SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2301.01296 · CVPR · 2023

TinyMIM: An Empirical Study of Distilling MIM Pre-trained Models

Fangyun Wei, Zheng Zhang, Han Hu, Sucheng Ren

arXiv · PDF · Open in the Atlas

Code that ran

8 of 11 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (5 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 7 have no contract verdict; 0 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/2301.01296.json · badge: /api/ran/2301.01296.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
oliverrensu/d-igpt community
Papers with Code archive
6 ran · 1 no recorded run
OliverRensu/TinyMIM community
Papers with Code archive
2 ran · 1 no recorded run
copy not recorded community
not in the paper's declared repositories
0 ran · 1 no recorded run
FunctionStatusWhere it lives
Attention Ran
ran on a synthesized input
oliverrensu/d-igpt/DiGPT_torch/models_digpt.py
pointer only (licence: NONE) · get_code("6fb43d8ac6c1d00c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, oliverrensu/d-igpt 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.

Attention Ran
ran on a synthesized input
OliverRensu/TinyMIM/models_tinymim.py
pointer only (licence: NONE) · get_code("e861849da1498470")
How it ran

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

Block Ran
ran on a synthesized input · constructed an object; no result was computed
oliverrensu/d-igpt/DiGPT_torch/models_digpt.py
pointer only (licence: NONE) · get_code("3def779b7964615e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, oliverrensu/d-igpt 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.

Block Ran
ran on a synthesized input · constructed an object; no result was computed
OliverRensu/TinyMIM/models_tinymim.py
pointer only (licence: NONE) · get_code("01d6c22c6a63aed1")
How it ran

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

CrossAttention Ran
ran on a synthesized input · constructed an object; no result was computed
oliverrensu/d-igpt/DiGPT_torch/models_digpt.py
pointer only (licence: NONE) · get_code("ce2a200723aec3f8")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, oliverrensu/d-igpt 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.

DecoderBlock Ran
ran on a synthesized input · constructed an object; no result was computed
oliverrensu/d-igpt/DiGPT_torch/models_digpt.py
pointer only (licence: NONE) · get_code("3d96fefa337b0261")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, oliverrensu/d-igpt 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.

PatchEmbed Ran
ran on a synthesized input · constructed an object; no result was computed
oliverrensu/d-igpt/DiGPT_torch/models_digpt.py
pointer only (licence: NONE) · get_code("468a394a75068b28")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, oliverrensu/d-igpt 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_2d_sincos_pos_embed Ran
ran, honoured the contract we drafted
oliverrensu/d-igpt/DiGPT_torch/models_digpt.py
pointer only (licence: NONE) · get_code("5a37690a13a6157d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, oliverrensu/d-igpt 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.

DiGPT Not yet run
unverified (harvested, no recorded run)
oliverrensu/d-igpt/DiGPT_torch/models_digpt.py
pointer only (licence: NONE) · get_code("d86994f1871555f5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, oliverrensu/d-igpt 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.

TinyMIMViT Not yet run
unverified (harvested, no recorded run)
OliverRensu/TinyMIM/models_tinymim.py
pointer only (licence: NONE) · get_code("521a3b2b4735b6d4")
How it ran

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

get_2d_sincos_pos_embed_from_grid Not yet run
unverified (harvested, no recorded run)
this paper's copy was not recorded; identical code first harvested from Zhangwenyao1/DreamVLA
pointer only; the stored copy get_code serves, from Zhangwenyao1/DreamVLA, is pointer only (licence: NONE) · get_code("2884deadbb637c3e")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 11 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 3 the same month, 3 later) and 8 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_2d_sincos_pos_embed_from_grid
brick of this paper's assembly: helper
190 other papers
20 dated earlier, 3 the same month, 166 later, 1 same year, order not determinable · 65 only as an assembly brick
1807.10221 (2018-07)
Unified Perceptual Parsing for Scene Understanding
2105.12723 (2021-05)
Nested Hierarchical Transformer: Towards Accurate, Data-Efficient and Interpretable Visual Understanding
2111.06377 (2021-11)
Masked Autoencoders Are Scalable Vision Learners
and 187 more not named here
get_2d_sincos_pos_embed
brick of this paper's assembly: helper
95 other papers
15 dated earlier, 3 the same month, 76 later, 1 same year, order not determinable · 33 only as an assembly brick
1807.10221 (2018-07)
Unified Perceptual Parsing for Scene Understanding
2105.12723 (2021-05)
Nested Hierarchical Transformer: Towards Accurate, Data-Efficient and Interpretable Visual Understanding
2111.06377 (2021-11)
Masked Autoencoders Are Scalable Vision Learners
and 92 more not named here
PatchEmbed
brick of this paper's assembly: helper
10 other papers
6 dated earlier, 1 the same month, 3 later · 7 only as an assembly brick
2010.11929 (2020-10)
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
2103.10619 (2021-03)
Scalable Vision Transformers with Hierarchical Pooling
2106.02034 (2021-06)
DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification
and 7 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

Masked image modeling (MIM) performs strongly in pretraining large vision Transformers (ViTs). However, small models that are critical for real-world applications cannot or only marginally benefit from this pre-training approach. In this paper, we explore distillation techniques to transfer the success of large MIM-based pre-trained models to smaller ones. We systematically study different options in the distillation framework, including distilling targets, losses, input, network regularization, sequential distillation, etc, revealing that: 1) Distilling token relations is more effective than CLS token-and feature-based distillation; 2) An intermediate layer of the teacher network as target perform better than that using the last layer when the depth of the student mismatches that of the teacher; 3) Weak regularization is preferred; etc. With these findings, we achieve significant fine-tuning accuracy improvements over the scratch MIM pre-training on ImageNet-1K classification, using all the ViT-Tiny, ViT-Small, and ViTbase models, with +4.2%/+2.4%/+1.4% gains, respectively. Our TinyMIM model of base size achieves 52.2 mIoU in AE20K semantic segmentation, which is +4.1 higher than the MAE baseline. Our TinyMIM model of tiny size achieves 79.6% top-1 accuracy on ImageNet-1K image classification, which sets a new record for small vision models of the same size and computation budget. This strong performance suggests an alternative way for developing small vision Transformer models, that is, by exploring better training methods rather than introducing inductive biases into architectures as in most previous works. Code is available at https://github.com/OliverRensu/TinyMIM.

For agents

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

get_harvested_code_for_paper("2301.01296")
get_code_for_paper("2301.01296")
have("2301.01296")

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

curl https://syntology.ai/api/ran/2301.01296.json

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

[![Syntology run record](https://syntology.ai/api/ran/2301.01296.svg)](https://syntology.ai/paper/2301.01296)

Connect an agent — have() is free.