulating-knowledge-in-one-prompt, is pointer only (licence: NONE) · get_code("d558beac7f489465")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, tmtuan1307/nayer 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.

advarsarial_classification_evaluator Not yet run
unverified (harvested, no recorded run)
tmtuan1307/nayer/datafree/evaluators.py
pointer only (licence: NONE) · get_code("1b7f09e4bbd308e1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, tmtuan1307/nayer 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.

classification_evaluator Not yet run
unverified (harvested, no recorded run)
tmtuan1307/nayer/datafree/evaluators.py
pointer only (licence: NONE) · get_code("081369ab7a329c47")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, tmtuan1307/nayer 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.

segmentation_evaluator Not yet run
unverified (harvested, no recorded run)
tmtuan1307/nayer/datafree/evaluators.py
pointer only (licence: NONE) · get_code("31a485e439cd35d5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, tmtuan1307/nayer 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 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 10 distinct functions with an identity, 7 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 7 later) and 3 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
find_classes 7 other papers
2 dated earlier, 5 later
2103.13027 (2021-03)
AutoMix: Unveiling the Power of Mixup for Stronger Classifiers
2209.04996 (2022-09)
Switchable Online Knowledge Distillation
2401.11687 (2024-01)
TIM: An Efficient Temporal Interaction Module for Spiking Transformer
and 4 more not named here
kldiv 3 other papers
1 dated earlier, 2 later
2112.12371 (2021-12)
DENSE: Data-Free One-Shot Federated Learning
2407.11902 (2024-07)
Encapsulating Knowledge in One Prompt
2409.01128 (2024-09)
Diffusion-Driven Data Replay: A Novel Approach to Combat Forgetting in Federated Class Continual Learning
make_dataset 3 other papers
1 dated earlier, 2 later
2103.13027 (2021-03)
AutoMix: Unveiling the Power of Mixup for Stronger Classifiers
2401.11687 (2024-01)
TIM: An Efficient Temporal Interaction Module for Spiking Transformer
2408.01952 (2024-08)
CACE-Net: Co-guidance Attention and Contrastive Enhancement for Effective Audio-Visual Event Localization
classification_evaluator 1 other paper
1 later
2407.11902 (2024-07)
Encapsulating Knowledge in One Prompt
cross_entropy 1 other paper
1 later
2407.11902 (2024-07)
Encapsulating Knowledge in One Prompt
jsdiv 1 other paper
1 later
2407.11902 (2024-07)
Encapsulating Knowledge in One Prompt
register_hooks 1 other paper
1 later
2407.11902 (2024-07)
Encapsulating Knowledge in One Prompt

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

Data-Free Knowledge Distillation (DFKD) has made significant recent strides by transferring knowledge from a teacher neural network to a student neural network without accessing the original data. Nonetheless, existing approaches encounter a significant challenge when attempting to generate samples from random noise inputs, which inherently lack meaningful information. Consequently, these models struggle to effectively map this noise to the ground-truth sample distribution, resulting in prolonging training times and low-quality outputs. In this paper, we propose a novel Noisy Layer Generation method (NAYER) which relocates the random source from the input to a noisy layer and utilizes the meaningful constant label-text embedding (LTE) as the input. LTE is generated by using the language model once, and then it is stored in memory for all subsequent training processes. The significance of LTE lies in its ability to contain substantial meaningful inter-class information, enabling the generation of high-quality samples with only a few training steps. Simultaneously, the noisy layer plays a key role in addressing the issue of diversity in sample generation by preventing the model from overemphasizing the constrained label information. By reinitializing the noisy layer in each iteration, we aim to facilitate the generation of diverse samples while still retaining the method's efficiency, thanks to the ease of learning provided by LTE. Experiments carried out on multiple datasets demonstrate that our NAYER not only outperforms the state-of-the-art methods but also achieves speeds 5 to 15 times faster than previous approaches. The code is available at https://github.com/tmtuan1307/nayer.

For agents

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

get_harvested_code_for_paper("2310.00258")
get_code_for_paper("2310.00258")
have("2310.00258")

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

curl https://syntology.ai/api/ran/2310.00258.json

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

[![Syntology run record](https://syntology.ai/api/ran/2310.00258.svg)](https://syntology.ai/paper/2310.00258)

Connect an agent — have() is free.